Robust LLM Training Infrastructure at ByteDance Paper • 2509.16293 • Published Oct 20, 2025 • 1
A Reconstruction-Based Framework for Caption Evaluation Beyond Reference Captions Paper • 2607.23235 • Published Jul 25 • 2
AnchorSplat: Feed-Forward 3D Gaussian Splatting with 3D Geometric Priors Paper • 2604.07053 • Published Apr 9 • 2
RealCAD: Towards Real-World Image-to-CAD Reconstruction under Domain Shift and Parameter Bias Paper • 2608.30617 • Published 25 days ago • 2
Breaking the Horizontal Prior: From Long-Tailed Orientation Bias to Roll-Robust Monocular Depth Estimation Paper • 2608.00678 • Published Aug 1 • 2
AffordAny: Open-World 3D Affordance Grounding from Monocular RGB Images via Vision-Language-Guided Geometric Reasoning Paper • 2608.20720 • Published Aug 21 • 2
Scaling Test-Time Robustness of Vision-Language Models via Self-Critical Inference Framework Paper • 2603.07659 • Published Mar 25 • 3