DynaGuard: A Dynamic Guardrail Model With User-Defined Policies Paper • 2509.02563 • Published 4 days ago • 17
MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning Paper • 2506.05523 • Published Jun 5 • 34
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach Paper • 2502.05171 • Published Feb 7 • 150