activity
20242026
collaborators

11 papers

cs.CV2026

Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs

Xuan Zhang, Cunxiao Du, Sicheng Yu +4

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the…

cs.CL2026

LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation

Xuan Zhang, Fengzhuo Zhang, Cunxiao Du +4

Scaling language models to handle longer contexts introduces substantial memory challenges due to the growing cost of key-value (KV) caches. Motivated by the efficiency gains of hy…

cs.CL2026

LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification

Penghui Yang, Cunxiao Du, Fengzhuo Zhang +4

As Large Language Models (LLMs) can now process extremely long contexts, efficient inference over these extended inputs has become increasingly important, especially for emerging a…

cs.LG2026

Demystifying the Slash Pattern in Attention: The Role of RoPE

Yuan Cheng, Fengzhuo Zhang, Yunlong Hou +5

Large Language Models (LLMs) often exhibit slash attention patterns, where attention scores concentrate along the -th sub-diagonal for some offset . These patterns play a k…

cs.CV2026

Annealed Relaxation of Speculative Decoding for Faster Autoregressive Image Generation

Xingyao Li, Fengzhuo Zhang, Cunxiao Du +1

Despite significant progress in autoregressive image generation, inference remains slow due to the sequential nature of AR models and the ambiguity of image tokens, even when using…

cs.LG2025

BanditSpec: Adaptive Speculative Decoding via Bandit Algorithms

Yunlong Hou, Fengzhuo Zhang, Cunxiao Du +6

Speculative decoding has emerged as a popular method to accelerate the inference of Large Language Models (LLMs) while retaining their superior text generation performance. Previou…