AI.info

Xinyi Wang

Explore Xinyi Wang on AI.info.

• Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas
• Atomic Skills are the Prerequisite: When Reinforcement Learning Synthesizes Compositional Reasoning, and When It Only Amplifies
• AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
• Don't Tell the Answer, Truly Guide the Reasoning During RL Rollouts