12 papers
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…
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…
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…
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…
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…
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…