9 papers
Seen, Said, or Forgotten? A Causal Audit of Visual KV Memory Across Dialog Turns
Hong Chen, Kang Chen, Yuxuan Fan +4
Stateful multimodal assistants encode an image once but may answer questions about it many turns later. Attention-guided visual-KV eviction assumes that evidence irrelevant now wil…
Semantic Integrity Matters: Benchmarking and Preserving High-Density Reasoning in KV Cache Compression
Xiang Liu, Zhenheng Tang, Hong Chen +6
While Key-Value (KV) cache compression is essential for efficient LLM inference, current evaluations disproportionately focus on sparse retrieval tasks, potentially masking the deg…
DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
Xiang Liu, Xuming Hu, Xiaowen Chu +1
Recent reasoning Large Language Models (LLMs) demonstrate remarkable problem-solving abilities but often generate long thinking traces whose utility is unclear. Our work aims to im…
SSR: Speculative Parallel Scaling Reasoning in Test-time
Yuanlin Chu, Bo Wang, Xiang Liu +3
Large language models (LLMs) have achieved impressive results on multi-step mathematical reasoning, yet at the cost of high computational overhead. This challenge is particularly a…
SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
Hong Chen, Xiang Liu, Bo Wang +5
The linear growth of Key-Value (KV) cache remains a bottleneck for multi-turn LLM deployment. Existing KV cache compression methods often fail to account for the structural propert…
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Xiang Liu, Zhenheng Tang, Peijie Dong +5
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Althoug…