AI.info

Yuxin Jiang

Explore Yuxin Jiang on AI.info.

• Olaf-World: Orienting Latent Actions for Video World Modeling
• P-RAG: Prompt-Enhanced Parametric RAG with LoRA and Selective CoT for Biomedical and Multi-Hop QA
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents