Huishuai Zhang

FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs

LEARNING TO GENERATE FORMALLY VERIFIABLE STEP-BY-STEP LOGIC REASONING VIA STRUCTURED FORMAL INTERMEDIARIES

MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning

K-frames: Scene-Driven Any-k Keyframe Selection for Long Video Understanding

Beyond Isolated Facts: Synthesizing Narrative and Grounded Supervision for VideoQA

Efficient RL Training for Reasoning Models via Length-Aware Optimization

Synthesize Privacy-Preserving High-Resolution Images via Private Textual Intermediaries

Automatic Jailbreaking of Text-to-Image Generative AI Systems for Copyright Infringement

Understanding Nonlinear Implicit Bias via Region Counts in Input Space

Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes

Understanding Nonlinear Implicit Bias via Region Counts in Input Space

Evidence-Enhanced Triplet Generation Framework for Hallucination Alleviation in Generative Question Answering

On the Convergence of Adam under Non-uniform Smoothness: Separability from SGDM and Beyond

Towards Efficient and No Forgetting Domain Continual Pretraining by Mitigating the Stability Gap

AIDBench: A benchmark for evaluating the authorship identification capability of large language models

Latent Preference Coding: Aligning Large Language Models via Discrete Latent Codes