Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction Paper • 2605.26230 • Published 3 days ago • 32
SpatialBench: Is Your Spatial Foundation Model an All-Round Player? Paper • 2605.27367 • Published 1 day ago • 48
MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research Paper • 2605.26114 • Published 3 days ago • 44
LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding Paper • 2605.27365 • Published 1 day ago • 65
CoSPlay: Cooperative Self-Play at Test-Time with Self-Generated Code and Unit Test Paper • 2605.23491 • Published 6 days ago • 6
HorizonStream: Long-Horizon Attention for Streaming 3D Reconstruction Paper • 2605.23889 • Published 6 days ago • 2
InstructSAM: Segment Any Instance with Any Instructions Paper • 2605.26102 • Published 3 days ago • 10
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World Paper • 2605.26086 • Published 3 days ago • 20
ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention Paper • 2605.23081 • Published 7 days ago • 29
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction Paper • 2605.26115 • Published 3 days ago • 39
GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction Paper • 2605.23888 • Published 6 days ago • 9
From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills Paper • 2605.23899 • Published 6 days ago • 27
SkillOpt: Executive Strategy for Self-Evolving Agent Skills Paper • 2605.23904 • Published 6 days ago • 177
OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding Paper • 2605.18577 • Published 10 days ago • 4
SAM 3D Animal: Promptable Animal 3D Reconstruction from Images in the Wild Paper • 2605.07604 • Published 20 days ago • 2