NeurIPS 2025 Explorer
Concepts
Authors
Glossary
johnsanterre.github.io
task-specific rewards
3 papers
Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment
Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models
SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning