collaborators

7 papers

cs.CL2025

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

Chenlong Deng, Zhisong Zhang, Kelong Mao +6

Large language models are increasingly capable of handling long-context inputs, but the memory overhead of key-value (KV) cache remains a major bottleneck for general-purpose deplo…

cs.CL2025

Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation

Junyu Ma, Tianqing Fang, Zhisong Zhang +3

Mamba's theoretical infinite-context potential is limited in practice when sequences far exceed training lengths. This work explores unlocking Mamba's long-context memory ability b…

cs.CV2025

VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models

Ce Zhang, Kaixin Ma, Tianqing Fang +5

Recent Large Vision-Language Models (LVLMs) have advanced multi-modal understanding by incorporating finer-grained visual perception and encoding. However, such methods incur signi…

cs.CL2025

WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback

Minda Hu, Tianqing Fang, Jianshu Zhang +7

Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment…

cs.CL2025

UNCLE: Benchmarking Uncertainty Expressions in Long-Form Generation

Ruihan Yang, Caiqi Zhang, Zhisong Zhang +4

Large Language Models (LLMs) are prone to hallucination, particularly in long-form generations. A promising direction to mitigate hallucination is to teach LLMs to express uncertai…

cs.CL2024

A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression

Chenlong Deng, Zhisong Zhang, Kelong Mao +4

In this work, we provide a thorough investigation of gist-based context compression methods to improve long-context processing in large language models. We focus on two key questio…