Tianlong Chen

6 papers University of North Carolina at Chapel Hill

• $\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer
• BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model
• IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios
• Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures
• Multi-Agent Debate for LLM Judges with Adaptive Stability Detection
• One Token Embedding Is Enough to Deadlock Your Large Reasoning Model