activity
20242026
collaborators

9 papers

cs.CV2026

Diagnosing Visual Ignorance in Vision-Language Models

Runyu Zhou, Qi Zhang, Qixun Wang +1

Vision-Language Models (VLMs) frequently rely on language priors, producing confident answers that are weakly grounded in visual evidence. While this behavior is widely observed, i…

cs.CL2026

TrustLDM: Benchmarking Trustworthiness in Language Diffusion Models

Yichuan Mo, Yukun Jiang, Yanbo Shi +4

The rapid development of Language Diffusion Models (LDMs) challenges the dominant position of auto-regressive competitors in language processing. However, their flexible, any-order…

cs.LG2026

On the Adversarial Transferability of Generalized "Skip Connections"

Yisen Wang, Yichuan Mo, Dongxian Wu +3

Skip connection is an essential ingredient for modern deep models to be deeper and more powerful. Despite their huge success in normal scenarios (state-of-the-art classification pe…

cs.CL2026

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Mingjie Li, Wai Man Si, Michael Backes +2

Despite the impressive performance of general-purpose large language models (LLMs), they often require fine-tuning or post-training to excel at specific tasks. For instance, large…

cs.LG2025

Decoding Large Language Diffusion Models with Foreseeing Movement

Yichuan Mo, Quan Chen, Mingjie Li +2

Large Language Diffusion Models (LLDMs) benefit from a flexible decoding mechanism that enables parallelized inference and controllable generations over autoregressive models. Yet…

cs.AI2025

Know When to Explore: Difficulty-Aware Certainty as a Guide for LLM Reinforcement Learning

Ang Li, Zhihang Yuan, Yang Zhang +2

Reinforcement Learning with Verifiable Feedback (RLVF) has become a key technique for enhancing the reasoning abilities of Large Language Models (LLMs). However, its reliance on sp…