Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs Paper • 2608.12781 • Published 11 days ago • 33
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe Paper • 2605.03677 • Published May 5 • 28
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe Paper • 2605.03677 • Published May 5 • 28
Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents Paper • 2605.07630 • Published May 8 • 1