Lijie Wen

REMA: A Unified Reasoning Manifold Framework for Interpreting Large Language Model

LiRA: Linguistic Robust Anchoring for Cross-lingual Large Language Models

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

Efficient Heuristics Generation for Solving Combinatorial Optimization Problems Using Large Language Models

C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention

Interpretable Contrastive Monte Carlo Tree Search Reasoning