SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering? Paper • 2603.15401 • Published 8 days ago • 18
GradMem: Learning to Write Context into Memory with Test-Time Gradient Descent Paper • 2603.13875 • Published 10 days ago • 33
V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning Paper • 2603.14482 • Published 9 days ago • 21
Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights Paper • 2603.12228 • Published 12 days ago • 12
view article Article How to Use Multiple GPUs in Hugging Face Transformers: Device Map vs Tensor Parallelism Feb 12 • 18
Nested Learning: The Illusion of Deep Learning Architectures Paper • 2512.24695 • Published Dec 31, 2025 • 45
Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation Paper • 2512.10949 • Published Dec 11, 2025 • 47
Depth Anything 3: Recovering the Visual Space from Any Views Paper • 2511.10647 • Published Nov 13, 2025 • 101
view article Article Thinking Outside the Attention Box: Introducing Gated Associative Memory (GAM) Sep 3, 2025 • 5
ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning Paper • 2508.10419 • Published Aug 14, 2025 • 75
view article Article <p style="text-align:center;"> Bridging the Gap: Making Robotics Feel Like Machine Learning </p> Aug 12, 2025 • 12