T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images Paper • 2610.03308 • Published 14 days ago • 16
SpatialASM: Internalizing Active Mentalization for Spatial Reasoning Paper • 2610.13832 • Published 7 days ago • 29
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published 16 days ago • 317
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published 16 days ago • 97
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs Paper • 2610.07987 • Published 10 days ago • 70
Less from More: Reinforcing Sparse Video Reasoning from Dense References Paper • 2610.10893 • Published 9 days ago • 10
SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments Paper • 2610.12611 • Published 8 days ago • 108
Humanity's Sixth Sense: Benchmarking Intuitive Visual Reasoning in Multimodal Models Paper • 2610.08966 • Published 8 days ago • 26
REMORY: Learning Residual Memory for Context Compaction Paper • 2610.11287 • Published 8 days ago • 60
DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training Paper • 2610.12468 • Published 8 days ago • 46
SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces Paper • 2610.11366 • Published 8 days ago • 17