155 citations · 366 across the 34 of their papers we have counts for
36 papers
Training-Free Predictive Spatio-Temporal Token Pruning for Few-Step Autoregressive Video Diffusion
Jia Li, Xurui Peng, Xing Wang +1
Few-step autoregressive (AR) video diffusion models generate videos chunk by chunk and have made efficient video generation practical. However, further accelerating these models to…
Efficient Reasoning Exploration via State-Conditioned Latent Steering with Progress Guidance
Hengyuan Zhang, Chenming Shang, Zunhai Su +10
Best-of- is a widely used inference strategy for complex reasoning, whose effectiveness depends on whether sampled candidates can cover diverse and high-quality reasoning paths.…
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
Xiaomeng Fu, Jia Li, Yiming Hu +5
Autoregressive (AR) streaming models have emerged as a powerful paradigm for long video generation. However, the linearly growing Key-Value (KV) cache poses a significant bottlenec…
Learning to See through Illumination Extremes with Event Streaming in Multimodal Large Language Models
Baoheng Zhang, Jiahui Liu, Gui Zhao +7
Multimodal Large Language Models (MLLMs) perform strong vision-language reasoning under standard conditions but fail in extreme illumination, where RGB inputs lose irrevocable stru…
Residual Decoding: Mitigating Hallucinations in Large Vision-Language Models via History-Aware Residual Guidance
Xinrong Chen, Xu Chu, Yingmin Qiu +8
Large Vision-Language Models (LVLMs) can reason from image-text inputs and perform well in various multimodal tasks. Despite this success, they are affected by language priors and…
Beyond Outliers: A Data-Free Layer-wise Mixed-Precision Quantization Approach Driven by Numerical and Structural Dual-Sensitivity
Hengyuan Zhang, Xinrong Chen, Zunhai Su +10
Layer-wise mixed-precision quantization (LMPQ) enables effective compression under extreme low-bit settings by allocating higher precision to sensitive layers. However, existing me…
Train Short, Inference Long: Training-free Horizon Extension for Autoregressive Video Generation
Jia Li, Xiaomeng Fu, Xurui Peng +7
Autoregressive video diffusion models have emerged as a scalable paradigm for long video generation. However, they often suffer from severe extrapolation failure, where rapid error…
Lifecycle Cost-Effectiveness Modeling for Redundancy-Enhanced Multi-Chiplet Architectures
Zizhen Liu, Fangzhiyi Wang, Mengdi Wang +4
The growing demand for compute-intensive applications has made multi-chiplet architectures a promising alternative to monolithic designs, offering improved scalability and manufact…
Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
Hengyuan Zhang, Zhihao Zhang, Mingyang Wang +26
Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat…
Find Your Optimal Teacher: Personalized Data Synthesis via Router-Guided Multi-Teacher Distillation
Hengyuan Zhang, Shiping Yang, Xiao Liang +8
Training student models on synthetic data generated by strong teacher models is a promising way to distilling the capabilities of teachers. However, recent studies show that strong…
Fully Integrated Memristive Spiking Neural Network with Analog Neurons for High-Speed Event-Based Data Processing
Zhu Wang, Song Wang, Zhiyuan Du +5
The demand for edge artificial intelligence to process event-based, complex data calls for hardware beyond conventional digital, von-Neumann architectures. Neuromorphic computing,…
SeerAttention-R: Sparse Attention Adaptation for Long Reasoning
Yizhao Gao, Shuming Guo, Shijie Cao +12
We introduce SeerAttention-R, a sparse attention framework specifically tailored for the long decoding of reasoning models. Extended from SeerAttention, SeerAttention-R retains the…
GuiLoMo: Allocating Expert Number and Rank for LoRA-MoE via Bilevel Optimization with GuidedSelection Vectors
Hengyuan Zhang, Xinrong Chen, Yingmin Qiu +7
Parameter-efficient fine-tuning (PEFT) methods, particularly Low-Rank Adaptation (LoRA), offer an efficient way to adapt large language models with reduced computational costs. How…
TATAA: Programmable Mixed-Precision Transformer Acceleration with a Transformable Arithmetic Architecture
Jiajun Wu, Mo Song, Jingmin Zhao +3
Modern transformer-based deep neural networks present unique technical challenges for effective acceleration in real-world applications. Apart from the vast amount of linear operat…
SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs
Yizhao Gao, Zhichen Zeng, Dayou Du +8
Attention is the cornerstone of modern Large Language Models (LLMs). Yet its quadratic complexity hinders efficiency and scalability, especially for long-context processing. A prom…
Co-designing a Sub-millisecond Latency Event-based Eye Tracking System with Submanifold Sparse CNN
Baoheng Zhang, Yizhao Gao, Jingyuan Li +1
Eye-tracking technology is integral to numerous consumer electronics applications, particularly in the realm of virtual and augmented reality (VR/AR). These applications demand sol…
Event-Based Eye Tracking. AIS 2024 Challenge Survey
Zuowen Wang, Chang Gao, Zongwei Wu +36
This survey reviews the AIS 2024 Event-Based Eye Tracking (EET) Challenge. The task of the challenge focuses on processing eye movement recorded with event cameras and predicting t…
A Composable Dynamic Sparse Dataflow Architecture for Efficient Event-based Vision Processing on FPGA
Yizhao Gao, Baoheng Zhang, Yuhao Ding +1
Event-based vision represents a paradigm shift in how vision information is captured and processed. By only responding to dynamic intensity changes in the scene, event-based sensin…
Random resistive memory-based deep extreme point learning machine for unified visual processing
Shaocong Wang, Yizhao Gao, Yi Li +21
Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive m…
SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features
Song Wang, Zhu Wang, Can Li +2
In comparison to conventional RGB cameras, the superior temporal resolution of event cameras allows them to capture rich information between frames, making them prime candidates fo…
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
Jiajun Zhou, Jiajun Wu, Yizhao Gao +7
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched. A prominent challenge is to quantize the DNN models into…
Exploiting Elasticity in Tensor Ranks for Compressing Neural Networks
Jie Ran, Rui Lin, Hayden K. H. So +2
Elasticities in depth, width, kernel size and resolution have been explored in compressing deep neural networks (DNNs). Recognizing that the kernels in a convolutional neural netwo…
HAO: Hardware-aware neural Architecture Optimization for Efficient Inference
Zhen Dong, Yizhao Gao, Qijing Huang +3
Automatic algorithm-hardware co-design for DNN has shown great success in improving the performance of DNNs on FPGAs. However, this process remains challenging due to the intractab…
Mix and Match: A Novel FPGA-Centric Deep Neural Network Quantization Framework
Sung-En Chang, Yanyu Li, Mengshu Sun +5
Deep Neural Networks (DNNs) have achieved extraordinary performance in various application domains. To support diverse DNN models, efficient implementations of DNN inference on edg…