activity
20242026
collaborators

7 papers

cs.HC2026

Large Language Models have Chain-of-Affect

Junjie Xu, Xingjiao Wu, Luwei Xiao +11

As large language models (LLMs) move into persistent, user-facing roles, their behavior must be understood not as isolated responses but as a trajectory unfolding over sustained in…

cs.CL2026

Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models

Amogh Sheth, Biruk Assefa, Yi Wen Huang +2

Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifi…

cs.CV2025

PathAgent: Toward Interpretable Analysis of Whole-slide Pathology Images via Large Language Model-based Agentic Reasoning

Jingyun Chen, Linghan Cai, Zhikang Wang +5

Analyzing whole-slide images (WSIs) requires an iterative, evidence-driven reasoning process that parallels how pathologists dynamically zoom, refocus, and self-correct while colle…

cs.LG2025

The 'Sure' Trap: Multi-Scale Poisoning Analysis of Stealthy Compliance-Only Backdoors in Fine-Tuned Large Language Models

Yuting Tan, Yi Huang, Zhuo Li

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common…

cs.CV2025

MindVL: Towards Efficient and Effective Training of Multimodal Large Language Models on Ascend NPUs

Feilong Chen, Yijiang Liu, Yi Huang +5

We propose MindVL, a multimodal large language model (MLLMs) trained on Ascend NPUs. The training of state-of-the-art MLLMs is often confined to a limited set of hardware platforms…

cs.AI2024

ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning

Yi Huang, Fangyin Cheng, Fan Zhou +7

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in data analytics when integrated with Multi-Agent Systems (MAS). However, these systems oft…