SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe Paper • 2607.03451 • Published 8 days ago • 24
Multi-Turn Agentic Scientific Literature Search via Workflow Induction Paper • 2607.00597 • Published 10 days ago • 25
PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising Paper • 2606.30968 • Published 12 days ago • 27
Why Can't I Open My Drawer? Mitigating Object-Driven Shortcuts in Zero-Shot Compositional Action Recognition Paper • 2601.16211 • Published 9 days ago • 42
Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligence Paper • 2607.07675 • Published 3 days ago • 42
Video-Oasis: Rethinking Evaluation of Video Understanding Paper • 2603.29616 • Published 9 days ago • 43
Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation Paper • 2607.07608 • Published 3 days ago • 50
RynnWorld-Teleop: An Action-Conditioned World Model for Digital Teleoperation Paper • 2607.06558 • Published 4 days ago • 74
Accurate, Interdisciplinary and Transparent Structure-property Understanding with Deep Native Structural Reasoning Paper • 2607.07708 • Published 3 days ago • 77
RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation Paper • 2607.06559 • Published 4 days ago • 85
Vidu S1: A Real-Time Interactive Video Generation Model Paper • 2607.03118 • Published 8 days ago • 108
NVFP4 Collection Dynamic Unsloth NVFP4 Quants. Faster and more accurate. • 3 items • Updated about 7 hours ago • 15
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published 8 days ago • 57
Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs Paper • 2607.04371 • Published 6 days ago • 4
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning Paper • 2604.12374 • Published Apr 14 • 39