Chen Chen
4 papers · Latest:
Large Language Models are Universal Reasoners for Visual Generation
UniReasoner uses LLMs as universal reasoners to close the understanding-generation gap in text-to-image models via self-critiqued visual drafts.
PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning
PRISM introduces a black-box on-policy distillation stage to align large multimodal models, mitigating distributional drift between SFT and RLVR for improved performance.
Projected Attainable Speed Space: A Driving Efficiency Metric Connecting Instantaneous Evaluation to Travel Time
Introduces Projected Attainable Speed Space (PASS), a unified driving efficiency metric for AVs, linking instantaneous performance to overall travel time.
Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders
This paper introduces Windowed Partial AUC (WPAUC) and TAWin RL to optimize LLM recommenders, improving Top-K performance by better handling hard negatives.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.