CLIP is a seminal multimodal model that maps images and text into a shared representation space by contrastive learning on billions of image–caption pairs. Inspired by the rapid progress of large language models (LLMs), we investigate how the superior linguistic understanding and broad world knowledge of LLMs can further strengthen CLIP—particularly in handling long, complex captions. We introduce an efficient fine-tuning framework that embeds an LLM into a pretrained CLIP while incurring almost the same training cost as regular CLIP fine-tuning. Our method first “embedding-izes” the LLM for the CLIP setting, then couples it to the pretrained CLIP vision encoder through a lightweight adaptor trained on only a few million image–caption pairs. With this strategy we achieve large performance gains—without large-scale retraining—over state-of-the-art CLIP variants such as EVA02 and SigLIP-2. The LLM-enhanced CLIP delivers consistent improvements across a wide spectrum of downstream tasks, including linear-probe classification, zero-shot image–text retrieval with both short and long captions (in English and other languages), zero-shot/supervised image segmentation, object detection, and used as tokenizer for multimodal large-model benchmarks.

Text-to-video generation poses significant challenges due to the inherent complexity of video data, which spans both temporal and spatial dimensions. It introduces additional redundancy, abrupt variations, and a domain gap between language and vision tokens while generation. Addressing these challenges requires an effective video tokenizer that can efficiently encode video data while preserving essential semantic and spatiotemporal information, serving as a critical bridge between text and vision. Inspired by the observation in VQ-VAE-2, we propose HiTVideo, a novel approach for text-to-video generation with hierarchical tokenizers. It utilizes a 3D causal VAE with a multi-layer discrete token framework, encoding video content into hierarchically structured codebooks. Higher layers capture semantic information with higher compression, while lower layers focus on fine-grained spatiotemporal details, striking a balance between compression efficiency and reconstruction quality. Our approach efficiently encodes longer video sequences (e.g., 8 seconds, 64 frames), reducing bits per pixel (bpp) by approximately 70% compared to previous tokenizers, while maintaining competitive reconstruction quality. We explore the trade-offs between compression and reconstruction, while emphasizing the advantages of high-compressed semantic tokens in text-to-video tasks. HiTVideo aims to address the potential limitations of existing video tokenizers in text-to-video generation tasks, striving for higher compression ratios, improved token quality, and simplify LLMs modeling under language guidance, offering a scalable and promising framework for advancing text to video generation.

Equal access to digital technologies is critical for education, employment, and social participation. However, mainstream interfaces are visually oriented, creating steep learning curves and frequent obstacles for screen reader users, and limiting their independence and opportunities. Existing support is inadequate—tutorials mainly target sighted users, while human assistance lacks real-time availability. We introduce AskEase, an on-demand AI assistant that provides step-by-step, screen reader user-friendly guidance for computer use. AskEase manages multiple sources of context to infer user intent and deliver precise, situation-specific guidance. Its seamless interaction design minimizes disruption and reduces the effort of seeking help. We demonstrated its effectiveness through representative usage scenarios and robustness tests. In a within-subjects study with 12 screen reader users, AskEase significantly improved task success while reducing perceived workload, including physical demand, effort, and frustration. These results demonstrate the potential of LLM-powered assistants to promote accessible computing and expand opportunities for users with visual impairments.

Generative AI agents are reshaping human-computer interaction, shifting users from direct task execution to supervising machine-driven actions, especially the rise of “vibe coding” in programming. Yet little is known about how programmers who use screen readers interact with AI code assistants in practice. We conducted a longitudinal study with 16 blind and low-vision programmers. Participants completed a GitHub Copilot tutorial, engaged with a programming task, and provided initial feedback. After two weeks of AI-assisted programming, follow-ups examined how their practices and perceptions evolved. Our findings show that code assistants enhanced programming efficiency and bridged accessibility gaps. However, participants struggled to convey intent, interpret AI outputs, and manage multiple views while maintaining situational awareness. They showed diverse preferences for accessibility features, expressed a need to balance automation with control, and encountered barriers when learning to use these tools. Furthermore, we propose design principles and recommendations for more accessible and inclusive human-AI collaborations.

Artificial intelligence (AI) has been increasingly applied to gaming, with large language models (LLMs) playing a key role in character control. However, efficiently co-locating game rendering and LLM inference on one GPU presents challenges due to resource constraints, diverse latency requirements, and fine-grained task scheduling. We propose LEGO, an algorithm-system co-design that enables the efficient co-location of LLM inference and game rendering tasks. Algorithmwise, LEGO features a resource-oriented layer-skipping adaptor, which distills knowledge from skipped layers to reduce computational demand while maintaining inference accuracy. System-wise, LEGO proposes a headroom-maximizing LLM scheduler, which dynamically partitions inference tasks to utilize available rendering headroom. Evaluations on an Nvidia RTX 4090 show that LEGO meets latency targets in all scenarios, improves rendering headroom utilization by up to 28.6 %, and reduces LLM inference accuracy loss by up to 86.3 % compared to current layer-skipping approaches.

Large language models (LLMs) enable longcontext tasks but face efficiency challenges due to the growing key-value (KV) cache.We propose LeanK, a learning-based method that prunes unimportant key (K) cache channels by leveraging static channel sparsity.With a novel two-stage training process, LeanK learns channel-wise static mask that could satisfy specific sparsity ratio and hardware alignment requirement.LeanK reduces GPU memory and accelerates decoding without sacrificing accuracy.Experiments demonstrate up to 70% K cache and 16%-18% V cache memory reduction.Custom decoding kernel enables 1.3x speedup for attention computation.We also provide insights into model channels and attention heads during long-context inference by analyzing the learned importance distribution.Our code is available at https://aka.ms/LeanK.

As machine learning models grow in complexity and size, necessitating the use of extensive GPU clusters, the challenge of managing frequent system failures becomes increasingly critical. These failures can lead to substantial losses in computational time and resources. Large-scale model training often does not use GPU redundancy for fault tolerance, underscoring the necessity for an efficient checkpoint mechanism for GPU failure recovery. Enhanced failure resilience demands more frequent checkpoints; however suspend-and-resume based checkpoints could severely lower training throughput.RapidScribe addresses this challenge head-on by leveraging unused GPU bus bandwidth to facilitate tensor transfers from GPU to host in concurrent with ongoing training. At the heart of RapidScribe is the Steno protocol, which lowers checkpoint traffic aggressively by copying both gradients and model training states. Steno generates copy schedules to be fully interleaved within training processes to minimize training interruptions. The low bandwidth usage by Steno makes it even a viable solution for disk-based checkpoints. Experiments show that RapidScribe’s parallel checkpoint techniques ensure that frequent checkpoint operations are deeply synchronized with neural network training cycles, preserving near-baseline throughput across various distributed training configurations on a AMD MI250 GPU cluster, thus providing a robust checkpoint-based solution to GPU fault tolerance.

Long-context Large Language Models (LLMs) have enabled numerous downstream applications but also introduced significant challenges related to computational and memory efficiency. To address these challenges, optimizations for long-context inference have been developed, centered around the KV cache. However, existing benchmarks often evaluate in single-request, neglecting the full lifecycle of the KV cache in real-world use. This oversight is particularly critical, as KV cache reuse has become widely adopted in LLMs inference frameworks, such as vLLM and SGLang, as well as by LLM providers, including OpenAI, Microsoft, Google, and Anthropic. To address this gap, we introduce SCBENCH (SharedContextBENCH), a comprehensive benchmark for evaluating long-context methods from a KV cache centric perspective: 1) KV cache generation, 2) KV cache compression, 3) KV cache retrieval, and 4) KV cache loading. Specifically, SCBench uses test examples with shared context, ranging 12 tasks with two shared context modes, covering four categories of long-context capabilities: string retrieval, semantic retrieval, global information, and multi-task. With SCBench, we provide an extensive KV cache-centric analysis of eight categories long-context solutions, including Gated Linear RNNs (Codestal-Mamba), Mamba-Attention hybrids (Jamba-1.5-Mini), and efficient methods such as sparse attention, KV cache dropping, quantization, retrieval, loading, and prompt compression. The evaluation is conducted on six Transformer-based long-context LLMs: Llama-3.1-8B/70B, Qwen2.5-72B/32B, Llama-3-8B-262K, and GLM-4-9B. Our findings show that sub-O(n) memory methods suffer in multi-turn scenarios, while sparse encoding with O(n) memory and sub-O(n^2) pre-filling computation perform robustly. Dynamic sparsity yields more expressive KV caches than static patterns, and layer-level sparsity in hybrid architectures reduces memory usage with strong performance. Additionally, we identify attention distribution shift issues in long-generation scenarios.

To deliver coherent and personalized experiences in long-term conversations, existing approaches typically perform retrieval augmented response generation by constructing memory banks from conversation history at either the turn-level, session-level, or through summarization techniques. In this paper, we explore the impact of different memory granularities and present two key findings: (1) Both turn-level and session-level memory units are suboptimal, affecting not only the quality of final responses, but also the accuracy of the retrieval process. (2) The redundancy in natural language introduces noise, hindering precise retrieval. We demonstrate that *LLMLingua-2*, originally designed for prompt compression to accelerate LLM inference, can serve as an effective denoising method to enhance memory retrieval accuracy. Building on these insights, we propose **SeCom**, a method that constructs a memory bank with topical segments by introducing a conversation **Se**gmentation model, while performing memory retrieval based on **Com**pressed memory units. Experimental results show that **SeCom** outperforms turn-level, session-level, and several summarization-based methods on long-term conversation benchmarks such as *LOCOMO* and *Long-MT-Bench+*. Additionally, the proposed conversation segmentation method demonstrates superior performance on dialogue segmentation datasets such as *DialSeg711*, *TIAGE*, and *SuperDialSeg*.

The integration of long-context capabilities with visual understanding unlocks unprecedented potential for Vision Language Models (VLMs). However, the quadratic attention complexity during the pre-filling phase remains a significant obstacle to real-world deployment. To overcome this limitation, we introduce MMInference (Multimodality Million tokens Inference), a dynamic sparse attention method that accelerates the prefilling stage for long-context multi-modal inputs. First, our analysis reveals that the temporal and spatial locality of video input leads to a unique sparse pattern, the Grid pattern. Simultaneously, VLMs exhibit markedly different sparse distributions across different modalities. We introduce a permutation-based method to leverage the unique Grid pattern and handle modality boundary issues. By offline search the optimal sparse patterns for each head, MMInference constructs the sparse distribution dynamically based on the input. We also provide optimized GPU kernels for efficient sparse computations. Notably, MMInference integrates seamlessly into existing VLM pipelines without any model modifications or fine-tuning. Experiments on multi-modal benchmarks-including Video QA, Captioning, VisionNIAH, and Mixed-Modality NIAH-with state-of-the-art long-context VLMs (LongVila, LlavaVideo, VideoChat-Flash, Qwen2.5-VL) show that MMInference accelerates the pre-filling stage by up to 8.3x at 1M tokens while maintaining accuracy. Our code is available at https://ama.ms/MMInference.

Transformer-based Large Language Models (LLMs) have become increasingly important. However, scaling LLMs to longer contexts incurs slow inference speed and high GPU memory consumption for caching key-value (KV) vectors. This paper presents RetrievalAttention, a training-free approach to both accelerate the decoding phase and reduce GPU memory consumption by pre-building KV vector indexes for fixed contexts and maintaining them in CPU memory for efficient retrieval. Unlike conventional KV cache methods, RetrievalAttention integrate approximate nearest neighbor search (ANNS) indexes into attention computation. We observe that off-the-shelf ANNS techniques often fail due to the out-of-distribution (OOD) nature of query and key vectors in attention mechanisms. RetrievalAttention overcomes this with an attention-aware vector index. Our evaluation shows RetrievalAttention achieves near full attention accuracy while accessing only 1-3\% of the data, significantly reducing inference costs. Remarkably, RetrievalAttention enables LLMs with 8B parameters to handle 128K tokens on a single NVIDIA RTX4090 (24GB), achieving a decoding speed of 0.107 seconds per token.

In this paper, we propose a novel learning paradigm, termed *Chain-of-Model* (CoM), which incorporates the causal relationship into the hidden states of each layer as a chain style. thereby introducing great scaling efficiency in model training and inference flexibility in deployment.We introduce the concept of *Chain-of-Representation* (CoR), which formulates the hidden states at each layer as a combination of multiple sub-representations (i.e., chains). In each layer, each chain from the output representations can only view all of its preceding chains in the input representations. Consequently, the model built upon CoM framework can progressively scale up the model size by increasing the chains based on the previous models (i.e., chains), and offer multiple sub-models at varying sizes for elastic inference by using different chain numbers. Based on this principle, we devise *Chain-of-Language-Model* (CoLM), which incorporates the idea of CoM into each layer of Transformer architecture. Based on CoLM, we further introduce CoLM-Air by introducing a *KV sharing* mechanism, that computes all keys and values within the first chain and then shares across all chains. This design demonstrates additional extensibility, such as enabling seamless LM switching, prefilling acceleration and so on. Experimental results demonstrate our CoLM family can achieve comparable performance to the standard Transformer, while simultaneously enabling greater flexiblity, such as progressive scaling to improve training efficiency and offer multiple varying model sizes for elastic inference, paving a a new way toward building language models.

Translating natural language to visualization (NL2VIS) has shown great promise for visual data analysis, but it remains a challenging task that requires multiple low-level implementations, such as natural language processing and visualization design. Recent advancements in pre-trained large language models (LLMs) are opening new avenues for generating visualizations from natural language. However, the lack of a comprehensive and reliable benchmark hinders our understanding of LLMs' capabilities in visualization generation. In this paper, we address this gap by proposing a new NL2VIS benchmark called VisEval. Firstly, we introduce a high-quality and large-scale dataset. This dataset includes 2,524 representative queries covering 146 databases, paired with accurately labeled ground truths. Secondly, we advocate for a comprehensive automated evaluation methodology covering multiple dimensions, including validity, legality, and readability. By systematically scanning for potential issues with a number of heterogeneous checkers, VisEval provides reliable and trustworthy evaluation outcomes. We run VisEval on a series of state-of-the-art LLMs. Our evaluation reveals prevalent challenges and delivers essential insights for future advancements.

Huiqiang Jiang, Qianhui Wu, Xufang Luo, Dongsheng Li, Chin-Yew Lin, Yuqing Yang, Lili Qiu. Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

In the era of data-driven decision-making, the complexity of data analysis necessitates advanced expertise and tools of data science, presenting significant challenges even for specialists.Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing.Yet their practical efficacy remains constrained by the varied demands of realworld applications and complicated analytical process.In this paper, we introduce DSEvala novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the performance of these agents throughout the entire data science lifecycle.Incorporating a novel bootstrapped annotation method, we streamline dataset preparation, improve the evaluation coverage, and expand benchmarking comprehensiveness.Our findings uncover prevalent obstacles and provide critical insights to inform future advancements in the field.

In recent years, Contrastive Learning (CL) has become a predominant representation learning paradigm for time series. Most existing methods manually build specific CL Strategies (CLS) by human heuristics for certain datasets and tasks. However, manually developing CLS usually requires excessive prior knowledge about the data, and massive experiments to determine the detailed CL configurations. In this paper, we present an Automated Machine Learning (AutoML) practice at Microsoft, which automatically learns CLS for time series datasets and tasks, namely Automated Contrastive Learning (AutoCL). We first construct a principled search space of size over 3 × 1012, covering data augmentation, embedding transformation, contrastive pair construction, and contrastive losses. Further, we introduce an efficient reinforcement learning algorithm, which optimizes CLS from the performance on the validation tasks, to obtain effective CLS within the space. Experimental results on various real-world datasets demonstrate that AutoCL could automatically find the suitable CLS for the given dataset and task. From the candidate CLS found by AutoCL on several public datasets/tasks, we compose a transferable Generally Good Strategy (GGS), which has a strong performance for other datasets. We also provide empirical analysis as a guide for the future design of CLS.

The field of machine learning (ML) has gained widespread adoption, leading to significant demand for adapting ML to specific scenarios, which is yet expensive and non-trivial.The predominant approaches towards the automation of solving ML tasks (e.g., AutoML) are often time-consuming and hard to understand for human developers.In contrast, though human engineers have the incredible ability to understand tasks and reason about solutions, their experience and knowledge are often sparse and difficult to utilize by quantitative approaches.In this paper, we aim to bridge the gap between machine intelligence and human knowledge by introducing a novel framework MLCopilot 1 , which leverages the state-of-the-art large language models to develop ML solutions for novel tasks.We showcase the possibility of extending the capability of LLMs to comprehend structured inputs and perform thorough reasoning for solving novel ML tasks.And we find that, after some dedicated design, the LLM can (i) observe from the existing experiences of ML tasks and (ii) reason effectively to deliver promising results for new tasks.The solution generated can be used directly to achieve high levels of competitiveness.

The performance of large language models (LLMs) is significantly influenced by the quality of the prompts provided.In response, researchers have developed enormous prompt engineering strategies aimed at modifying the prompt text to enhance task performance.In this paper, we introduce a novel technique termed position engineering, which offers a more efficient way to guide large language models.Unlike prompt engineering, which requires substantial effort to modify the text provided to LLMs, position engineering merely involves altering the positional information in the prompt without modifying the text itself.We have evaluated position engineering in two widely-used LLM scenarios: retrieval-augmented generation (RAG) and in-context learning (ICL).Our findings show that position engineering substantially improves upon the baseline in both cases.Position engineering thus represents a promising new strategy for exploiting the capabilities of large language models.

We introduce Nada, the first framework to autonomously design network algorithms by leveraging the generative capabilities of large language models (LLMs). Starting with an existing algorithm implementation, Nada enables LLMs to create a wide variety of alternative designs in the form of code blocks. It then efficiently identifies the top-performing designs through a series of filtering techniques, minimizing the need for full-scale evaluations and significantly reducing computational costs. Using adaptive bitrate (ABR) streaming as a case study, we demonstrate that Nada produces novel ABR algorithms---previously unknown to human developers---that consistently outperform the original algorithm in diverse network environments, including broadband, satellite, 4G, and 5G.

The computational challenges of Large Language Model (LLM) inference remain a significant barrier to their widespread deployment, especially as prompt lengths continue to increase. Due to the quadratic complexity of the attention computation, it takes 30 minutes for an 8B LLM to process a prompt of 1M tokens (i.e., the pre-filling stage) on a single A100 GPU. Existing methods for speeding up prefilling often fail to maintain acceptable accuracy or efficiency when applied to long-context LLMs. To address this gap, we introduce MInference (Milliontokens Inference), a sparse calculation method designed to accelerate pre-filling of long-sequence processing. Specifically, we identify three unique patterns in long-context attention matrices-the A-shape, Vertical-Slash, and Block-Sparse-that can be leveraged for efficient sparse computation on GPUs. We determine the optimal pattern for each attention head offline and dynamically build sparse indices based on the assigned pattern during inference. With the pattern and sparse indices, we perform efficient sparse attention calculations via our optimized GPU kernels to significantly reduce the latency in the pre-filling stage of longcontext LLMs. Our proposed technique can be directly applied to existing LLMs without any modifications to the pre-training setup or additional fine-tuning. By evaluating on a wide range of downstream tasks, including InfiniteBench, RULER, PG-19, and Needle In A Haystack, and models including LLaMA-3-1M, GLM-4-1M, Yi-200K, Phi-3-128K, and Qwen2-128K, we demonstrate that MInference effectively reduces inference latency by up to 10x for pre-filling on an A100, while maintaining accuracy. Our code is available at https://aka.ms/MInference.

Online video streaming has fundamental limitations on the transmission bandwidth and computational capacity and super-resolution is a promising potential solution. However, applying existing video super-resolution methods to online streaming is non-trivial. Existing video codecs and streaming protocols (e.g., WebRTC) dynamically change the video quality both spatially and temporally, which leads to diverse and dynamic degradations. Furthermore, online streaming has a strict requirement for latency that most existing methods are less applicable. As a result, this paper focuses on the rarely exploited problem setting of online streaming video super resolution. To facilitate the research on this problem, a new benchmark dataset named LDV-WebRTC is constructed based on a real-world online streaming system. Leveraging the new benchmark dataset, we propose a novel method specifically for online video streaming, which contains a convolution and Look-Up Table (LUT) hybrid model to achieve better performance-latency trade-off. To tackle the changing degradations, we propose a mixture-of-expert-LUT module, where a set of LUT specialized in different degradations are built and adaptively combined to handle different degradations. Experiments show our method achieves 720P video SR around 100 FPS, while significantly outperforms existing LUT-based methods and offers competitive performance compared to efficient CNN-based methods. Code is available at https://github.com/quzefan/ConvLUT.

Ensemble methods can deliver surprising performance gains but also bring significantly higher computational costs, e.g., can be up to 2048X in large-scale ensemble tasks. However, we found that the majority of computations in ensemble methods are redundant. For instance, over 77% of samples in CIFAR-100 dataset can be correctly classified with only a single ResNet-18 model, which indicates that only around 23% of the samples need an ensemble of extra models. To this end, we propose an inference efficient ensemble learning method, to simultaneously optimize for effectiveness and efficiency in ensemble learning. More specifically, we regard ensemble of models as a sequential inference process and learn the optimal halting event for inference on a specific sample. At each timestep of the inference process, a common selector judges if the current ensemble has reached ensemble effectiveness and halt further inference, otherwise filters this challenging sample for the subsequent models to conduct more powerful ensemble. Both the base models and common selector are jointly optimized to dynamically adjust ensemble inference for different samples with various hardness, through the novel optimization goals including sequential ensemble boosting and computation saving. The experiments with different backbones on real-world datasets illustrate our method can bring up to 56% inference cost reduction while maintaining comparable performance to full ensemble, achieving significantly better ensemble utility than other baselines. Code and supplemental materials are available at https://seqml.github.io/irene.

Vision transformers have shown great success due to their high model capabilities. However, their remarkable performance is accompanied by heavy computation costs, which makes them unsuitable for real-time applications. In this paper, we propose a family of high-speed vision transformers named Efficient ViT. We find that the speed of existing transformer models is commonly bounded by memory inefficient operations, especially the tensor reshaping and element-wise functions in MHSA. Therefore, we design a new building block with a sandwich layout, i.e., using a single memory-bound MHSA between efficient FFN layers, which improves memory efficiency while enhancing channel communication. Moreover, we discover that the attention maps share high similarities across heads, leading to computational redundancy. To address this, we present a cascaded group attention module feeding attention heads with different splits of the full feature, which not only saves computation cost but also improves attention diversity. Comprehensive experiments demonstrate EfficientViT outperforms existing efficient models, striking a good trade-off between speed and accuracy. For instance, our EfficientViT-M5 surpasses MobileNetV3-Large by 1.9% in accuracy, while getting 40.4% and 45.2% higher throughput on Nvidia V100 GPU and Intel Xeon CPU, respectively. Compared to the recent efficient model MobileViT-XXS, EfficientViT-M2 achieves 1.8% superior accuracy, while running$5.8\times/3.7\times$faster on the GPU/CPU, and$7.4\times faster$when converted to ONNX format. Code and models are available at here.

Large language models (LLMs) have been applied in various applications due to their astonishing capabilities.With advancements in technologies such as chain-of-thought (CoT) prompting and in-context learning (ICL), the prompts fed to LLMs are becoming increasingly lengthy, even exceeding tens of thousands of tokens.To accelerate model inference and reduce cost, this paper presents LLMLingua, a coarse-to-fine prompt compression method that involves a budget controller to maintain semantic integrity under high compression ratios, a token-level iterative compression algorithm to better model the interdependence between compressed contents, and an instruction tuning based method for distribution alignment between language models.We conduct experiments and analysis over four datasets from different scenarios, i.e., GSM8K, BBH, ShareGPT, and Arxiv-March23; showing that the proposed approach yields state-of-the-art performance and allows for up to 20x compression with little performance loss. 1

Deep learning training on cloud platforms usually follows the tradition of the separation of storage and computing. The training executes on a compute cluster equipped with GPUs/TPUs while reading data from a separate cluster hosting the storage service. To alleviate the potential bottleneck, a training cluster usually leverages its local storage as a cache to reduce the remote IO from the storage cluster. However, existing deep learning schedulers do not manage storage resources thus fail to consider the diverse caching effects across different training jobs. This could degrade scheduling quality significantly.

Monitoring and analyzing stereotypical behaviours is important for early intervention and care taking in Autism Spectrum Disorder (ASD). This paper focuses on automatically detecting stereotypical behaviours with computer vision techniques. Off-the-shelf methods tackle this task by supervised classification and activity recognition techniques. However, the un-bounded types of stereotypical behaviours and the difficulty in collecting video recordings of ASD patients largely limit the feasibility of the existing supervised detection methods. As a result, we tackle these challenges from a new perspective, i.e. unsupervised video anomaly detection for stereotypical behaviours detection. The models can be trained among unlabeled videos containing only normal behaviours and unknown types of abnormal behaviours can be detected during inference. Correspondingly, we propose a Dual Stream deep model for Stereotypical Behaviours Detection, DS-SBD, based on the temporal trajectory of human poses and the repetition patterns of human actions. Extensive experiments are conducted to verify the effectiveness of our proposed method and suggest that it serves as a potential benchmark for future research.

Neural Architecture Search (NAS) has shown promising performance in the automatic design of vision transformers (ViT) exceeding 1G FLOPs. However, designing lightweight and low-latency ViT models for diverse mobile devices remains a big challenge. In this work, we propose ElasticViT, a two-stage NAS approach that trains a high-quality ViT supernet over a very large search space for covering a wide range of mobile devices, and then searches an optimal sub-network (subnet) for direct deployment. However, current supernet training methods that rely on uniform sampling suffer from the gradient conflict issue: the sampled subnets can have vastly different model sizes (e.g., 50M vs. 2G FLOPs), leading to different optimization directions and inferior performance. To address this challenge, we propose two novel sampling techniques: complexity-aware sampling and performance-aware sampling. Complexity-aware sampling limits the FLOPs difference among the subnets sampled across adjacent training steps, while covering different-sized subnets in the search space. Performance-aware sampling further selects subnets that have good accuracy, which can reduce gradient conflicts and improve supernet quality. Our discovered models, ElasticViT models, achieve top-1 accuracy from 67.2% to 80.0% on ImageNet from 60M to 800M FLOPs without extra retraining, outperforming all prior CNNs and ViTs in terms of accuracy and latency. Our tiny and small models are also the first ViT models that surpass state-of-the-art CNNs with significantly lower latency on mobile devices. For instance, ElasticViT-S1 runs 2.62× faster than EfficientNet-B0 with 0.1% higher accuracy.

The combination of Neural Architecture Search (NAS) and quantization has proven successful in automatically designing low-FLOPs INT8 quantized neural networks (QNN). However, directly applying NAS to design accurate QNN models that achieve low latency on real-world devices leads to inferior performance. In this work, we identify that the poor INT8 latency is due to the quantization-unfriendly issue: the operator and configuration (e.g., channel width) choices in prior art search spaces lead to diverse quantization efficiency and can slow down the INT8 inference speed. To address this challenge, we propose SpaceEvo, an automatic method for designing a dedicated, quantization-friendly search space for each target hardware. The key idea of SpaceEvo is to automatically search hardware-preferred operators and configurations to construct the search space, guided by a metric called Q-T score to quantify how quantization-friendly a candidate search space is. We further train a quantized-for-all supernet over our discovered search space, enabling the searched models to be directly deployed without extra retraining or quantization. Our discovered models, SEQnet, establish new SOTA INT8 quantized accuracy under various latency constraints, achieving up to 10.1% accuracy improvement on ImageNet than prior art CNNs under the same latency. Extensive experiments on real devices show that SpaceEvo consistently outperforms manually-designed search spaces with up to 2.5× faster speed while achieving the same accuracy.

In vision-language modeling, image token removal is an efficient augmentation technique to reduce the cost of encoding image features. The CLIP-style models, however, have been found to be negatively impacted by this technique. We hypothesize that removing a large portion of image tokens may inadvertently destroy the semantic information associated to a given text description, resulting in misaligned paired data in CLIP training. To address this issue, we propose an attentive token removal approach, which retains a small number of tokens that have a strong semantic correlation to the corresponding text description. The correlation scores are dynamically evaluated through an EMA-updated vision encoder. Our method, termed attentive mask CLIP, outperforms original CLIP and CLIP variant with random token removal while saving the training time. In addition, our approach also enables efficient multi-view contrastive learning. Experimentally, by training ViT-B on YFCC-15M dataset, our approach achieves 43.9% top-1 accuracy on ImageNet-1K zero-shot classification, 62.7/42.1 and 38.0/23.2 I2T/T2I retrieval accuracy on Flickr30K and MS COCO, outperforming SLIP by +1.1%, +5.5/+0.9, and +4.4/+1.3, respectively, while being 2.30× faster. An efficient version of our approach runs 1.16× faster than the plain CLIP model, while achieving significant gains of +5.3%, +11.3/+8.0, and +9.5/+4.9 on these benchmarks, respectively. Code will be release in https://github.com/microsoft/A-CLIP.

Deploying pre-trained transformer models like BERT on downstream tasks in resource-constrained scenarios is challenging due to their high inference cost, which grows rapidly with input sequence length. In this work, we propose a constraint-aware and ranking-distilled token pruning method ToP, which selectively removes unnecessary tokens as input sequence passes through layers, allowing the model to improve online inference speed while preserving accuracy. ToP overcomes the limitation of inaccurate token importance ranking in the conventional self-attention mechanism through a ranking-distilled token distillation technique, which distills effective token rankings from the final layer of unpruned models to early layers of pruned models. Then, ToP introduces a coarse-to-fine pruning approach that automatically selects the optimal subset of transformer layers and optimizes token pruning decisions within these layers through improved L0 regularization. Extensive experiments on GLUE benchmark and SQuAD tasks demonstrate that ToP outperforms state-of-the-art token pruning and model compression methods with improved accuracy and speedups. ToP reduces the average FLOPs of BERT by 8.1X while achieving competitive accuracy on GLUE, and provides a real latency speedup of up to 7.4X on an Intel CPU. Code is available at https://github.com/microsoft/Moonlit/tree/main/ToP

While language-guided image manipulation has made remarkable progress, the challenge of how to instruct the manipulation process faithfully reflecting human intentions persists. An accurate and comprehensive description of a manipulation task using natural language is laborious and sometimes even impossible, primarily due to the inherent uncertainty and ambiguity present in linguistic expressions. Is it feasible to accomplish image manipulation without resorting to external cross-modal language information? If this possibility exists, the inherent modality gap would be effortlessly eliminated. In this paper, we propose a novel manipulation methodology, dubbed ImageBrush, that learns visual instructions for more accurate image editing. Our key idea is to employ a pair of transformation images as visual instructions, which not only precisely captures human intention but also facilitates accessibility in real-world scenarios. Capturing visual instructions is particularly challenging because it involves extracting the underlying intentions solely from visual demonstrations and then applying this operation to a new image. To address this challenge, we formulate visual instruction learning as a diffusion-based inpainting problem, where the contextual information is fully exploited through an iterative process of generation. A visual prompting encoder is carefully devised to enhance the model's capacity in uncovering human intent behind the visual instructions. Extensive experiments show that our method generates engaging manipulation results conforming to the transformations entailed in demonstrations. Moreover, our model exhibits robust generalization capabilities on various downstream tasks such as pose transfer, image translation and video inpainting.

Approximate Nearest Neighbor Search (ANNS) on high dimensional vector data is now widely used in various applications, including information retrieval, question answering, and recommendation. As the amount of vector data grows continuously, it becomes important to support updates to vector index, the enabling technique that allows for efficient and accurate ANNS on vectors.

Dynamic sparsity, where the sparsity patterns are unknown until runtime, poses a significant challenge to deep learning. The state-of-the-art sparsity-aware deep learning solutions are restricted to pre-defined, static sparsity patterns due to significant overheads associated with preprocessing. Efficient execution of dynamic sparse computation often faces the misalignment between the GPU-friendly tile configuration for efficient execution and the sparsity-aware tile shape that minimizes coverage wastes (non-zero values in tensor).

Deep learning-based models have achieved remarkable performance in video super-resolution (VSR) in recent years, but most of these models are less applicable to online video applications. These methods solely consider the distortion quality and ignore crucial requirements for online applications, e.g., low latency and low model complexity. In this paper, we focus on online video transmission in which VSR algorithms are required to generate high-resolution video sequences frame by frame in real time. To address such challenges, we propose an extremely low-latency VSR algorithm based on a novel kernel knowledge transfer method, named the convolutional kernel bypass graft (CKBG). First, we design a lightweight network structure that does not require future frames as inputs and saves extra time for caching these frames. Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with “kernel grafts”, which are extra convolutional kernels containing the prior knowledge of the external pretrained image SR models. During the testing phase, we further accelerate the grafted multibranch network by converting it into a simple single-path structure. The experimental results show that our proposed method can process online video sequences up to 110 FPS with very low model complexity and competitive SR performance.

Despite the impressive progress of general face detection, the tuning of hyper-parameters and architectures is still critical for the performance of a domain-specific face detector. Though existing AutoML works can speedup such process, they either require tuning from scratch for a new scenario or do not consider data privacy. To scale up, we derive a new AutoML setting from a platform perspective. In such setting, new datasets sequentially arrive at the platform, where an architecture and hyper-parameter configuration is recommended to train the optimal face detector for each dataset. This, however, brings two major challenges: (1) how to predict the best configuration for any given dataset without touching their raw images due to the privacy concern? and (2) how to continuously improve the AutoML algorithm from previous tasks and offer a better warm-up for future ones? We introduce “HyperFD”, a new privacy-preserving online AutoML framework for face detection. At its core part, a novel meta-feature representation of a dataset as well as its learning paradigm is proposed. Thanks to HyperFD, each local task (client) is able to effectively leverage the learning “experience” of previous tasks without uploading raw images to the platform; meanwhile, the meta-feature extractor is continuously learned to better trade off the bias and variance. Extensive experiments demonstrate the effectiveness and efficiency of our design.

Hypernasality is an abnormal resonance in human speech production, especially in patients with craniofacial anomalies such as cleft palate.In clinical application, hypernasality estimation is crucial in cleft palate diagnosis, as its results determine the subsequent surgery and additional speech therapy.Therefore, designing an automatic hypernasality assessment method will facilitate speech-language pathologists to make precise diagnoses.Existing methods for hypernasality estimation only conduct acoustic analysis based on low-resource cleft palate dataset, by using statistical or neural network-based features.In this paper, we propose a novel approach that uses automatic speech recognition model to improve hypernasality estimation.Specifically, we first pre-train an encoder-decoder framework in an automatic speech recognition (ASR) objective by using speech-to-text dataset, and then fine-tune ASR encoder on the cleft palate dataset for hypernasality estimation.Benefiting from such design, our model for hypernasality estimation can enjoy the advantages of ASR model: 1) compared with low-resource cleft palate dataset, the ASR task usually includes large-scale speech data in the general domain, which enables better model generalization; 2) the text annotations in ASR dataset guide model to extract better acoustic features.Experimental results on two cleft palate datasets demonstrate that our method achieves superior performance compared with previous approaches.

A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative representations. Unfortunately, these handcrafted objectives rely heavily on expert knowledge and may be sub-optimal. In this paper, we propose a principled and universal method for learning better representations with auxiliary loss functions, named Automated Auxiliary Loss Search (A2LS), which automatically searches for top-performing auxiliary loss functions for RL. Specifically, based on the collected trajectory data, we define a general auxiliary loss space of size $7.5 \times 10^{20}$ and explore the space with an efficient evolutionary search strategy. Empirical results show that the discovered auxiliary loss (namely, A2-winner) significantly improves the performance on both high-dimensional (image) and low-dimensional (vector) unseen tasks with much higher efficiency, showing promising generalization ability to different settings and even different benchmark domains. We conduct a statistical analysis to reveal the relations between patterns of auxiliary losses and RL performance.

Time series data generation has drawn increasing attention in recent years. Several generative adversarial network (GAN) based methods have been proposed to tackle the problem usually with the assumption that the targeted time series data are well-formatted and complete. However, real-world time series (RTS) data are far away from this utopia, e.g., long sequences with variable lengths and informative missing data raise intractable challenges for designing powerful generation algorithms. In this paper, we propose a novel generative framework for RTS data – RTSGAN to tackle the aforementioned challenges. RTSGAN first learns an encoder-decoder module which provides a mapping between a time series instance and a fixed-dimension latent vector and then learns a generation module to generate vectors in the same latent space. By combining the generator and the decoder, RTSGAN is able to generate RTS which respect the original feature distributions and the temporal dynamics. To generate time series with missing values, we further equip RTSGAN with an observation embedding layer and a decide-and-generate decoder to better utilize the informative missing patterns. Experiments on the four RTS datasets show that the proposed framework outperforms the previous generation methods in terms of synthetic data utility for downstream classification and prediction tasks. Our code is available at https://seqml.github.io/rtsgan.

With the recent trend of on-device deep learning, inference latency has become a crucial metric in running Deep Neural Network (DNN) models on various mobile and edge devices. To this end, latency prediction of DNN model inference is highly desirable for many tasks where measuring the latency on real devices is infeasible or too costly, such as searching for efficient DNN models with latency constraints from a huge model-design space. Yet it is very challenging and existing approaches fail to achieve a high accuracy of prediction, due to the varying model-inference latency caused by the runtime optimizations on diverse edge devices.