G^3VLA: Geometric Inductive Bias for Vision-Language-Action Models Paper • 2606.24472 • Published 6 days ago • 10
VisionWeave: Weaving Elastic Visual Representations as a Native Capability of MLLMs Paper • 2610.07987 • Published 14 days ago • 71
Incremental Open-Ended Deep Research with Structured Harness Paper • 2610.11566 • Published 12 days ago • 7
Adapting prior-data fitted networks for tabular anomaly detection Paper • 2610.06693 • Published 15 days ago • 6
ScholarCatalyst: A Benchmark for Retrieving Papers That Inspire New Research Paper • 2610.02202 • Published 19 days ago • 16
FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations Paper • 2609.20817 • Published Sep 17 • 39
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 369
Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMs Paper • 2609.03820 • Published Sep 3 • 16