AI.info

Yejin Choi

Explore Yejin Choi on AI.info.

• SPADE: Self-Play in Adaptive Synthetic Executable Environments
• ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment
• Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
• Privasis: Synthesizing the Largest "Public" Private Dataset from Scratch
• MoCo: A One-Stop Shop for Model Collaboration Research
• Learning to Discover at Test Time
• End-to-End Test-Time Training for Long Context
• NVIDIA Nemotron 3: Efficient and Open Intelligence
• ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
• Latent Collaboration in Multi-Agent Systems
• Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
• Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)
• ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge
• VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents
• MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
• Opt-ICL at LeWiDi-2025: Maximizing In-Context Signal from Rater Examples via Meta-Learning