Yi Dong

6

Papers

234

Total Citations

Papers (6)

HelpSteer2-Preference: Complementing Ratings with Preferences

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

NeurIPS 2025arXiv

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

NeurIPS 2025arXiv

FALCON: Fine-grained Activation Manipulation by Contrastive Orthogonal Unalignment for Large Language Model

Feature Purification Matters: Suppressing Outlier Propagation for Training-Free Open-Vocabulary Semantic Segmentation

ChromaFusionNet (CFNet): Natural Fusion of Fine-Grained Color Editing