collaborators

7 papers

cs.LG2026

CommitKV: Lifecycle-Aware KV Cache Compression via Commit Transitions for Multi-Turn Agents

Weizhong Huang, Jinchao Zhang, Xiawu Zheng

Multi-turn Reasoning-and-Acting (ReAct) agents accumulate growing trajectories of reasoning, tool calls, and observations. Their key-value (KV) caches grow accordingly, increasing…

q-bio.NC2026

Neural Langevin Machine: a local asymmetric learning rule can be creative

Zhendong Yu, Weizhong Huang, Haiping Huang

Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neur…

cs.CV2025

QuoTA: Query-oriented Token Assignment via CoT Query Decouple for Long Video Comprehension

Yongdong Luo, Wang Chen, Xiawu Zheng +8

Recent advances in long video understanding typically mitigate visual redundancy through visual token pruning based on attention distribution. However, while existing methods emplo…

q-bio.NC2025

Freezing chaos without synaptic plasticity

Weizhong Huang, Haiping Huang

Chaos is ubiquitous in high-dimensional neural dynamics. A strong chaotic fluctuation may be harmful to information processing. A traditional way to mitigate this issue is to intro…

cs.LG2025

Dynamic Low-Rank Sparse Adaptation for Large Language Models

Weizhong Huang, Yuxin Zhang, Xiawu Zheng +4

Despite the efficacy of network sparsity in alleviating the deployment strain of Large Language Models (LLMs), it endures significant performance degradation. Applying Low-Rank Ada…

cs.LG2025

Determining Layer-wise Sparsity for Large Language Models Through a Theoretical Perspective

Weizhong Huang, Yuxin Zhang, Xiawu Zheng +2

In this paper, we address the challenge of determining the layer-wise sparsity rates of large language models (LLMs) through a theoretical perspective. Specifically, we identify a…