The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 4 days ago • 388
Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access Paper • 2610.33079 • Published 9 days ago • 16
BrickWright: Agentic Creation of Physically Feasible Brick Builds Paper • 2610.31651 • Published 8 days ago • 14
RuleTrek: Benchmarking Agentic Rule Reasoning in Complex Scenarios Paper • 2610.19698 • Published 16 days ago • 79
Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation Paper • 2609.38748 • Published 22 days ago • 69
orcarouter/OrcaSAQ-2-Cyber-27B-Uncensored-GGUF Text Generation • 27B • Updated 3 days ago • 24.8k • 570
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation Paper • 2609.20744 • Published Sep 17 • 50
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation Paper • 2609.08084 • Published Sep 8 • 68
Locked at the Entrance, Open Inside: Where RLVR Narrows the Solution Space Paper • 2608.29188 • Published Aug 29 • 10
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published Sep 3 • 65
Thinking in a Low-Resource Language: What SFT Builds, What RL Fixes, What Accuracy Cannot See Paper • 2608.17744 • Published Aug 18 • 15