Yi Dong

ProfBench: Multi-Domain Rubrics requiring Professional Knowledge to Answer and Judge

RLBFF: Binary Flexible Feedback to bridge between Human Feedback & Verifiable Rewards

Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning

The Invisible Leash? Why RLVR May or May Not Escape Its Origin

ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration

BroRL: Scaling Reinforcement Learning via Broadened Exploration

TinyEye: Sharpening Visual Reasoning of Tiny Models with Offline Policy Optimization

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

HelpSteer2-Preference: Complementing Ratings with Preferences

Diverging Preferences: When do Annotators Disagree and do Models Know?

Diverging Preferences: When do Annotators Disagree and do Models Know?