OmniVideo-100K: A Dataset for Audio-Visual Reasoning through Structured Scripts and Evidence Chains Paper • 2606.14702 • Published 9 days ago • 31
BRDFusion: Physics Meets Generation for Urban Scene Inverse Rendering Paper • 2606.17049 • Published 6 days ago • 27
Who Should Lead Decoding Now? Tracking Reliable Trajectories for Ensembling Masked Diffusion Language Models Paper • 2606.16281 • Published 6 days ago • 33
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models Paper • 2606.16140 • Published 6 days ago • 102
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published 5 days ago • 196
FastContext: Training Efficient Repository Explorer for Coding Agents Paper • 2606.14066 • Published 9 days ago • 89
MMDiff: Extending Diffusion Transformers for Multi-Modal Generation Paper • 2606.16673 • Published 6 days ago • 5