6 papers
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
Langzhou He, Junyou Zhu, Yue Zhou +7
Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy…
RuPLaR : Efficient Latent Compression of LLM Reasoning Chains with Rule-Based Priors From Multi-Step to One-Step
Xiaocheng Luo, Kang Wang, Zaifu Zhan +2
The Chain-of-Thought (CoT) paradigm, while enhancing the interpretability of Large Language Models (LLMs), is constrained by the inefficiencies and expressive limits of natural lan…
LongFlow: Efficient KV Cache Compression for Reasoning Models
Yi Su, Zhenxu Tian, Dan Qiao +3
Recent reasoning models such as OpenAI-o1 and DeepSeek-R1 have shown strong performance on complex tasks including mathematical reasoning and code generation. However, this perform…
: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving
Yuechi Zhou, Yi Su, Jianxin Zhang +5
Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conve…
CaliDrop: KV Cache Compression with Calibration
Yi Su, Quantong Qiu, Yuechi Zhou +6
Large Language Models (LLMs) require substantial computational resources during generation. While the Key-Value (KV) cache significantly accelerates this process by storing attenti…
Accurate KV Cache Quantization with Outlier Tokens Tracing
Yi Su, Yuechi Zhou, Quantong Qiu +6
The impressive capabilities of Large Language Models (LLMs) come at the cost of substantial computational resources during deployment. While KV Cache can significantly reduce recom…