activity
20242026
collaborators

7 papers

cs.CL2026

V-SEAM: Visual Semantic Editing and Attention Modulating for Causal Interpretability of Vision-Language Models

Qidong Wang, Junjie Hu, Ming Jiang

Recent advances in causal interpretability have extended from language models to vision-language models (VLMs), seeking to reveal their internal mechanisms through input interventi…

cs.CV2025

dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning

Yingzi Ma, Yulong Cao, Wenhao Ding +6

The autonomous driving community is increasingly focused on addressing the challenges posed by out-of-distribution (OOD) driving scenarios. A dominant research trend seeks to enhan…

eess.IV2025

AT-CXR: Uncertainty-Aware Agentic Triage for Chest X-rays

Xueyang Li, Mingze Jiang, Gelei Xu +4

Agentic AI is advancing rapidly, yet truly autonomous medical-imaging triage, where a system decides when to stop, escalate, or defer under real constraints, remains relatively und…

cs.LG2025

SIMCOPILOT: Evaluating Large Language Models for Copilot-Style Code Generation

Mingchao Jiang, Abhinav Jain, Sophia Zorek +1

We introduce SIMCOPILOT, a benchmark that simulates the role of large language models (LLMs) as interactive, "copilot"-style coding assistants. Targeting both completion (finishing…

cs.CL2025

No Preference Left Behind: Group Distributional Preference Optimization

Binwei Yao, Zefan Cai, Yun-Shiuan Chuang +4

Preferences within a group of people are not uniform but follow a distribution. While existing alignment methods like Direct Preference Optimization (DPO) attempt to steer models t…

cs.CL2025

Large Language Models Are Active Critics in NLG Evaluation

Shuying Xu, Junjie Hu, Ming Jiang

The conventional paradigm of using large language models (LLMs) for natural language generation (NLG) evaluation relies on pre-defined task definitions and evaluation criteria, pos…