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 9 hours ago
MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models commentedon a paper about 9 hours ago
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models commentedon a paper about 9 hours ago
The Trinity of Consistency as a Defining Principle for General World ModelsOrganizations
None yet