Aiwei Liu

StableToken: A Noise-Robust Semantic Speech Tokenizer for Resilient SpeechLLMs

PMark: Towards Robust and Distortion-free Semantic-level Watermarking with Channel Constraints

You only need 4 extra tokens: Synergistic Test-time Adaptation for LLMs

WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild

MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection

Omni-SafetyBench: A Benchmark for Safety Evaluation of Audio-Visual Large Language Models

Can Watermarked LLMs be Identified by Users via Crafted Prompts?

TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights

Less is More: Extreme Gradient Boost Rank-1 Adaption for Efficient Finetuning of LLMs

Mitigating Modality Prior-Induced Hallucinations in Multimodal Large Language Models via Deciphering Attention Causality

EXPLORING RESPONSE UNCERTAINTY IN MLLMS: AN EMPIRICAL EVALUATION UNDER MISLEADING SCENARIOS

Interpretable Contrastive Monte Carlo Tree Search Reasoning