ROSS: Relearning from Self-Generated Rollouts through Selective Supervision
Paper • 2609.35954 • Published • 52
Pusen Dong
Dowsonsss
·
AI & ML interests
None yet
Recent Activity
upvoted a paper 9 days ago
ROSS: Relearning from Self-Generated Rollouts through Selective Supervision upvoted a paper 10 days ago
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents upvoted a paper 10 days ago
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General AgentsOrganizations
None yet
upvoted a paper 9 days ago
upvoted 3
papers 10 days ago
Learning to Learn from Context: Synthetic Training from Perturbed Public Documents
Paper • 2609.33642 • Published • 33
Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents
Paper • 2609.33772 • Published • 35
CompoWorld: Compositional Environment Scaling for General Agents
Paper • 2609.33665 • Published • 41
upvoted 3
papers 5 months ago
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills
Paper • 2605.23899 • Published • 27
Lens: Rethinking Training Efficiency for Foundational Text-to-Image Models
Paper • 2605.21573 • Published • 109
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
Paper • 2605.10344 • Published • 52