OSReward: Instituting Standardized Evaluation for Cross-Platform Computer-Use Reward Models
Paper • 2607.28609 • Published • 67
Zesen Zhao
SourORZ
AI & ML interests
RL
Recent Activity
upvoted a paper about 2 months ago
Foresight: Failure Detection for Long-Horizon Robotic Manipulation with Action-Conditioned World Model Latents upvoted a paper 10 months ago
TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion
ControlOrganizations
