Trung Bui

Steering MoE LLMs via Expert (De)Activation

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Toward Robust Hyper-Detailed Image Captioning: A Multiagent Approach and Dual Evaluation Metrics for Factuality and Coverage

NoLiMa: Long-Context Evaluation Beyond Literal Matching

DynaSaur: Large Language Agents Beyond Predefined Actions

VSP: Assessing the dual challenges of perception and reasoning in spatial planning tasks for MLLMs

Taipan: Efficient and Expressive State Space Language Models with Selective Attention

Enhancing Factuality in Detailed Image Captioning with LLM-MLLM Collaboration