activity
20242026
collaborators

12 papers

cs.CL2026

Convolution for Large Language Models

Yuchuan Tian, Yingte Shu, Wei He +7

Large language models (LLMs) largely rely on Transformers, where self-attention provides global token interaction but does not explicitly encode the locality of natural language. W…

cs.CL2026

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs

Tengxuan Liu, Shiyao Li, Jiayi Yang +7

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT rea…

cs.CL2026

FlexDraft: Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration

Yaojie Zhang, Jianuo Huang, Junlong Ke +5

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify…

cs.LG2026

Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs

Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3

Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel d…

cs.CV2026

SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer

Tongcheng Fang, Hanling Zhang, Ruiqi Xie +8

Diffusion Transformers have demonstrated remarkable performance in video generation. However, their long input sequences incur substantial latency due to the quadratic complexity o…

cs.RO2026

StreamingVLA: Streaming Vision-Language-Action Model with Action Flow Matching and Adaptive Early Observation

Yiran Shi, Dongqi Guo, Tianchen Zhao +8

Vision-language-action (VLA) models have demonstrated exceptional performance in natural language-driven perception and control. However, the high computational cost of VLA models…