MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation Paper • 2602.11337 • Published 1 day ago • 2
ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation Paper • 2602.11598 • Published about 23 hours ago
Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments Paper • 2602.11964 • Published about 15 hours ago
MiniCPM-SALA: Hybridizing Sparse and Linear Attention for Efficient Long-Context Modeling Paper • 2602.11761 • Published about 19 hours ago
Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation Paper • 2602.10699 • Published 2 days ago • 1
CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion Paper • 2602.10999 • Published 1 day ago • 10
When to Memorize and When to Stop: Gated Recurrent Memory for Long-Context Reasoning Paper • 2602.10560 • Published 2 days ago • 24
Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters Paper • 2602.10604 • Published 2 days ago • 158
Olaf-World: Orienting Latent Actions for Video World Modeling Paper • 2602.10104 • Published 2 days ago • 25
VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model Paper • 2602.10098 • Published 2 days ago • 15
Code2World: A GUI World Model via Renderable Code Generation Paper • 2602.09856 • Published 3 days ago • 183
SAGE: Scalable Agentic 3D Scene Generation for Embodied AI Paper • 2602.10116 • Published 2 days ago • 7
How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs Paper • 2602.08808 • Published 4 days ago • 8
Rolling Sink: Bridging Limited-Horizon Training and Open-Ended Testing in Autoregressive Video Diffusion Paper • 2602.07775 • Published 5 days ago • 7
InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery Paper • 2602.08990 • Published 3 days ago • 63
Aster: Autonomous Scientific Discovery over 20x Faster Than Existing Methods Paper • 2602.07040 • Published 9 days ago • 2
SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees Paper • 2602.06554 • Published 7 days ago • 4