DINOv3 Collection DINOv3: foundation models producing excellent dense features, outperforming SotA w/o fine-tuning - https://arxiv.org/abs/2508.10104 • 13 items • Updated Aug 21 • 403
NextStep-1: Toward Autoregressive Image Generation with Continuous Tokens at Scale Paper • 2508.10711 • Published Aug 14 • 144
Open Vision Reasoner: Transferring Linguistic Cognitive Behavior for Visual Reasoning Paper • 2507.05255 • Published Jul 7 • 74
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge Paper • 2507.04447 • Published Jul 6 • 44
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge Paper • 2507.04447 • Published Jul 6 • 44
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge Paper • 2507.04447 • Published Jul 6 • 44 • 2
OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models Paper • 2506.03135 • Published Jun 3 • 40
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Paper • 2505.24863 • Published May 30 • 97
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Paper • 2505.24863 • Published May 30 • 97
AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time Paper • 2505.24863 • Published May 30 • 97 • 2
ReCamMaster: Camera-Controlled Generative Rendering from A Single Video Paper • 2503.11647 • Published Mar 14 • 145
Learning Getting-Up Policies for Real-World Humanoid Robots Paper • 2502.12152 • Published Feb 17 • 42 • 3
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation Paper • 2502.13143 • Published Feb 18 • 31
SoFar Collection Collections of NeurIPS 2025 Spotlight paper: "SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation" • 5 items • Updated Sep 24 • 3
SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation Paper • 2502.13143 • Published Feb 18 • 31
Learning Getting-Up Policies for Real-World Humanoid Robots Paper • 2502.12152 • Published Feb 17 • 42