JEPA-Anything: Learning Predictive Models across Different Worlds Paper • 2609.20800 • Published 20 days ago • 77
The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100 Paper • 2609.03231 • Published Sep 3 • 5
ENEAS: Embedding-guided Neural Ensemble for Adaptive Segmentation Paper • 2609.03756 • Published Sep 3 • 25
RenderFormer-V2: Neural Rendering with Heterogeneous Scene Primitives Paper • 2609.05738 • Published Sep 4 • 6
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation Paper • 2609.08084 • Published 29 days ago • 72
Uncertainty-Aware World Model for Aerial Image-Goal Navigation Paper • 2608.05597 • Published Aug 6 • 12
AdvFD: Boosting Visual Generation via Adversarial Fr'echet Distance Loss Paper • 2608.11205 • Published Aug 11 • 27
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models Paper • 2608.10708 • Published Aug 11 • 16
Strips as Tokens: Artist Mesh Generation with Native UV Segmentation Paper • 2604.09132 • Published Apr 10 • 56
Attention Sink in Transformers: A Survey on Utilization, Interpretation, and Mitigation Paper • 2604.10098 • Published Apr 11 • 84
Habitat-GS: A High-Fidelity Navigation Simulator with Dynamic Gaussian Splatting Paper • 2604.12626 • Published Apr 14 • 16
Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective Paper • 2604.14025 • Published Apr 15 • 15
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself Paper • 2604.14048 • Published Apr 15 • 18