WildCity: A Real-World City-Scale Testbed for Rendering, Simulation, and Spatial Intelligence Paper • 2607.06838 • Published 3 days ago • 4
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 2 days ago • 39
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 7 days ago • 52
PointDiT: Pixel-Space Diffusion for Monocular Geometry Estimation Paper • 2607.02515 • Published 8 days ago • 9
Nemotron-Labs-Diffusion: A Tri-Mode Language Model Unifying Autoregressive, Diffusion, and Self-Speculation Decoding Paper • 2607.05722 • Published 3 days ago • 7
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation Paper • 2607.05147 • Published 4 days ago • 23
SkillHone: A Harness for Continual Agent Skill Evolution Through Persistent Decision History Paper • 2606.08671 • Published 17 days ago • 43
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning Paper • 2606.29526 • Published 12 days ago • 160
InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization Paper • 2607.04988 • Published 4 days ago • 22
ResearchStudio-Idea: An Evidence-Grounded Research-Ideation Skill Suite from ML Conference Outcomes Paper • 2607.04439 • Published 5 days ago • 48
view article Article LeRobot v0.6.0: Imagine, Evaluate, Improve +7 imstevenpmwork, pepijn223, CarolinePascal, lilkm, maximellerbach, nepyope, nikodembartnik, Nico-robot, thomwolf • 3 days ago • 49
ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog Paper • 2607.04438 • Published 5 days ago • 56
YOLOE-26: Integrating YOLO26 with YOLOE for Real-Time Open-Vocabulary Instance Segmentation Paper • 2602.00168 • Published Jan 29 • 2
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model Paper • 2607.00678 • Published 9 days ago • 19