Guoshun Nan

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

Offline Reinforcement Learning with Adaptive Feature Fusion

The Invisible Mind: Auditing Privacy Invocation in Latent Chain-of-Thought Reasoning

Learning to Respond: A Large-Scale Benchmark and Progressive Learning Framework for Trigger-Centric Online Video Understanding

Trajectory Generation with Conservative Value Guidance for Offline Reinforcement Learning

Towards Robust Agentic Systems through Generative Flow Exploration of Primitives

Multi-agent Imitates Enterprise Dynamics

Balance Your Move: Investigating Text to Motion from a Signal Density Measuring View

Mitigating Hallucination in Multimodal Reasoning via Functional Attention Control

O²-CritiCuRL: Offline-Online Step-aware Curriculum Reinforcement Learning for Visual Reasoning

Advancing Expert Specialization for Better MoE

KGMark: A Diffusion Watermark for Knowledge Graphs

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models