Spiking Neural Networks (SNNs) offer a promising direction for energy-efficient and brain-inspired computing, yet their vulnerability to adversarial perturbations remains poorly understood. In this work, we revisit the adversarial robustness of SNNs through the lens of temporal ensembling, treating the network as a collection of evolving sub-networks across discrete timesteps. This formulation uncovers two critical but underexplored challenges—the fragility of individual temporal sub-networks and the tendency for adversarial vulnerabilities to transfer across time. To overcome these limitations, we propose Robust Temporal self-Ensemble (RTE), a training framework that improves the robustness of each sub-network while reducing the temporal transferability of adversarial perturbations. RTE integrates both objectives into a unified loss and employs a stochastic sampling strategy for efficient optimization. Extensive experiments across multiple benchmarks demonstrate that RTE consistently outperforms existing training methods in robust-accuracy trade-off. Additional analyses reveal that RTE reshapes the internal robustness landscape of SNNs, leading to more resilient and temporally diversified decision boundaries. Our study highlights the importance of temporal structure in adversarial learning and offers a principled foundation for building robust spiking models.

Haibo Tong, Zeyang Yue, Feifei Zhao, Erliang Lin, Lu Jia, Ruolin Chen, Yinqian Sun, Qian Zhang, Yi Zeng. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Field-Programmable Gate Arrays (FPGAs) have been shown to be viable for Large Language Model (LLM) deployment, but they remain less competitive than embedded GPUs and NPUs for final edge products. This is largely because existing FPGA-based LLM accelerator prototypes rely on large, expensive FPGA devices to provide sufficient hardware resources for satisfactory performance, whereas edge products are highly cost-sensitive. In this work, we move beyond pure architectural prototyping to evaluate the feasibility of using low-cost FPGAs as the final implementation medium for LLM deployment. We propose Hummingbird+, which encompasses: (1) a compact embedded FPGA-based LLM accelerator designed to deliver comparable inference performance compared to embedded GPUs and NPUs, and (2) a custom Printed Circuit Board (PCB) built around a Zynq UltraScale XCZU2CG/3EG SoC, equipped with 24GB of memory and an expected Bill of Materials (BOMs) under \150 in mass production. Through extensive FPGA-centric optimizations, we significantly reduce the accelerator's resource consumption, enabling deployment on entry-level FPGAs with exceptional cost efficiency. On this platform, we successfully deploy the GPTQ 4-bit Qwen3-30B-A3B LLM, achieving a decoding speed of over 18 token/s and a prefill speed of over 50 token/s without further model compression. To our knowledge, this is the first demonstration of an FPGA-based edge product serving as a practical and cost-effective final implementation medium for LLM deployment.

As AI closely interacts with human society, it is crucial to ensure that its behavior is safe, altruistic, and aligned with human ethical and moral values. However, existing research on embedding ethical considerations into AI remains insufficient, and previous external constraints based on principles and rules are inadequate to provide AI with long-term stability and generalization capabilities. Emotional empathy intrinsically motivates altruistic behaviors aimed at alleviating others' negative emotions through emotional sharing and contagion mechanisms. Motivated by this, we draw inspiration from the neural mechanism of human emotional empathy-driven altruistic decision making, and simulate the shared self-other perception-mirroring-empathy neural circuits, to construct a brain-inspired emotional empathy driven altruistic decision-making model. Here, empathy directly impacts dopamine release to form intrinsic altruistic motivation. The proposed model exhibits consistent altruistic behaviors across three experimental settings: emotional contagion-integrated two agent altruistic rescue, multi-agent gaming, and robotic emotional empathy interaction scenarios. In-depth analyses validate the positive correlation between empathy levels and altruistic preferences (consistent with psychological behavioral experiment findings), while also demonstrating how interaction partners' empathy levels influence the agent's behavioral patterns. We further test the proposed model's performance and stability in moral dilemmas involving conflicts between self-interest and others'well-being, partially observable environments, and adversarial defense scenarios. This work provides preliminary exploration of human-like empathy-driven altruistic moral decision making, contributing potential perspectives for developing ethically aligned AI.

Spiking transformers are emerging as a promising architecture that combines the energy efficiency of Spiking Neural Networks (SNNs) with the powerful attention mechanisms of transformers. However, existing hardware accelerators lack support for spiking attention, exhibit limited throughput when exploiting fine-grained sparsity, and struggle with scalable parallelism in sparse computation. To address these challenges, we propose FireFly-T, a dual-engine overlay architecture that integrates a sparse engine for activation sparsity and a binary engine for spiking attention. In the sparse engine, we present a high-throughput sparse decoder that exploits fine-grained sparsity by concurrently extracting multiple non-zero spikes. To complement this, we introduce a scalable load balancing mechanism with weight dispatch and out-of-order execution, eliminating bank conflicts to support scalable multidimensional parallelism. In the binary engine, we leverage the byte-level write capability of SRAMs to efficiently manipulate the 3D dataflows required for spiking attention with minimal resource overhead. We also optimize the core AND-PopCount operation in spiking attention through a LUT6-based implementation, improving timing closure and reducing LUT utilization on Xilinx FPGAs. As an overlay architecture, FireFly-T further incorporates an orchestrator that dynamically manipulates input dataflows with flexible adaptation to diverse network topologies, while ensuring efficient resource utilization and maintaining high throughput. Experimental results demonstrate that our accelerator achieves 1.39× and 2.40× higher energy efficiency, as well as 4.21× and 7.10× greater DSP efficiency, compared to FireFly v2 and the transformer-enabled SpikeTA, respectively. These results highlight its potential as an efficient hardware platform for spiking transformers.

Dynamic Vision Sensors (DVS) capture event data with high temporal resolution and low power consumption, presenting a more efficient solution for visual processing in dynamic and real-time scenarios compared to conventional video capture methods. Event data augmentation serves as an essential method for overcoming the limitation of scale and diversity in event datasets. Our comparative experiments demonstrate that the two factors, spatial integrity and temporal continuity, can significantly affect the capacity of event data augmentation, which guarantee the maintenance of the sparsity and high dynamic range characteristics unique to event data. However, existing augmentation methods often neglect the preservation of spatial integrity and temporal continuity. To address this, we developed a novel event data augmentation strategy EventZoom, which employs a temporal progressive strategy, embedding transformed samples into the original samples through progressive scaling and shifting. The scaling process avoids the spatial information loss associated with cropping, while the progressive strategy prevents interruptions or abrupt changes in temporal information. We validated EventZoom across various supervised learning frameworks. The experimental results show that EventZoom consistently outperforms existing event data augmentation methods with SOTA performance. For the first time, we have concurrently employed Semi-supervised and Unsupervised learning to verify feasibility on event augmentation algorithms, demonstrating the applicability and effectiveness of EventZoom as a powerful event-based data augmentation tool in handling real-world scenes with high dynamics and variability environments.

Human beings often experience stress, which can significantly influence their performance. This study explores whether Large Language Models (LLMs) exhibit stress responses similar to those of humans and whether their performance fluctuates under different stress-inducing prompts. To investigate this, we developed a novel set of prompts, termed StressPrompt, designed to induce varying levels of stress. These prompts were derived from established psychological frameworks and carefully calibrated based on ratings from human participants. We then applied these prompts to several LLMs to assess their responses across a range of tasks, including instruction-following, complex reasoning, and emotional intelligence. The findings suggest that LLMs, like humans, perform optimally under moderate stress, consistent with the Yerkes-Dodson law. Notably, their performance declines under both low and high-stress conditions. Our analysis further revealed that these StressPrompts significantly alter the internal states of LLMs, leading to changes in their neural representations that mirror human responses to stress. This research provides critical insights into the operational robustness and flexibility of LLMs, demonstrating the importance of designing AI systems capable of maintaining high performance in real-world scenarios where stress is prevalent, such as in customer service, healthcare, and emergency response contexts. Moreover, this study contributes to the broader AI research community by offering a new perspective on how LLMs handle different scenarios and their similarities to human cognition.

The extremely high computational and storage demands of large language models have excluded most edge devices, which were widely used for efficient machine learning, from being viable options. A typical edge device usually only has 4GB of memory capacity and a bandwidth of less than 20GB/s, while a large language model quantized to 4-bit precision with 7B parameters already requires 3.5GB of capacity, and its decoding process is purely bandwidth-bound. In this paper, we aim to explore these limits by proposing a hardware accelerator for large language model (LLM) inference on the Zynq-based KV260 platform, equipped with 4GB of 64-bit 2400Mbps DDR4 memory. We successfully deploy a LLaMA2-7B model, achieving a decoding speed of around 5 token/s, utilizing 93.3% of the memory capacity and reaching 85% decoding speed of the theoretical memory bandwidth limit. To fully reserve the memory capacity for model weights and key-value cache, we develop the system in a bare-metal environment without an operating system. To fully reserve the bandwidth for model weight transfers, we implement a customized dataflow with an operator fusion pipeline and propose a data arrangement format that can maximize the data transaction efficiency. This research marks the first attempt to deploy a 7B level LLM on a standalone embedded field programmable gate array (FPGA) device. It provides key insights into efficient LLM inference on embedded FPGA devices and provides guidelines for future architecture design.

Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardware resources available in such environments. While embedded FPGAs have demonstrated performance and energy efficiency in traditional deep neural networks, their potential for LLM inference remains largely unexplored. Recent efforts to deploy LLMs on FPGAs have primarily relied on large, expensive cloud-grade hardware and have only shown promising results on relatively small LLMs, limiting their real-world applicability. In this work, we present Hummingbird, a novel FPGA accelerator designed specifically for LLM inference on embedded FPGAs. Hummingbird is smaller—targeting embedded FPGAs such as the KV260 and ZCU104 with 67% LUT, 39% DSP, and 42% power savings over existing research. Hummingbird is stronger—targeting LLaMA3-8B and supporting longer contexts, overcoming the typical 4GB memory constraint of embedded FPGAs through offloading strategies. Finally, Hummingbird is faster—achieving 4.8 tokens/s and 8.6 tokens/s for LLaMA3-8B on the KV260 and ZCU104 respectively, with 93-94% model bandwidth utilization, outperforming the prior 4.9 token/s for LLaMA2-7B with 84% bandwidth utilization baseline. We further demonstrate the viability of industrial applications by deploying Hummingbird on a cost-optimized Spartan UltraScale FPGA, paving the way for affordable LLM solutions at the edge.

Spiking Neural Networks (SNNs) hold promise for energy-efficient, biologically inspired computing. We identify substantial informatio loss during spike transmission, linked to temporal dependencies in traditional Leaky Integrate-and-Fire (LIF) neuron-a key factor potentially limiting SNN performance. Existing SNN architectures also underutilize modern GPUs, constrained by single-bit spike storage and isolated weight-spike operations that restrict computational efficiency. We introduce ${SpikePack}$, a neuron model designed to reduce transmission loss while preserving essential features like membrane potential reset and leaky integration. ${SpikePack}$ achieves constant $\mathcal{O}(1)$ time and space complexity, enabling efficient parallel processing on GPUs and also supporting serial inference on existing SNN hardware accelerators. Compatible with standard Artificial Neural Network (ANN) architectures, ${SpikePack}$ facilitates near-lossless ANN-to-SNN conversion across various networks. Experimental results on tasks such as image classification, detection, and segmentation show ${SpikePack}$ achieves significant gains in accuracy and efficiency for both directly trained and converted SNNs over state-of-the-art models. Tests on FPGA-based platforms further confirm cross-platform flexibility, delivering high performance and enhanced sparsity. By enhancing information flow and rethinking SNN-ANN integration, ${SpikePack}$ advances efficient SNN deployment across diverse hardware platforms.

As large language models (LLMs) become integral to various applications, ensuring both their safety and utility is paramount. Jailbreak attacks, which manipulate LLMs into generating harmful content, pose significant challenges to this balance. Existing defenses, such as prompt engineering and safety fine-tuning, often introduce computational overhead, increase inference latency, and lack runtime flexibility. Moreover, overly restrictive safety measures can degrade model utility by causing refusals of benign queries. In this paper, we introduce *Jailbreak Antidote*, a method that enables real-time adjustment of LLM safety preferences by manipulating a sparse subset of the model's internal states during inference. By shifting the model's hidden representations along a safety direction with varying strengths, we achieve flexible control over the safety-utility balance without additional token overhead or inference delays. Our analysis reveals that safety-related information in LLMs is sparsely distributed; adjusting approximately *5\%* of the internal state is as effective as modifying the entire state. Extensive experiments on nine LLMs (ranging from 2 billion to 72 billion parameters), evaluated against ten jailbreak attack methods and compared with six defense strategies, validate the effectiveness and efficiency of our approach. By directly manipulating internal states during reasoning, *Jailbreak Antidote* offers a lightweight, scalable solution that enhances LLM safety while preserving utility, opening new possibilities for real-time safety mechanisms in widely-deployed AI systems.

The hierarchical architecture has become a mainstream design paradigm for Vision Transformers (ViTs), with Patch Merging serving as the pivotal component that transforms a columnar architecture into a hierarchical one. Drawing inspiration from the brain's ability to integrate global and local information for comprehensive visual understanding, we propose Stepwise Patch Merging (SPM), which enhances the subsequent attention mechanism's ability to 'see' better. SPM consists of Multi-Scale Aggregation (MSA) and Guided Local Enhancement (GLE) striking a proper balance between long-range dependency modeling and local feature enhancement. Extensive experiments conducted on benchmark datasets, including ImageNet-1K, COCO, and ADE20K, demonstrate that SPM significantly improves the performance of various models, particularly in dense prediction tasks such as object detection and semantic segmentation. Meanwhile, experiments show that combining SPM with different backbones can further improve performance. The code has been released at https://github.com/Yonghao-Yu/StepwisePatchMerging.

The evolution of the human brain has led to the development of complex synaptic plasticity, enabling dynamic adaptation to a constantly evolving world. This progress inspires our exploration into a new paradigm for Spiking Neural Networks (SNNs): a Plasticity-Driven Learning Framework (PDLF). This paradigm diverges from traditional neural network models that primarily focus on direct training of synaptic weights, leading to static connections that limit adaptability in dynamic environments. Instead, our approach delves into the heart of synaptic behavior, prioritizing the learning of plasticity rules themselves. This shift in focus from weight adjustment to mastering the intricacies of synaptic change offers a more flexible and dynamic pathway for neural networks to evolve and adapt. Our PDLF does not merely adapt existing concepts of functional and Presynaptic-Dependent Plasticity but redefines them, aligning closely with the dynamic and adaptive nature of biological learning. This reorientation enhances key cognitive abilities in artificial intelligence systems, such as working memory and multitasking capabilities, and demonstrates superior adaptability in complex, real-world scenarios. Moreover, our framework sheds light on the intricate relationships between various forms of plasticity and cognitive functions, thereby contributing to a deeper understanding of the brain's learning mechanisms. Integrating this groundbreaking plasticity-centric approach in SNNs marks a significant advancement in the fusion of neuroscience and artificial intelligence. It paves the way for developing AI systems that not only learn but also adapt in an ever-changing world, much like the human brain.

Spiking Transformers have recently emerged as promising architectures for combining the efficiency of spiking neural networks with the representational power of self-attention. However, the lack of standardized implementations, evaluation pipelines, and consistent design choices has hindered fair comparison and principled analysis. In this paper, we introduce \textbf{STEP}, a unified benchmark framework for Spiking Transformers that supports a wide range of tasks, including classification, segmentation, and detection across static, event-based, and sequential datasets. STEP provides modular support for diverse components such as spiking neurons, input encodings, surrogate gradients, and multiple backends (e.g., SpikingJelly, BrainCog). Using STEP, we reproduce and evaluate several representative models, and conduct systematic ablation studies on attention design, neuron types, encoding schemes, and temporal modeling capabilities. We also propose a unified analytical model for energy estimation, accounting for spike sparsity, bitwidth, and memory access, and show that quantized ANNs may offer comparable or better energy efficiency. Our results suggest that current Spiking Transformers rely heavily on convolutional frontends and lack strong temporal modeling, underscoring the need for spike-native architectural innovations. The full code is available at: https://github.com/Fancyssc/STEP.

Developmental plasticity plays a prominent role in shaping the brain's structure during ongoing learning in response to dynamically changing environments. However, the existing network compression methods for deep artificial neural networks (ANNs) and spiking neural networks (SNNs) draw little inspiration from brain's developmental plasticity mechanisms, thus limiting their ability to learn efficiently, rapidly, and accurately. This paper proposed a developmental plasticity-inspired adaptive pruning (DPAP) method, with inspiration from the adaptive developmental pruning of dendritic spines, synapses, and neurons according to the "use it or lose it, gradually decay" principle. The proposed DPAP model considers multiple biologically realistic mechanisms (such as dendritic spine dynamic plasticity, activity-dependent neural spiking trace, and local synaptic plasticity), with additional adaptive pruning strategy, so that the network structure can be dynamically optimized during learning without any pre-training and retraining. Extensive comparative experiments show consistent and remarkable performance and speed boost with the extremely compressed networks on a diverse set of benchmark tasks for deep ANNs and SNNs, especially the spatio-temporal joint pruning of SNNs in neuromorphic datasets. This work explores how developmental plasticity enables complex deep networks to gradually evolve into brain-like efficient and compact structures, eventually achieving state-of-the-art (SOTA) performance for biologically realistic SNNs.

Spiking Neural Networks (SNNs), with their brain-inspired structure using discrete spikes instead of continuous activations, are gaining attention for their potential of efficient processing on neuromorphic chips. While current SNN hardware accelerators often prioritize temporal spike sparsity, exploiting sparse synaptic weights offers significant untapped potential for even greater efficiency. To address this, we propose FireFly-S, a Sparse extension of the FireFly series. This co-optimized software-hardware design focusing on leveraging dual-side sparsity for acceleration. On the software side, we propose a novel algorithmic optimization framework that combines gradient rewiring for pruning and modified Learned Step Size Quantization (LSQ) tailored for SNNs, which achieves remarkable weight sparsity exceeding 85% and enables efficient 4-bit quantization with negligible accuracy loss. On the hardware side, we present an efficient dual-side sparsity detector employing a Bitmap-based sparse decoding logic to pinpoint the positions of non-zero weights and input spikes. The logic allows for the direct bypassing of redundant computations, thereby enhancing computational efficiency. Different from the overlay architecture adopted by previous FireFly series, we adopt a parametric spatial architecture with inter-layer pipelining that can fully exploit the fine-grained programmability and reconfigurability of Field-Programmable Gate Arrays (FPGAs), enabling fast deployment for various models. A spatial-temporal dataflow is also proposed to support such inter-layer pipelining and avoid long-term temporal dependencies. In experiments conducted on the MNIST, DVS-Gesture and CIFAR-10 datasets, the FireFly-S model achieves 85-95% sparsity with 4-bit quantization and the hardware accelerator effectively leverages the dual-side sparsity, delivering outstanding performance metrics of 10,047 FPS/W on MNIST, 3,683 FPS/W on DVS-Gesture, and 2,327 FPS/W on CIFAR-10.

Spiking neural networks (SNNs) have been widely applied not only for their advantages in energy efficiency with discrete signal processing but also for their natural suitability to integrate multiscale biological plasticity. However, most SNNs still adopt the structure of the well-established deep neural networks (DNNs), with few attempts at implementing automatic neural architecture search (NAS) for SNNs. The neural motifs topology, modular regional structures, and global cross-brain region connections in the human brain are the product of natural evolution, serving as a perfect reference for designing brain-inspired SNN architecture. Here, we propose an efficient multiscale evolutionary NAS (MSE-NAS) for SNN, simultaneously considering micro-, meso-, and macro-scale brain topologies as the evolutionary search space and is supplemented with customized brain-inspired indirect evaluation (BIE) function, encoding scheme and genetic operations. This is the first instance that the evolutionary characteristics of microconnections and electrophysiological patterns have been incorporated into one single evolutionary framework. The proposal of MSE-NAS proves that the evolutionary structure and mechanism of the human brain can essentially help better handle artificial intelligence tasks, revealing the important value and key role of integrating evolutionary computation (EC) principles in optimizing biologically realistic neural models. Extensive experiments demonstrate that MSE-NAS achieves superior performance with shorter simulation steps on static datasets (CIFAR10 and CIFAR100) and neuromorphic datasets (CIFAR10-DVS and DVS128-Gesture). More importantly, the emergence of general capabilities, such as transferability and robustness brought about by evolution confirms the innovative progress and important value of EC in the field of brain-inspired intelligence.

Spiking neural networks (SNNs) are rich in spatio-temporal dynamics and are suitable for processing event-based neuromorphic data. However, event-based datasets are usually less annotated than static datasets. This small data scale makes SNNs prone to overfitting and limits their performance. In order to improve the generalization ability of SNNs on event-based datasets, we use static images to assist SNN training on event data. In this paper, we first discuss the domain mismatch problem encountered when directly transferring networks trained on static datasets to event data. We argue that the inconsistency of feature distributions becomes a major factor hindering the effective transfer of knowledge from static images to event data. To address this problem, we propose solutions in terms of two aspects: feature distribution and training strategy. Firstly, we propose a knowledge transfer loss, which consists of domain alignment loss and spatio-temporal regularization. The domain alignment loss learns domain-invariant spatial features by reducing the marginal distribution distance between the static image and the event data. Spatio-temporal regularization provides dynamically learnable coefficients for domain alignment loss by using the output features of the event data at each time step as a regularization term. In addition, we propose a sliding training strategy, which gradually replaces static image inputs probabilistically with event data, resulting in a smoother and more stable training for the network. We validate our method on neuromorphic datasets, including N-Caltech101, CEP-DVS, and N-Omniglot. The experimental results show that our proposed method achieves better performance on all datasets compared to the current state-of-the-art methods. Code is available at https://github.com/Brain-Cog-Lab/Transfer-for-DVS.

Spiking Neural Networks (SNNs) have been widely praised for their high energy efficiency and immense potential. However, comprehensive research that critically contrasts and correlates SNNs with quantized Artificial Neural Networks (ANNs) remains scant, often leading to skewed comparisons lacking fairness towards ANNs. This paper introduces a unified perspective, illustrating that the time steps in SNNs and quantized bit-widths of activation values present analogous representations. Building on this, we present a more pragmatic and rational approach to estimating the energy consumption of SNNs. Diverging from the conventional Synaptic Operations (SynOps), we champion the “Bit Budget” concept. This notion permits an intricate discourse on strategically allocating computational and storage resources between weights, activation values, and temporal steps under stringent hardware constraints. Guided by the Bit Budget paradigm, we discern that pivoting efforts towards spike patterns and weight quantization, rather than temporal attributes, elicits profound implications for model performance. Utilizing the Bit Budget for holistic design consideration of SNNs elevates model performance across diverse data types, encompassing static imagery and neuromorphic datasets. Our revelations bridge the theoretical chasm between SNNs and quantized ANNs and illuminate a pragmatic trajectory for future endeavors in energy-efficient neural computations.

Systolic architectures are widely embraced by neural network accelerators for their superior performance in highly parallelized computation. The DSP48E2s serve as dedicated arithmetic blocks in Xilinx Ultrascale series FPGAs and constitute a fundamental component in FPGA-based systolic matrix engines. Harnessing the full potential of DSP48E2s in architectural design can result in significant performance enhancements for systolic architectures on Ultrascale series FPGAs. This paper unveils several previously untapped DSP optimization techniques capable of further enhancing FPGA-based systolic matrix engines. We apply these techniques to two well-known systolic architectures: Google TPUv1 and Xilinx Vitis AI DPU. With the proposed techniques, our design achieves substantial resource and power reduction compared to the open-source TPUv1 FPGA implementation and the Vitis AI DPU implementation in the same parallelism setting. We also demonstrate the applicability of our techniques to neuromorphic hardware for supporting spiking neural network acceleration.

Efficient parallel computing has become a pivotal element in advancing artificial intelligence. Yet, the deployment of Spiking Neural Networks (SNNs) in this domain is hampered by their inherent sequential computational dependency. This constraint arises from the need for each time step’s processing to rely on the preceding step’s outcomes, significantly impeding the adaptability of SNN models to massively parallel computing environments. Addressing this challenge, our paper introduces the innovative Parallel Spiking Unit (PSU) and its two derivatives, the Input-aware PSU (IPSU) and Reset-aware PSU (RPSU). These variants skillfully decouple the leaky integration and firing mechanisms in spiking neurons while probabilistically managing the reset process. By preserving the fundamental computational attributes of the spiking neuron model, our approach enables the concurrent computation of all membrane potential instances within the SNN, facilitating parallel spike output generation and substantially enhancing computational efficiency. Comprehensive testing across various datasets, including static and sequential images, Dynamic Vision Sensor (DVS) data, and speech datasets, demonstrates that the PSU and its variants not only significantly boost performance and simulation speed but also augment the energy efficiency of SNNs through enhanced sparsity in neural activity. These advancements underscore the potential of our method in revolutionizing SNN deployment for high-performance parallel computing applications.

Decoding non-invasive brain recordings is pivotal for advancing our understanding of human cognition but faces challenges due to individual differences and complex neural signal representations. Traditional methods often require customized models and extensive trials, lacking interpretability in visual reconstruction tasks. Our framework integrates 3D brain structures with visual semantics using a *Vision Transformer 3D*. This unified feature extractor efficiently aligns fMRI features with multiple levels of visual embeddings, eliminating the need for subject-specific models and allowing extraction from single-trial data. The extractor consolidates multi-level visual features into one network, simplifying integration with Large Language Models (LLMs). Additionally, we have enhanced the fMRI dataset with diverse fMRI-image-related textual data to support multimodal large model development. Integrating with LLMs enhances decoding capabilities, enabling tasks such as brain captioning, complex reasoning, concept localization, and visual reconstruction. Our approach demonstrates superior performance across these tasks, precisely identifying language-based concepts within brain signals, enhancing interpretability, and providing deeper insights into neural processes. These advances significantly broaden the applicability of non-invasive brain decoding in neuroscience and human-computer interaction, setting the stage for advanced brain-computer interfaces and cognitive models.

Inspired by the information transmission process in the brain, Spiking Neural Networks (SNNs) have gained considerable attention due to their event-driven nature. However, as the network structure grows complex, managing the spiking behavior within the network becomes challenging. Networks with excessively dense or sparse spikes fail to transmit sufficient information, inhibiting SNNs from exhibiting superior performance. Current SNNs linearly sum presynaptic information in postsynaptic neurons, overlooking the adaptive adjustment effect of dendrites on information processing. In this study, we introduce the Dendritic Spatial Gating Module (DSGM), which scales and translates the input, reducing the loss incurred when transforming the continuous membrane potential into discrete spikes. Simultaneously, by implementing the Dendritic Temporal Adjust Module (DTAM), dendrites assign different importance to inputs of different time steps, facilitating the establishment of the temporal dependency of spiking neurons and effectively integrating multi-step time information. The fusion of these two modules results in a more balanced spike representation within the network, significantly enhancing the neural network's performance. This approach has achieved state-of-the-art performance on static image datasets, including CIFAR10 and CIFAR100, as well as event datasets like DVS-CIFAR10, DVS-Gesture, and N-Caltech101. It also demonstrates competitive performance compared to the current state-of-the-art on the ImageNet dataset.

Spiking Neural Networks (SNNs) are expected to be a promising alternative to Artificial Neural Networks (ANNs) due to their strong biological interpretability and high energy efficiency. Specialized SNN hardware offers clear advantages over general-purpose devices in terms of power and performance. However, there’s still room to advance hardware support for state-of-the-art (SOTA) SNN algorithms and improve computation and memory efficiency. As a further step in supporting high-performance SNNs on specialized hardware, we introduce FireFly v2, an FPGA SNN accelerator that can address the issue of non-spike operation in current SOTA SNN algorithms, which presents an obstacle in the end-to-end deployment onto existing SNN hardware. To more effectively align with the SNN characteristics, we design a spatiotemporal dataflow that allows four dimensions of parallelism and eliminates the need for membrane potential storage, enabling on-the-fly spike processing and spike generation. To further improve hardware acceleration performance, we develop a high-performance spike computing engine as a backend based on a systolic array operating at 500-600MHz. To the best of our knowledge, FireFly v2 achieves the highest clock frequency among all FPGA-based implementations. Furthermore, it stands as the first SNN accelerator capable of supporting non-spike operations, which are commonly used in advanced SNN algorithms. FireFly v2 has doubled the throughput and DSP efficiency when compared to our previous version of FireFly and it exhibits ×1.33 the DSP efficiency and ×1.42 the power efficiency compared to the current most advanced FPGA accelerators.

Children possess the ability to learn multiple cognitive tasks sequentially, which is a major challenge toward the long-term goal of artificial general intelligence. Existing continual learning frameworks are usually applicable to Deep Neural Networks (DNNs) and lack the exploration on more brain-inspired, energy-efficient Spiking Neural Networks (SNNs). Drawing on continual learning mechanisms during child growth and development, we propose Dynamic Structure Development of Spiking Neural Networks (DSD-SNN) for efficient and adaptive continual learning. When learning a sequence of tasks, the DSD-SNN dynamically assigns and grows new neurons to new tasks and prunes redundant neurons, thereby increasing memory capacity and reducing computational overhead. In addition, the overlapping shared structure helps to quickly leverage all acquired knowledge to new tasks, empowering a single network capable of supporting multiple incremental tasks (without the separate sub-network mask for each task). We validate the effectiveness of the proposed model on multiple class incremental learning and task incremental learning benchmarks. Extensive experiments demonstrated that our model could significantly improve performance, learning speed and memory capacity, and reduce computational overhead. Besides, our DSD-SNN model achieves comparable performance with the DNNs-based methods, and significantly outperforms the state-of-the-art (SOTA) performance for existing SNNs-based continual learning methods.

The prevalence of violence in daily life poses significant threats to individuals' physical and mental well-being. Using surveillance cameras in public spaces has proven effective in proactively deterring and preventing such incidents. However, concerns regarding privacy invasion have emerged due to their widespread deployment.To address the problem, we leverage Dynamic Vision Sensors (DVS) cameras to detect violent incidents and preserve privacy since it captures pixel brightness variations instead of static imagery. We introduce the Bullying10K dataset, encompassing various actions, complex movements, and occlusions from real-life scenarios. It provides three benchmarks for evaluating different tasks: action recognition, temporal action localization, and pose estimation. With 10,000 event segments, totaling 12 billion events and 255 GB of data, Bullying10K contributes significantly by balancing violence detection and personal privacy persevering. And it also poses a challenge to the neuromorphic dataset. It will serve as a valuable resource for training and developing privacy-protecting video systems. The Bullying10K opens new possibilities for innovative approaches in these domains.

High-quality and challenging event stream datasets play an important role in the design of an efficient event-driven mechanism that mimics the brain. Although event cameras can provide high dynamic range and low-energy event stream data, the scale is smaller and more difficult to obtain than traditional frame-based data, which restricts the development of neuromorphic computing. Data augmentation can improve the quantity and quality of the original data by processing more representations from the original data. This paper proposes an efficient data augmentation strategy for event stream data: EventMix. We carefully design the mixing of different event streams by Gaussian Mixture Model (GMM) to generate random 3D masks and achieve arbitrary shape mixing of event streams in the spatio-temporal dimension. By computing the relative distances of event streams, we propose a more reasonable way to assign labels to the mixed samples. The experimental results on multiple neuromorphic datasets have shown that our strategy can improve performance on neuromorphic classification tasks as well as neuromorphic human action recognition tasks both for ANNs and SNNs, and we have achieved state-of-the-art performance on DVS-CIFAR10, N-Caltech101, and DVS-Gesture datasets.

The backpropagation algorithm has promoted the rapid development of deep learning, but it relies on a large amount of labeled data and still has a large gap with how humans learn. The human brain can quickly learn various conceptual knowledge in a self-organized and unsupervised manner, accomplished through coordinating various learning rules and structures in the human brain. Spike-timing-dependent plasticity (STDP) is a general learning rule in the brain, but spiking neural networks (SNNs) trained with STDP alone is inefficient and perform poorly. In this paper, taking inspiration from short-term synaptic plasticity, we design an adaptive synaptic filter and introduce the adaptive spiking threshold as the neuron plasticity to enrich the representation ability of SNNs. We also introduce an adaptive lateral inhibitory connection to adjust the spikes balance dynamically to help the network learn richer features. To speed up and stabilize the training of unsupervised spiking neural networks, we design a samples temporal batch STDP (STB-STDP), which updates weights based on multiple samples and moments. By integrating the above three adaptive mechanisms and STB-STDP, our model greatly accelerates the training of unsupervised spiking neural networks and improves the performance of unsupervised SNNs on complex tasks. Our model achieves the current state-of-the-art performance of unsupervised STDP-based SNNs in the MNIST and FashionMNIST datasets. Further, we tested on the more complex CIFAR10 dataset, and the results fully illustrate the superiority of our algorithm. Our model is also the first work to apply unsupervised STDP-based SNNs to CIFAR10. At the same time, in the small-sample learning scenario, it will far exceed the supervised ANN using the same structure.

Spiking neural networks (SNNs) have been widely used due to their strong biological interpretability and high-energy efficiency. With the introduction of the backpropagation algorithm and surrogate gradient, the structure of SNNs has become more complex, and the performance gap with artificial neural networks (ANNs) has gradually decreased. However, most SNN hardware implementations for field-programmable gate arrays (FPGAs) cannot meet arithmetic or memory efficiency requirements, which significantly restricts the development of SNNs. They do not delve into the arithmetic operations between the binary spikes and synaptic weights or assume unlimited on-chip RAM resources using overly expensive devices on small tasks. To improve arithmetic efficiency, we analyze the neural dynamics of spiking neurons, generalize the SNN arithmetic operation to the multiplex-accumulate operation, and propose a high-performance implementation of such operation by utilizing the DSP48E2 hard block in Xilinx Ultrascale FPGAs. To improve memory efficiency, we design a memory system to enable efficient synaptic weights and membrane voltage memory access with reasonable on-chip RAM consumption. Combining the above two improvements, we propose an FPGA accelerator that can process spikes generated by the firing neurons on-the-fly (FireFly). FireFly is the first SNN accelerator that incorporates DSP optimization techniques into SNN synaptic operations. FireFly is implemented on several FPGA edge devices with limited resources but still guarantees a peak performance of 5.53 TOP/s at 300 MHz. As a lightweight accelerator, FireFly achieves the highest computational density efficiency compared with existing research using large FPGA devices.

Spiking neural network (SNN), as a brain-inspired energy-efficient neural network, has attracted the interest of researchers. While the training of spiking neural networks is still an open problem. One effective way is to map the weight of trained ANN to SNN to achieve high reasoning ability. However, the converted spiking neural network often suffers from performance degradation and a considerable time delay. To speed up the inference process and obtain higher accuracy, we theoretically analyze the errors in the conversion process from three perspectives: the differences between IF and ReLU, time dimension, and pooling operation. We propose a neuron model for releasing burst spikes, a cheap but highly efficient method to solve residual information. In addition, Lateral Inhibition Pooling (LIPooling) is proposed to solve the inaccuracy problem caused by MaxPooling in the conversion process. Experimental results on CIFAR and ImageNet demonstrate that our algorithm is efficient and accurate. For example, our method can ensure nearly lossless conversion of SNN and only use about 1/10 (less than 100) simulation time under 0.693x energy consumption of the typical method. Our code is available at https://github.com/Brain-Inspired-Cognitive-Engine/Conversion_Burst.

Spiking neural network (SNN) has attracted much attention due to its powerful spatio-temporal information representation ability. Capsule Neural Network (CapsNet) does well in assembling and coupling features of different network layers. Here, we propose Spiking CapsNet by combining spiking neurons and capsule structures. In addition, we propose a more biologically plausible Spike Timing Dependent Plasticity routing mechanism. The coupling ability is further improved by fully considering the spatio-temporal relationship between spiking capsules of the low layer and the high layer. We have verified experiments on the MNIST, FashionMNIST, and CIFAR10 datasets. Our algorithm still shows comparable performance concerning other excellent SNNs with typical structures (convolutional, fully-connected) on these classification tasks. Our Spiking CapsNet combines SNN and CapsNet’s strengths and shows strong robustness to noise and affine transformation. By adding different Salt-Pepper and Gaussian noise to the test dataset, the experimental results demonstrate that our algorithm is more resistant to noise than other approaches. As well, our Spiking CapsNet shows strong generalization to affine transformation on the AffNIST dataset. Our code is available at https://github.com/BrainCog-X/Brain-Cog.

Neural networks with a large number of parameters are prone to overfitting problems when trained on a relatively small training set. Introducing weight penalties of regularization is a promising technique for solving this problem. Taking inspiration from the dynamic plasticity of dendritic spines, which plays an important role in the maintenance of memory, this letter proposes a brain-inspired developmental neural network based on dendritic spine dynamics (BDNN-dsd). The dynamic structure changes of dendritic spines include appearing, enlarging, shrinking, and disappearing. Such spine plasticity depends on synaptic activity and can be modulated by experiences-in particular, long-lasting synaptic enhancement/suppression (LTP/LTD), coupled with synapse formation (or enlargement)/elimination (or shrinkage), respectively. Subsequently, spine density characterizes an approximate estimate of the total number of synapses between neurons. Motivated by this, we constrain the weight to a tunable bound that can be adaptively modulated based on synaptic activity. Dynamic weight bound could limit the relatively redundant synapses and facilitate the contributing synapses. Extensive experiments demonstrate the effectiveness of our method on classification tasks of different complexity with the MNIST, Fashion MNIST, and CIFAR-10 data sets. Furthermore, compared to dropout and L2 regularization algorithms, our method can improve the network convergence rate and classification performance even for a compact network.

Spiking neural networks (SNNs) transmit information through discrete spikes that perform well in processing spatial-temporal information. Owing to their nondifferentiable characteristic, difficulties persist in designing SNNs that deliver good performance. SNNs trained with backpropagation have recently exhibited impressive performance by using gradient approximation. However, their performance on complex tasks remains significantly inferior to that of deep neural networks. By taking inspiration from autapses in the brain that connect spiking neurons with a self-feedback connection, we apply adaptive time-delayed self-feedback to the membrane potential to regulate the precision of the spikes. We also strike a balance between the excitatory and inhibitory mechanisms of neurons to dynamically control the output of spiking neurons. By combining these two mechanisms, we propose a deep SNN with adaptive self-feedback and balanced excitatory and inhibitory neurons (BackEISNN). The results of experiments on several standard datasets show that the two modules not only accelerate the convergence of the network but also increase its accuracy. Our model achieved state-of-the-art performance on the MNIST, Fashion-MNIST, and N-MNIST datasets. The proposed BackEISNN also achieved remarkably good performance on the CIFAR10 dataset while using a relatively light structure that competes against state-of-the-art SNNs.

In today's field of artificial intelligence, the plausibility of neural networks still lacks breakthrough. We believe one reason is that the current deep neural network method based on the framework of statistical learning, in essence, only uses the correlation between the data to make predictions, different from human beings who complete reasoning and decision-making by invariably induce the causality between propositions. To solve this problem, previous researchers have proposed some causal reasoning approaches based on the causal graphs. Inspired by the human brain, we propose Causal Reasoning Spiking Neural Network(CRSNN) to implement the causal reasoning with STDP learning rule and population coding mechanism. After the verification experiment in the basic case, we show the possibility of implementation causal reasoning with SNN. As far as we know, this is the first time that SNN is used to complete causal reasoning tasks, which is an essential topic both in cognitive neuroscience and artificial intelligence.

It is suggested from neuroscience that the response of V1 neurons in primate visual streams behaves quite like Gabor filters. As an inspiration from primate neural circuits to artificial neural networks, we propose to replace the first layer as a series of Gabor filters in convolutional neural networks. To enhance the performance of the neural network, we introduce a lateral inhibitory mechanism in Gabor filters, enlightened from the research results of neuroscience. To improve performance, we explore a parameter space and search the best suited parameters using cross validation. Experimental results demonstrate that the accuracy can basically match the results of the original convolutional neural networks. However, the adoption of Gabor filters can greatly reduce the time of training, as well as the memory and storage cost.

Convolutional neural networks (CNN) based trackers have been widely employed in visual object tracking due to their powerful representations. Features from different CNN layers encode different information. Deeper layers contain more semantic information, while the resolution is too coarse to localize the target. Shallower layers carry more detail information but are less robust for appearance variations. In this paper, we propose an algorithm which incorporates the Spatial and Temporal attention to take full advantage of the Hierarchical Convolutional Features for Tracking (STHCFT). We firstly learn correlation filters on each convolutional layer. Based on the spatial attention inspired by the paraventricular thalamus (PVT) in the brain, we choose the most important layer to build the base response, and the others to be the auxiliary responses. In addition, we make full use of the temporal attention to determine the weights of the auxiliary responses. Finally, the target is located by the maximum value of the fused responses. Extensive experimental results on the benchmark OTB-2013 and OTB-2015 have shown the proposed algorithm performs favorably against several state-of-the-art trackers.

Many efforts have been taken to train spiking neural networks (SNNs), but most of them still need improvements due to the discontinuous and non-differential characteristics of SNNs. While the mammalian brains solve these kinds of problems by integrating a series of biological plasticity learning rules. In this paper, we will focus on two biological plausible methodologies and try to solve these catastrophic training problems in SNNs. Firstly, the biological neural network will try to keep a balance between inputs and outputs on both the neuron and the network levels. Secondly, the biological synaptic weights will be passively updated by the changes of the membrane potentials of the neighbour-hood neurons, and the plasticity of synapses will not propagate back to other previous layers. With these biological inspirations, we propose Voltage-driven Plasticity-centric SNN (VPSNN), which includes four steps, namely: feed forward inference, unsupervised equilibrium state learning, supervised last layer learning and passively updating synaptic weights based on spike-timing dependent plasticity (STDP). Finally we get the accuracy of 98.52% on the hand-written digits classification task on MNIST. In addition, with the help of a visualization tool, we try to analyze the black box of SNN and get better understanding of what benefits have been acquired by the proposed method.

Due to the nature of Spiking Neural Networks (SNNs), it is challenging to be trained by biologically plausible learning principles. The multi-layered SNNs are with non-differential neurons, temporary-centric synapses, which make them nearly impossible to be directly tuned by back propagation. Here we propose an alternative biological inspired balanced tuning approach to train SNNs. The approach contains three main inspirations from the brain: Firstly, the biological network will usually be trained towards the state where the temporal update of variables are equilibrium (e.g. membrane potential); Secondly, specific proportions of excitatory and inhibitory neurons usually contribute to stable representations; Thirdly, the short-term plasticity (STP) is a general principle to keep the input and output of synapses balanced towards a better learning convergence. With these inspirations, we train SNNs with three steps: Firstly, the SNN model is trained with three brain-inspired principles; then weakly supervised learning is used to tune the membrane potential in the final layer for network classification; finally the learned information is consolidated from membrane potential into the weights of synapses by Spike-Timing Dependent Plasticity (STDP). The proposed approach is verified on the MNIST hand-written digit recognition dataset and the performance (the accuracy of 98.64%) indicates that the ideas of balancing state could indeed improve the learning ability of SNNs, which shows the power of proposed brain-inspired approach on the tuning of biological plausible SNNs.

Text generation is a typical nature language processing task, and is the basis of machine translation and question answering. Deep learning techniques can get good performance on this task under the condition that huge number of parameters and mass of data are available for training. However, human beings do not learn in this way. People combine knowledge learned before and something new with only few samples. This process is called one-shot learning. In this paper, we propose a neocortex based computational model, Semantic Hierarchical Temporal Memory model (SHTM), for one-shot text generation. The model is refined from Hierarchical Temporal Memory model. LSTM is used for comparative study. Results on three public datasets show that SHTM performs much better than LSTM on the measures of mean precision and BLEU score. In addition, we utilize SHTM model to do question answering in the fashion of text generation and verifying its superiority.

Human beings receive stimulations in primary sensory cortex and transfer them to higher brain regions automatically. What happened in this procedure? In this paper, we will focus on one of these regions (hippocampus) and try to simulate its working procedure by building an HMSNN (Hippocampus inspired Memory Spiking Neural Network) model. Dentate Gyrus (DG) and Cornu Ammonis area 3 (CA3) are the main regions of hippocampus and will be simulated by feed forward Spiking Neural Network (SNN) and recurrent Hopfield-like network respectively. From the structural perspective, the computational unit and the connectivity between neurons in HMSNN are all consistent with the anatomical-experimental results in hippocampus. From the functional perspective, the multi-scale memory formation, memory abstraction and memory retention will be shown in HMSNN model. In addition, the HMSNN is tested on MNIST handwritten digit dataset (with static images) and robot walking dataset (with dynamical images). The experimental result shows that: biological neural circuit inspired HMSNN shows comparable classification performance on both datasets compared to the state-of-art convolutional neural networks (CNNs), and shows significantly better performance compared to CNN when noises are introduced to the original images.

Given the explosive growth of scientific information and the fast advancement of research fields, researchers may not be able to find the most promising topics to combine with their current research and may be trapped in a few familiar research topics without creative ideas. Many studies of recommendation system make the effort to address the above problem, but they ignore the different styles of users and generate the recommendation results based on a common strategy. In this paper, we propose a framework to generate the adaptive recommendation results according to the research styles of users. Our framework contains 3 main parts, the research topic ontology construction, trend prediction and recommendation. First of all, the Fun of Academic Research Ontology (FARO), which has the capacity of describing dynamic and static research features and building a social network, is constructed to organize entities about academic research. Secondly, this paper predicts the popularity variation of research topics with the neural network model. Finally, some adaptive topics are recommended to specific researchers according to the evaluation of their research styles. Basically, this paper is inspired by the associative thinking of human brain to combine the advantages of Web knowledge representation language and the neural network to execute the prediction and recommendation. We test our results based on the publication data of IEEE and Springer. The experimental results demonstrate that our prediction model has a good generalization performance. A questionnaire survey is carried out to assess the recommendation results, and the result shows the feasibility of our method.

Brain-inspired algorithms such as convolutional neural network (CNN) have helped machine vision systems to achieve state-of-the-art performance for various tasks (e.g. image classification). However, CNNs mainly rely on local features (e.g. hierarchical features of points and angles from images), while important global structured features such as contour features are lost. Global understanding of natural objects is considered to be essential characteristics that the human visual system follows, and for developing human-like visual systems, the lost of consideration from this perspective may lead to inevitable failure on certain tasks. Experimental results have proved that well-trained CNN classifier cannot correctly distinguish fooling images (in which some local features from the natural images are chaotically distributed) from natural images. For example, a picture that is composed of yellow–black bars will be recognized as school bus with very high confidence by CNN. On the contrary, human visual system focuses on both the texture and contour features to form representation of images and would not mis-take them. In order to solve the upper problem, we propose a neural network model, named as histogram of oriented gradient (HOG) improved CNN (HCNN), that combines local and global features towards human-like classification based on CNN and HOG. The experimental results on MNIST datasets and part of ImageNet datasets show that HCNN outperforms traditional CNN for object classification with fooling images, which indicates the feasibility, accuracy and potential effectiveness of HCNN for solving image classification problem.

The human stereo vision process begins in primary visual cortex where complex cells are deemed as disparity detectors. Besides correct matches, complex cells could also respond to false matches which cause ambiguous depth perception. This reveals that there exist some inherent mechanisms in the higher visual processing areas for eliminating false matches and thus recovering true disparity. Due to the least understanding of this hierarchical process, this paper aims to investigate this problem by proposing a deep stereo vision model. There are three characteristics of the proposed model: 1) the obtained disparity maps become more accurate from lower layers to higher layers; 2) it tends to promote neural responses of correct matches while inhibiting those of incorrect matches; 3) it generalizes well to unseen data.

Early stages of the human visual system consist of retinal cones, retinal ganglion cells(RGC), lateral geniculate nucleus(LGN) and V1. Modeling early visual stages is conducive to reveal the mechanism of visual signal preprocessing and representation inside brain, as well as settle challenges artificial intelligence confronts. However, a majority of previous work often models RGC/LGN or V1 separately, seldom modeling them together hierarchically. In order to be consistent with the biological results, we propose HEVS (a Hierarchical computational model for Early stages of the Visual System), a feedforward neural network composed of three layers, which represent receptor neurons, RGC/LGN and V1 successively. Exactly as the visual system, the proposed locally connected model is derived in the unsupervised scenario on natural images and trained in the bottom-up order. In order to learn the two connection weights among three layers, we formulate two optimization problems based on the reconstruction error and sparse learning. Unlike traditional models on RGC/LGN, we perform weighted similarity measuring as a regular term to simulate the strong correlations among nearby neuron spikes in the same stage. Different from existing researches on modeling V1 neurons from image pixels directly, we transmit the signals represented by the ganglion cells in the second layer to the V1 neurons in the third layer. Moreover, solutions to these objectives are provided as well. Experimental results demonstrate that the characteristics of HEVS are consistent with those of the corresponding biological stages. The results further verify the performance of HEVS on dealing with the de-blurring and de-noising tasks.

Massive amounts of data are being generated on social media sites, such as Twitter and Facebook. These data can be used to better understand people (e.g., personality traits, perceptions, and preferences) and predict their behavior. As a result, a deeper understanding of users and their behavior can benefit a wide range of intelligent applications, such as advertising, social recommender systems, and personalized knowledge management. These applications will also benefit individual users themselves and optimize their experience across a wide variety of domains, such as retail, healthcare, and education. Since mining and understanding user behavior from social media often requires interdisciplinary effort, including machine learning, text mining, human-computer interaction, and social science, our workshop aims to bring together researchers and practitioners from multiple fields to discuss the creation of deeper models of individual users by mining the content that they publish and the social networking behavior that they exhibit.

We organize and present the 5th version of the International Workshop on Web-scale Knowledge Representation, Retrieval and Reasoning (Web-KR 2014) as a continuous effort to discuss and provide possible theories and techniques to deal with the barriers for knowledge processing at Web scale. This workshop was held in conjunction with the 2014 ACM International Conference on Information and Knowledge Management (CIKM 2014) on November 3rd, 2014 in Shanghai, China. Compared to previous workshops under the same title, accepted papers of this workshop covers even wider topics in the field. The contributions focus on semantic knowledge extraction, representation, knowledge clustering, inconsistency checking, entity relatedness and linking, query suggestions, etc. Many new approaches are proposed to investigate these topics in the context of Web-scale resources. This summary introduces the major contributions of accepted papers in the Web-KR 2014 workshop.

As a continuous effort for organizing discussions and providing possible theories and techniques to deal with the barriers for knowledge processing at Web scale, the 2013 International Workshop on Web-scale Knowledge Representation, Retrieval and Reasoning (Web-KR 2013) was held in conjunction with the 2013 ACM International Conference on Information and Knowledge Management (CIKM 2013) on November 1st, 2013 at Burlingame, CA, United States. This is the 4th version of the Web-KR workshop. As in previous workshops under the same title, accepted papers of this workshop cover many important topics in the field. This year, the contributions focus on multi-faceted understanding of Web knowledge sources, Web entity linking, deep Web knowledge acquisition, and Web-scale stream reasoning. Many new approaches are proposed to deal with these problems in the context of large scale Web resources. This summary introduces the major contributions of accepted papers in the Web-KR 2013 workshop.

This paper investigates on entity conceptualization and its applications based on a Web-scale knowledge base. Firstly, inspired by the spreading activation theory from Cognitive Psychology, a model for entity conceptualization in a context-free setting is introduced. Secondly, an extended model with additional consideration on environmental factors is proposed for context-sensitive entity conceptualization. With entity conceptualization, we propose a method for generating concept-level knowledge based on conceptualization of large-scale factual triple form knowledge acquired from the Wiki-Encyclopedias. We provide several typicality measures for understanding concept-level knowledge in different perspectives. Finally, we discuss how the concept-level knowledge and its typicality measures can be used for finding incorrect knowledge contributed by Wiki-Encyclopedia contents contributors.

The rapid and perpetual growth of knowledge on the Web has given rise to many grand challenges (such as scalability, inconsistency, uncertainty, distribution and dynamics) for traditional knowledge processing methods and systems. Knowledge representation, retrieval and reasoning methods need to evolve and adapt to the Web to face these challenges and make this vast, heterogenous knowledge useful and accessible. In this light, the International Workshop on Web-scale Knowledge Representation, Retrieval, and Reasoning (Web-KR) is initiated. This workshop serves as the third one in this workshop series. This summary discusses the scope of Web-KR and introduces the advances in this field through the accepted papers in the Web-KR 2012 workshop, co-located with CIKM 2012.

Web-based collaborative knowledge bases collect human knowledge through the Web. They can be used for answering questions or support different knowledge intensive applications on the Web. From a statistical point of view, they usually reveal some interesting characteristics, which can be acquired through statistical analysis to get deeper understanding of these kinds of knowledge bases. In this paper, we build a semantic knowledge base using the triples extracted from a Chinese wiki Web site called Baidu Baike. We make an investigation on the statistical results on the building process and structural characteristics of this knowledge base. We explain what we have observed and inferred and how the conclusion can help to understand the process of building large scale Web based collaborative knowledge bases and how to make them better.

For most scientists, their research interests are dynamically changing all the time. Through an analysis of research interests, we find that all the changes are with some characteristics. Plus, the research interests in the dynamic changing process are not isolated, instead, they are interconnected as a whole to form a holistic structure. We introduce some measurement parameters to track and detect the evolution process, we analyze the structural and dynamic characteristics of research interests through statistical analysis, and we also investigate on how they affect each other. As a possible application, we use observed characteristics of research interests to refine literature search on the Web, which shows that diverse user needs can be satisfied using various observations from research interests as constraints for vague queries. Such effort may provide some hints and various methods to support personalized search, and can be considered as a step forward user centric knowledge retrieval on the Web.

A Search Support Engine (SSE) is implemented based on the basic principles of Information Retrieval Support Systems (IRSS) and Information Seeking Support Systems (ISSS). An SSE aims at meeting the diversity needs from different users, providing various supporting functionalities, tools, etc. for users to perform various tasks beyond the traditional search and browsing provided by current search engines. As an illustrative example, we developed a DBLP search support engine (DBLP-SSE), and we discuss some concrete supporting functionalities, namely, search refinement support, domain analysis support, etc. Each of the functionality focus on a unique perspective supporting users finding useful information and knowledge from the DBLP dataset. The search support engine can be considered as a step towards Knowledge Retrieval (KR) and Web Intelligence (WI).

With the ever-increasing growth of data and information, finding the right knowledge becomes a real challenge and an urgent task. Traditional data and information retrieval systems that support the current web are no longer adequate for knowledge seeking tasks. Knowledge retrieval systems will be the next generation of retrieval system serving those purposes. Basic issues of knowledge retrieval systems are examined and a conceptual framework of such systems is proposed. Theories and Technologies such as theory of knowledge, machine learning and knowledge discovery, psychology, logic and inference, linguistics, etc. are briefly mentioned for the implementation of knowledge retrieval systems. Two applications of knowledge retrieval in rough sets and biomedical domains are presented.