Processing long visual token sequences poses a significant computational burden on Multimodal Large Language Models (MLLMs). While token pruning offers a path to acceleration, we find that current methods, while adequate for general understanding, catastrophically fail on fine-grained localization tasks. We attribute this failure to the inherent flaws of the two prevailing strategies: importance-based methods suffer from a strong positional bias, an inherent model artifact that distracts from semantic content, while diversity-based methods exhibit structural blindness, disregarding the user's prompt and spatial redundancy. To address this, we introduce D²Pruner, a framework that rectifies these issues by uniquely combining debiased importance with a structural pruning mechanism. Our method first secures a core set of the most critical tokens as pivots based on a debiased attention score. It then performs a Maximal Independent Set (MIS) selection on the remaining tokens, which are modeled on a hybrid graph where edges signify spatial proximity and semantic similarity. This process iteratively preserves the most important and available token while removing its neighbors, ensuring that the supplementary tokens are chosen to maximize importance and diversity. Extensive experiments demonstrate that D²Pruner achieves exceptional efficiency and fidelity.

Recent advancements in Large Language Models (LLMs) have shown that it is promising to utilize Process Reward Models (PRMs) as verifiers to enhance the performance of LLMs. However, current PRMs face three key challenges: (1) limited process supervision and generalization capabilities, (2) dependence on scalar value prediction without leveraging the generative abilities of LLMs, and (3) inability to scale the test-time compute of PRMs. In this work, we introduce GenPRM, a generative process reward model that performs explicit Chain-of-Thought (CoT) reasoning with code verification before providing judgment for each reasoning step. To obtain high-quality process supervision labels and rationale data, we propose Relative Progress Estimation (RPE) and a rationale synthesis framework that incorporates code verification. Experimental results on ProcessBench and several mathematical reasoning tasks show that GenPRM significantly outperforms prior PRMs with only 23K training data from MATH dataset. Through test-time scaling, a 1.5B GenPRM outperforms GPT-4o, and a 7B GenPRM surpasses Qwen2.5-Math-PRM-72B on ProcessBench. Additionally, GenPRM demonstrates strong abilities to serve as a critic model for policy model refinement. This work establishes a new paradigm for process supervision that bridges the gap between PRMs and critic models in LLMs.

Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Shuang Cheng, Yuhua Jiang, Zineng Zhou, Dawei Liu, Tao Wang, Linfeng Zhang, Biqing Qi, Bowen Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Yuhua Jiang, Shuang Cheng, Yihao Liu, Ermo Hua, Che Jiang, Weigao Sun, Yu Cheng, Feifei Gao, Biqing Qi, Bowen Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Fangyuan Li, Pengfei Li, Shijie Wang, Junqi Gao, Jianxing Liu, Biqing Qi, Yuqiang Li. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Pengfei Li, Shijie Wang, Fangyuan Li, Yikun Fu, Kaifeng Liu, Kaiyan Zhang, Dazhi Zhang, Yuqiang Li, Biqing Qi, Bowen Zhou. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

Binary Neural Networks (BNNs) have garnered significant attention due to their immense potential for deployment on edge devices. However, the non-differentiability of the quantization function poses a challenge for the optimization of BNNs, as its derivative cannot be backpropagated. To address this issue, hypernetwork based methods, which utilize neural networks to learn the gradients of non-differentiable quantization functions, have emerged as a promising approach due to their adaptive learning capabilities to reduce estimation errors. However, existing hypernetwork based methods typically rely solely on current gradient information, neglecting the influence of historical gradients. This oversight can lead to accumulated gradient errors when calculating gradient momentum during optimization. To incorporate historical gradient information, we design a Historical Gradient Storage (HGS) module, which models the historical gradient sequence to generate the first-order momentum required for optimization. To further enhance gradient generation in hypernetworks, we propose a Fast and Slow Gradient Generation (FSG) method. Additionally, to produce more precise gradients, we introduce Layer Recognition Embeddings (LRE) into the hypernetwork, facilitating the generation of layer-specific fine gradients. Extensive comparative experiments on the CIFAR-10 and CIFAR-100 datasets demonstrate that our method achieves faster convergence and lower loss values, outperforming existing baselines.

Retrieval-augmented generation (RAG) has emerged to address the knowledge-intensive visual question answering (VQA) task. Current methods mainly employ separate retrieval and generation modules to acquire external knowledge and generate answers, respectively. We propose ReAuSE, an alternative to the previous RAG model for the knowledge-based VQA task, which seamlessly integrates knowledge retriever into the generative multi-modal large language model, serving as a built-in search engine. Specifically, our model functions both as a generative retriever and an accurate answer generator. It not only helps retrieve documents from the knowledge base by producing identifier for each document, but it also answers visual questions based on the retrieved documents. Furthermore, we also propose a reinforced retrieval calibration module from relevance feedback to improve retrieval performance and align with the preferences for accurate answer generation. Extensive experiments on two representative OKVQA and A-OKVQA datasets demonstrate significant improvements ranging from 2.9% to 9.6% across all evaluation metrics when compared to strong baselines.

Graph Retrieval Augmented Generation (GraphRAG) effectively enhances external knowledge integration capabilities by explicitly modeling knowledge relationships, thereby improving the factual accuracy and generation quality of Large Language Models (LLMs) in specialized domains.However, existing methods suffer from two inherent limitations: 1) Inefficient Information Aggregation: They rely on a single agent and fixed iterative patterns, making it difficult to adaptively capture multi-level textual, structural, and degree information within graph data.2) Rigid Reasoning Mechanism: They employ preset reasoning schemes, which cannot dynamically adjust reasoning depth nor achieve precise semantic correction.To overcome these limitations, we propose Graph Counselor, an GraphRAG method based on multi-agent collaboration.This method uses the Adaptive Graph Information Extraction Module (AGIEM), where Planning, Thought, and Execution Agents work together to precisely model complex graph structures and dynamically adjust information extraction strategies, addressing the challenges of multi-level dependency modeling and adaptive reasoning depth.Additionally, the Self-Reflection with Multiple Perspectives (SR) module improves the accuracy and semantic consistency of reasoning results through self-reflection and backward reasoning mechanisms.Experiments demonstrate that Graph Counselor outperforms existing methods in multiple graph reasoning tasks, exhibiting higher reasoning accuracy and generalization ability.Our code is available at Graph-Counselor.

Supervised Fine-Tuning (SFT) and Preference Optimization (PO) are key processes for aligning Language Models (LMs) with human preferences post pre-training.While SFT excels in efficiency and PO in effectiveness, they are often combined sequentially without integrating their optimization objectives.This approach ignores the opportunities to bridge their paradigm gap and take the strengths from both.In this paper, we interpret SFT and PO with two subprocesses -Preference Estimation and Transition Optimization -defined at token level within the Markov Decision Process (MDP).This modeling shows that SFT is only a special case of PO with inferior estimation and optimization.PO estimates the model's preference by its entire generation, while SFT only scores model's subsequent predicted tokens based on prior tokens from ground truth answer.These priors deviates from model's distribution, hindering the preference estimation and transition optimization.Building on this view, we introduce Intuitive Fine-Tuning (IFT) to integrate SFT and PO into a single process.Through a temporal residual connection, IFT brings better estimation and optimization by capturing LMs' intuitive sense of its entire answers.But it solely relies on a single policy and the same volume of non-preference-labeled data as SFT.Our experiments show that IFT performs comparably or even superiorly to SFT and some typical PO methods across several tasks, particularly those requires generation, reasoning, and fact-following abilities.An explainable Frozen Lake game further validates the effectiveness of IFT for getting competitive policy.

Haoyang Su, Renqi Chen, Shixiang Tang, Zhenfei Yin, Xinzhe Zheng, Jinzhe Li, Biqing Qi, Qi Wu, Hui Li, Wanli Ouyang, Philip Torr, Bowen Zhou, Nanqing Dong. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

As an effective approach to equip models with multitask capabilities without additional training, model merging has garnered significant attention. However, existing merging methods face challenges of redundant parameter conflicts and the excessive storage burden of fine-tuned parameters. In this work, through controlled experiments, we reveal that for fine-tuned task vectors, only those parameters with magnitudes above a certain threshold contribute positively to the task, exhibiting a pulse-like characteristic. We then attempt leveraging this pulse-like characteristic to binarize the task vectors and reduce storage overhead. Further controlled experiments show that the binarized task vectors incur almost no decrease in fine-tuning and merging performance, and even exhibit stronger performance improvements as the proportion of redundant parameters increases. Based on these insights, we propose Task Switch (T-Switch), which decomposes task vectors into three components: 1) an activation switch instantiated by a binarized mask vector, 2) a polarity switch instantiated by a binarized sign vector, and 3) a scaling knob instantiated by a scalar coefficient. By storing task vectors in a binarized form, T-Switch alleviates parameter conflicts while ensuring efficient task parameter storage. Furthermore, to enable automated switch combination in T-Switch, we further introduce Auto-Switch, which enables training-free switch combination via retrieval from a small query set. Experiments indicate that our methods achieve significant performance improvements over existing baselines, requiring only 1-3% of the storage space of full-precision parameters.

Sihang Zeng, Kai Tian, Kaiyan Zhang, Yuru Wang, Junqi Gao, Runze Liu, Sa Yang, Jingxuan Li, Xinwei Long, Jiaheng Ma, Biqing Qi, Bowen Zhou. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Scaling inference-time computation is increasingly seen as the next frontier in scaling laws for large language models. Previous work in mathematics and coding has demonstrated the remarkable potential for inference-time scaling. During such scaling, fine-grained supervision through process-based reward models (PRMs) is essential for enhancement. However, exploration of inference-time scaling and PRMs in open-domain problems remains limited, where lacking exact answers and obtaining process supervision prove challenging. In this paper, we explore the construction of PRMs for open-domain tasks, specifically for instruction-following tasks. Utilizing existing outcome-based reward models (ORMs), we develop sentence-level preference trees based on the prefix similarity of parallel sampled candidates from datasets like UltraFeedback. This setup allows us to derive weak supervision for processes via back-propagation from outcome-level rewards. Subsequently, we integrate ORMs and PRMs under the same pairwise ranking objectives, resulting in our newly developed reward models, named OpenPRM. This approach significantly enhances the scalability of process-level supervision in open domains at minimal cost. We assess the performance of OpenPRM across various reward benchmarks, demonstrating its competitive edge over traditional ORMs in open domains and PRMs in specialized domains. Additionally, we investigate the scalability of inference-time computation for open-domain instructions. Our results highlight the limitations of ORMs’ scalability, while OpenPRM shows superior performance in scaled settings. Despite these advances, achieving automatic fine-grained supervision for open-domain inference-time scaling remains a substantial challenge. We hope these findings will spur further development of process supervision reward models in open-domain scenarios.

Extending the context length of Language Models (LMs) by improving Rotary Position Embedding (RoPE) has become a trend. While prior works mainly address RoPE’s limitations within attention, this paper uncovers the adverse effects on length generalization from nearly all parts of LMs. Using Discrete Signal Processing theory, we show that RoPE enables periodic attention by implicitly achieving Non-Uniform Discrete Fourier Transform. However, this periodicity is undermined by the spectrum damage caused by: 1) linear layers and activation functions outside of attention; 2) insufficiently trained frequency components brought by time-domain truncation. Building on our observations, we propose Fourier Position Embedding (FoPE), which enhances attention’s frequency-domain properties to improve both its periodic extension and length generalization. FoPE constructs Fourier Series and zero-outs the destructive frequency components, increasing model robustness against the spectrum damage. Experiments across various model scales and benchmarks show that, within varying context windows, FoPE maintains a more stable performance compared to other baselines. Several analyses and ablations bring further support to our method and theoretical modeling.

Heterogeneous Large Language Model (LLM) fusion integrates the strengths of multiple source LLMs with different architectures into a target LLM with low computational overhead. While promising, existing methods suffer from two major limitations: 1) **reliance on real data from limited domain** for knowledge fusion, preventing the target LLM from fully acquiring knowledge across diverse domains, and 2) **fixed data allocation proportions** across domains, failing to dynamically adjust according to the target LLM's varying capabilities across domains, leading to a capability imbalance. To overcome these limitations, we propose Bohdi, a synthetic-data-only heterogeneous LLM fusion framework. Through the organization of knowledge domains into a hierarchical tree structure, Bohdi enables automatic domain exploration and multi-domain data generation through multi-model collaboration, thereby comprehensively extracting knowledge from source LLMs. By formalizing domain expansion and data sampling proportion allocation on the knowledge tree as a Hierarchical Multi-Armed Bandit problem, Bohdi leverages the designed DynaBranches mechanism to adaptively adjust sampling proportions based on the target LLM's performance feedback across domains. Integrated with our proposed Introspection-Rebirth (IR) mechanism, DynaBranches dynamically tracks capability shifts during target LLM's updates via Sliding Window Binomial Likelihood Ratio Testing (SWBLRT), further enhancing its online adaptation capability. Comparative experimental results on a comprehensive suite of benchmarks demonstrate that Bohdi significantly outperforms existing baselines on multiple target LLMs, exhibits higher data efficiency, and virtually eliminates the imbalance in the target LLM's capabilities.

Attributing the behavior of Transformer models to internal computations is a central challenge in mechanistic interpretability. We introduce DePass, a unified framework for feature attribution based on a single decomposed forward pass. DePass decomposes hidden states into customized additive components, then propagates them with attention scores and MLP's activations fixed. It achieves faithful, fine-grained attribution without requiring auxiliary training. We validate DePass across token-level, model component-level, and subspace-level attribution tasks, demonstrating its effectiveness and fidelity. Our experiments highlight its potential to attribute information flow between arbitrary components of a Transformer model. We hope DePass serves as a foundational tool for broader applications in interpretability.

This paper investigates Reinforcement Learning (RL) on data without explicit labels for reasoning tasks in Large Language Models (LLMs). The core challenge of the problem is reward estimation during inference while not having access to ground-truth information. While this setting appears elusive, we find that common practices in Test-Time Scaling (TTS), such as majority voting, yield surprisingly effective rewards suitable for driving RL training. In this work, we introduce Test-Time Reinforcement Learning (TTRL), a novel method for training LLMs using RL on unlabeled data. TTRL enables self-evolution of LLMs by utilizing the priors in the pre-trained models. Our experiments demonstrate that TTRL consistently improves performance across a variety of tasks and models. Notably, TTRL boosts the pass@1 performance of Qwen-2.5-Math-7B by approximately 211% on the AIME 2024 with only unlabeled test data. Furthermore, although TTRL is only supervised by the Maj@N metric, TTRL has demonstrated performance to consistently surpass the upper limit of the initial model, and approach the performance of models trained directly on test data with ground-truth labels. Our experimental findings validate the general effectiveness of TTRL across various tasks and highlight TTRL's potential for broader tasks and domains.

Few-Shot Class-Incremental Learning (FSCIL) has gained considerable attention in recent years for its pivotal role in addressing continuously arriving classes. However, it encounters additional challenges. The scarcity of samples in new sessions intensifies overfitting, causing incompatibility between the output features of new and old classes, thereby escalating catastrophic forgetting. A prevalent strategy involves mitigating catastrophic forgetting through the Explicit Memory (EM), which comprise of class prototypes. However, current EM-based methods retrieves memory globally by performing Vector-to-Vector (V2V) interaction between features corresponding to the input and prototypes stored in EM, neglecting the geometric structure of local features. This hinders the accurate modeling of their positional relationships. To incorporate information of local geometric structure, we extend the V2V interaction to Graph-to-Graph (G2G) interaction. For enhancing local structures for better G2G alignment and the prevention of local feature collapse, we propose the Local Graph Preservation (LGP) mechanism. Additionally, to address sample scarcity in classes from new sessions, the Contrast-Augmented G2G (CAG2G) is introduced to promote the aggregation of same class features thus helps few-shot learning. Extensive comparisons on CIFAR100, CUB200, and the challenging ImageNet-R dataset demonstrate the superiority of our method over existing methods.

Graph Transformers have garnered significant attention due to their ability to address the challenges of long-distance interactions in previous GNNs. However, most current graph Transformers face difficulties when dealing with heterophilic graphs. To investigate this issue, we first analyzed the distribution of attention weights for homophilic and heterophilic graphs. We discovered that heterophily interferes with the allocation of attention weights, leading to errors in node classification. Further investigation revealed that the root cause may be the difficulty of current graph Transformers in capturing the difference between the features of each node and its neighbors. To alleviate this issue, we propose a position encoding strategy called DiSP to better capture the feature difference and introduce FDphormer, a new efficient and simple graph Transformer model based on DiSP. Additionally, we analyze the generalization error of existing graph Transformer models and provide an upper bound on the generalization error of current graph Transformers with the introduction of DiSP. Extensive experiments demonstrate that FDphormer not only outperforms state-of-the-art methods on diverse heterogeneous datasets but also exhibits competitive performance under homophily.

With the advancement of language models (LMs), their exposure to private data is increasingly inevitable, and their deployment (especially for smaller ones) on personal devices, such as PCs and smartphones, has become a prevailing trend.In contexts laden with user information, enabling models to both safeguard user privacy and execute commands efficiently emerges as an essential research imperative.In this paper, we propose CoGenesis, a collaborative generation framework integrating large (hosted on cloud infrastructure) and small models (deployed on local devices) to address privacy concerns logically.Initially, we design a pipeline to create personalized writing instruction datasets enriched with extensive context details as the testbed of this research issue.Subsequently, we introduce two variants of CoGenesis based on sketch and logits respectively.Our experimental findings, based on our synthesized dataset and two additional open-source datasets, indicate that: 1) Large-scale models perform well when provided with user context but struggle in the absence of such context.2) While specialized smaller models fine-tuned on the synthetic dataset show promise, they still lag behind their larger counterparts.3) Our CoGenesis framework, utilizing mixed-scale models, showcases competitive performance, providing a feasible solution to privacy issues.* Corresponding author 1 This paper defines large LMs (LLMs) as both closed and open-source models, designed for universal application and advanced performance, and intended for cloud deployment.Conversely, small LMs (SLMs) refer to models tailored for specific tasks and deployed on local devices.

Advanced life forms, sustained by the synergistic interaction of neural cognitive mechanisms, continually acquire and transfer knowledge throughout their lifespan. In contrast, contemporary machine learning paradigms exhibit limitations in emulating the facets of continual learning (CL). Nonetheless, the emergence of large language models (LLMs) presents promising avenues for realizing CL via interactions with these models. Drawing on Complementary Learning System theory, this paper presents a novel Interactive Continual Learning (ICL) framework, enabled by collaborative interactions among models of various sizes. Specifically, we assign the ViT model as System1 and multimodal LLM as System2. To enable the memory module to deduce tasks from class information and enhance Set2Set retrieval, we propose the Class-Knowledge-Task Multi-Head Attention (CKT-MHA). Additionally, to improve memory retrieval in System1 through enhanced geometric representation, we introduce the CL-vMF mechanism, based on the von Mises-Fisher (vMF) distribution. Mean-while, we introduce the von Mises-Fisher Outlier Detection and Interaction (vMF-ODI) strategy to identify hard examples, thus enhancing collaboration between System1 and System2 for complex reasoning realization. Comprehensive evaluation of our proposed ICL demonstrates significant resistance to forgetting and superior performance relative to existing methods. Code is available at github.com/ICL.

Long-term memory is significant for agents, in which insights play a crucial role.However, the emergence of irrelevant insight and the lack of general insight can greatly undermine the effectiveness of insight.To solve this problem, in this paper, we introduce Multi-Scale Insight Agent (MSI-Agent), an embodied agent designed to improve LLMs' planning and decision-making ability by summarizing and utilizing insight effectively across different scales.MSI achieves this through the experience selector, insight generator, and insight selector.Leveraging a three-part pipeline, MSI can generate task-specific and high-level insight, store it in a database, and then use relevant insight from it to aid in decisionmaking.Our experiments show that MSI outperforms another insight strategy when planning by GPT3.5.Moreover, We delve into the strategies for selecting seed experience and insight, aiming to provide LLM with more useful and relevant insight for better decision-making.Our observations also indicate that MSI exhibits better robustness when facing domainshifting scenarios.

Recently, stable diffusion (SD) models have typically flourished in the field of image synthesis and personalized editing, with a range of photorealistic and unprecedented images being successfully generated. As a result, widespread interest has been ignited to develop and use various SD-based tools for visual content creation. However, the exposure of AI-created content on public platforms could raise both legal and ethical risks. In this regard, the traditional methods of adding watermarks to the already generated images (i.e. post-processing) may face a dilemma (e.g., being erased or modified) in terms of copyright protection and content monitoring, since the powerful image inversion and text-to-image editing techniques have been widely explored in SD-based methods. In this work, we propose a Safe and high-traceable Stable Diffusion framework (namely Safe-SD) to adaptively implant the graphical watermarks (e.g., QR code) into the imperceptible structure-related pixels during the generative diffusion process for supporting text-driven invisible watermarking and detection. Different from the previous high-cost injection-then-detection training framework, we design a simple and unified architecture, which makes it possible to simultaneously train watermark injection and detection in a single network, greatly improving the efficiency and convenience of use. Moreover, to further support text-driven generative watermarking and deeply explore its robustness and high-traceability, we elaborately design a λ-sampling and λ-encryption algorithm to fine-tune a latent diffuser wrapped by a VAE for balancing high-fidelity image synthesis and high-traceable watermark detection. We present our quantitative and qualitative results on two representative datasets LSUN, COCO and FFHQ, demonstrating state-of-the-art performance of Safe-SD and showing it significantly outperforms the previous approaches.

Che Jiang, Biqing Qi, Xiangyu Hong, Dayuan Fu, Yang Cheng, Fandong Meng, Mo Yu, Bowen Zhou, Jie Zhou. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

Xuekai Zhu, Biqing Qi, Kaiyan Zhang, Xinwei Long, Zhouhan Lin, Bowen Zhou. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2024.

The most advanced diffusion models have recently adopted increasingly deep stacked networks (e.g., U-Net or Transformer) to promote the generative emergence capabilities of vision generation models similar to large language models (LLMs). However, progressively deeper stacked networks will intuitively cause numerical propagation errors and reduce noisy prediction capabilities on generative data, which hinders massively deep scalable training of vision generation models. In this paper, we first uncover the nature that neural networks being able to effectively perform generative denoising lies in the fact that the intrinsic residual unit has consistent dynamic property with the input signal's reverse diffusion process, thus supporting excellent generative abilities. Afterwards, we stand on the shoulders of two common types of deep stacked networks to propose a unified and massively scalable Neural Residual Diffusion Models framework (Neural-RDM for short), which is a simple yet meaningful change to the common architecture of deep generative networks by introducing a series of learnable gated residual parameters that conform to the generative dynamics. Experimental results on various generative tasks show that the proposed neural residual models obtain state-of-the-art scores on image's and video's generative benchmarks. Rigorous theoretical proofs and extensive experiments also demonstrate the advantages of this simple gated residual mechanism consistent with dynamic modeling in improving the fidelity and consistency of generated content and supporting large-scale scalable training.

Graph incremental learning has gained widespread attention for its ability to mitigate catastrophic forgetting for graph neural networks (GNN). Conventional methods typically require numerous labels for node classification. However, obtaining abundant labels is often challenging in practice, which makes graph few-shot incremental learning necessary. Current approaches rely on large number of samples from meta-learning to construct memories, and heavy fine-tuning of the GNN parameters that lead to the loss of past knowledge. These result in significant memory consumption and loss of past knowledge information, respectively. To tackle these issues, We introduce Mecoin to efficient construct and Preserve memory. For efficient storage and update of class prototypes, Mecoin use Structured Memory Unit (SMU) to cache prototypes of the seen classes and update new class prototypes through interaction between nodes and the cached prototypes by Memory Construction module(MeCo). Besides, to avoid extensive parameter fine-tuning and forgetting, we introduce a Memory Representation Adaptive Module called MRaM to separate the learning of prototypes and class representations and use Graph Knowledge Interchange Module (GKIM) to injects past knowledge information into GNN. We analyze the effectiveness of our paradigm from the perspectives of generalization error, and discuss the impact of different distillation methods on model performance through experiments and VC-dimension. By comparison with other related methods, we validate that Mecoin achieves higher accuracy and lower forgetting rate.

Deep State Space Models (SSMs) have proven effective in numerous task scenarios but face significant security challenges due to Adversarial Perturbations (APs) in real-world deployments. Adversarial Training (AT) is a mainstream approach to enhancing Adversarial Robustness (AR) and has been validated on various traditional DNN architectures. However, its effectiveness in improving the AR of SSMs remains unclear. While many enhancements in SSM components, such as integrating Attention mechanisms and expanding to data-dependent SSM parameterizations, have brought significant gains in Standard Training (ST) settings, their potential benefits in AT remain unexplored. To investigate this, we evaluate existing structural variants of SSMs with AT to assess their AR performance. We observe that pure SSM structures struggle to benefit from AT, whereas incorporating Attention yields a markedly better trade-off between robustness and generalization for SSMs in AT compared to other components. Nonetheless, the integration of Attention also leads to Robust Overfitting (RO) issues. To understand these phenomena, we empirically and theoretically analyze the output error of SSMs under AP. We find that fixed-parameterized SSMs have output error bounds strictly related to their parameters, limiting their AT benefits, while input-dependent SSMs may face the problem of error explosion. Furthermore, we show that the Attention component effectively scales the output error of SSMs during training, enabling them to benefit more from AT, but at the cost of introducing RO due to its high model complexity. Inspired by this, we propose a simple and effective Adaptive Scaling (AdS) mechanism that brings AT performance close to Attention-integrated SSMs without introducing the issue of RO.

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements in biomedicine, which have also raised privacy and security challenges. The construction of specialized generalists hinges largely on high-quality datasets, enhanced by techniques like supervised fine-tuning and reinforcement learning from human or AI feedback, and direct preference optimization. However, these leading technologies (e.g., preference learning) are still significantly limited in the open source community due to the scarcity of specialized data. In this paper, we present the UltraMedical collections, which consist of high-quality manual and synthetic datasets in the biomedicine domain, featuring preference annotations across multiple advanced LLMs. By utilizing these datasets, we fine-tune a suite of specialized medical models based on Llama-3 series, demonstrating breathtaking capabilities across various medical benchmarks. Moreover, we develop powerful reward models skilled in biomedical and general reward benchmark, enhancing further online preference learning within the biomedical LLM community.

From the perspective of information bottleneck (IB) theory, we propose a novel framework for performing black-box transferable adversarial attacks named IBTA, which leverages advancements in invariant features. Intuitively, diminishing the reliance of adversarial perturbations on the original data, under equivalent attack performance constraints, encourages a greater reliance on invariant features that contributes most to classification, thereby enhancing the transferability of adversarial attacks. Building on this motivation, we redefine the optimization of transferable attacks using a novel theoretical framework that centers around IB. Specifically, to overcome the challenge of unoptimizable mutual information, we propose a simple and efficient mutual information lower bound (MILB) for approximating computation. Moreover, to quantitatively evaluate mutual information, we utilize the Mutual Information Neural Estimator (MINE) to perform a thorough analysis. Our experiments on the ImageNet dataset well demonstrate the efficiency and scalability of IBTA and derived MILB. Our code is available at github.com/IBTA.

Deep neural networks (DNNs)-based natural language processing (NLP) systems are vulnerable to being fooled by adversarial examples presented in recent studies. Intent detection tasks in dialog systems are no exception, however, relatively few works have been attempted on the defense side. The combination of linear classifier and softmax is widely used in most defense methods for other NLP tasks. Unfortunately, it does not encourage the model to learn well-separated feature representations. Thus, it is easy to induce adversarial examples. In this article, we propose a simple, yet efficient defense method from the geometric constraint perspective. Specifically, we first propose an M-similarity metric to shrink variances of intraclass features. Intuitively, better geometric conditions of feature space can bring lower misclassification probability (MP). Therefore, we derive the optimal geometric constraints of anchors within each category from the overall MP (OMP) with theoretical guarantees. Due to the nonconvex characteristic of the optimal geometric condition, it is hard to satisfy the traditional optimization process. To this end, we regard such geometric constraints as manifold optimization processes in the Stiefel manifold, thus naturally avoiding the above challenges. Experimental results demonstrate that our method can significantly improve robustness compared with baselines, while retaining the excellent performance on normal examples.

Instruction tuning has recently been recognized as an effective way of aligning Large Language Models (LLMs) to enhance their generalization ability across various tasks.However, when tuning publicly accessible, centralized LLMs with private instruction data, privacy concerns are inevitable.While direct transfer of parameterized modules between models is a plausible approach to address this, its implications and effectiveness need further exploration.This paper focuses on Offsite-Tuning (OFT), a representative technique that transfers transformer blocks between centralized LLMs and downstream emulators.Given the limited understanding of the underlying mechanism of OFT, we perform an empirical analysis on LLMs from the perspectives of representation and functional similarity.Interestingly, our findings reveal a unique modular structure within the layers of LLMs that appears to emerge as the model size expands.Simultaneously, we note subtle but potentially significant changes in representation and intermediate predictions across the layers.Inspired by these observations, we propose CRaSh, involving Clustering, Removing, and Sharing, a training-free strategy to derive improved emulators from LLMs.CRaSh significantly boosts performance of OFT with billions of parameters.Furthermore, we investigate the optimal solutions yielded by fine-tuning with and without full model through the lens of loss landscape.Our findings demonstrate a linear connectivity among these optima falling over the same basin, thereby highlighting the effectiveness of CRaSh and OFT.The source code is publicly available at https://github.com/TsinghuaC3I/CRaSh.

The transferability of adversarial perturbations provides an effective shortcut for black-box attacks. Targeted perturbations have greater practicality but are more difficult to transfer between models. In this paper, we experimentally and theoretically demonstrated that neural networks trained on the same dataset have more consistent performance in High-Sample-Density-Regions (HSDR) of each class instead of low sample density regions. Therefore, in the target setting, adding perturbations towards HSDR of the target class is more effective in improving transferability. However, density estimation is challenging in high-dimensional scenarios. Further theoretical and experimental verification demonstrates that easy samples with low loss are more likely to be located in HSDR. Perturbations towards such easy samples in the target class can avoid density estimation for HSDR location. Based on the above facts, we verified that adding perturbations to easy samples in the target class improves targeted adversarial transferability of existing attack methods. A generative targeted attack strategy named Easy Sample Matching Attack (ESMA) is proposed, which has a higher success rate for targeted attacks and outperforms the SOTA generative method. Moreover, ESMA requires only $5\%$ of the storage space and much less computation time comparing to the current SOTA, as ESMA attacks all classes with only one model instead of seperate models for each class. Our code is available at https://github.com/gjq100/ESMA

Many approaches have been influential in the robotics field because of deep learning (DL). As space robots need more reliability and stability, model-free algorithms with deep learning have particular advantages over the traditional methods in space environment. In this paper, we present an original robot current/torque prediction based on robot dynamic system with deep learning. Also, we add sliding mode-based fixed-time controller to improve the control performance. It has analysed manipulator current information through robot dynamic property’s matrix nature from fewer samples. This method has significant benefits in terms of robot current/torque identification and tracking. It also performs well in robustness and learning rates. This generic method has developed to solve a variety of problems using deep learning and data filtering with manipulator dynamics process, which includes deep learning with fractional order differential operators, robot dynamics and Kalman smoothing. We verified our algorithm into a real two-joint space robot on air-floating platform in zero gravity environment. The final results show it can learn to predict current/torque based on robot dynamics and complete the finitetime convergence. This paper made several key contributions to the fields of current/torque identification and prediction with manipulator dynamics and deep learning in space robot models. It performs very well in robot current/torque tracking and predicting new situations.

Millimetre wave (mmWave) communications are the most promising candidate for the future fifth‐generation mobile broadband networks, which offer greater available spectrum than current cellular. However, the huge path loss and rain attenuation due to the characteristic of the mmWave channel make it difficult to realise. Thanks to the small wavelength of mmWave signals, massive multi‐input‐multi‐output (MIMO) systems can be leveraged to overcome the path loss. Unfortunately, in contrast to conventional MIMO systems, high‐power consumption and hardware cost make fully digital precoding impractical. In this study, the authors study the hybrid precoding structure for multiuser mmWave systems, which compromises the cost and performance. First, an extension algorithm from single user systems, which directly decomposes the optimal fully digital precoder into a baseband precoder and an analogue radio‐frequency (RF) precoder, is introduced according to the recent work. Then, the drawback of this kind of algorithm is analysed at high signal‐to‐noise ratios. Subsequently, a two‐stage hybrid precoding algorithm, which is based on the minimum mean‐squared error criterion is proposed, where the modified Broyden–Fletcher–Goldfarb–Shanno (BFGS) algorithm is presented to reduce the reconstruction error of computing the analogue RF precoder. Simulation results show that the proposed precoding algorithm can significantly improve the performance of the system sum‐rate.