U-ARM : Ultra low-cost general teleoperation interface for robot manipulation Paper • 2509.02437 • Published Sep 2 • 5
Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising Paper • 2511.08633 • Published 28 days ago • 53
Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds Paper • 2511.08892 • Published 26 days ago • 194
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation Paper • 2511.02778 • Published Nov 4 • 102 • 3
VCode: a Multimodal Coding Benchmark with SVG as Symbolic Visual Representation Paper • 2511.02778 • Published Nov 4 • 102
Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B Paper • 2511.06221 • Published 29 days ago • 128
The Station: An Open-World Environment for AI-Driven Discovery Paper • 2511.06309 • Published 29 days ago • 35
Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models Paper • 2511.01618 • Published Nov 3 • 9
QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs Paper • 2510.11696 • Published Oct 13 • 176
Artificial Hippocampus Networks for Efficient Long-Context Modeling Paper • 2510.07318 • Published Oct 8 • 30
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention Paper • 2510.04212 • Published Oct 5 • 23
VLA-R1: Enhancing Reasoning in Vision-Language-Action Models Paper • 2510.01623 • Published Oct 2 • 10
The Dragon Hatchling: The Missing Link between the Transformer and Models of the Brain Paper • 2509.26507 • Published Sep 30 • 535