Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Paper • 2510.25992 • Published • 48
Grant Singleton
grantsing
AI & ML interests
Computer vision, robotics, LLMs
Recent Activity
commentedon a paper about 22 hours ago
Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation commentedon a paper about 22 hours ago
DreamID-Omni: Unified Framework for Controllable Human-Centric Audio-Video Generation commentedon a paper about 22 hours ago
Exposing the Systematic Vulnerability of Open-Weight Models to Prefill AttacksOrganizations
None yet