DeepSeekMath-V2: Towards Self-Verifiable Mathematical Reasoning Paper β’ 2511.22570 β’ Published 9 days ago β’ 62 β’ 2
Depth Anything 3: Recovering the Visual Space from Any Views Paper β’ 2511.10647 β’ Published 23 days ago β’ 92 β’ 5
Depth Anything 3: Recovering the Visual Space from Any Views Paper β’ 2511.10647 β’ Published 23 days ago β’ 92 β’ 5
RoboChallenge: Large-scale Real-robot Evaluation of Embodied Policies Paper β’ 2510.17950 β’ Published Oct 20 β’ 7 β’ 2
SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction Paper β’ 2510.07723 β’ Published Oct 9 β’ 4 β’ 1
Stabilizing MoE Reinforcement Learning by Aligning Training and Inference Routers Paper β’ 2510.11370 β’ Published Oct 13 β’ 3 β’ 1
SR-Scientist: Scientific Equation Discovery With Agentic AI Paper β’ 2510.11661 β’ Published Oct 13 β’ 3 β’ 2
LATTE: Latent Trajectory Embedding for Diffusion-Generated Image Detection Paper β’ 2507.03054 β’ Published Jul 3 β’ 1 β’ 1
FlagEval Findings Report: A Preliminary Evaluation of Large Reasoning Models on Automatically Verifiable Textual and Visual Questions Paper β’ 2509.17177 β’ Published Sep 21 β’ 13 β’ 2
RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation Paper β’ 2509.16198 β’ Published Sep 19 β’ 127 β’ 19
MedReseacher-R1: Expert-Level Medical Deep Researcher via A Knowledge-Informed Trajectory Synthesis Framework Paper β’ 2508.14880 β’ Published Aug 20 β’ 15 β’ 2
HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering Paper β’ 2509.09713 β’ Published Sep 8 β’ 24 β’ 7
Drawing2CAD: Sequence-to-Sequence Learning for CAD Generation from Vector Drawings Paper β’ 2508.18733 β’ Published Aug 26 β’ 9 β’ 3
False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize Paper β’ 2509.03888 β’ Published Sep 4 β’ 3 β’ 3
Towards a Unified View of Large Language Model Post-Training Paper β’ 2509.04419 β’ Published Sep 4 β’ 75 β’ 7