DreamTraj: Generating 6-DoF Object Trajectories by Reading Unrendered Video Diffusion Latents Paper • 2608.00486 • Published 4 days ago • 12
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU Paper • 2607.19191 • Published 15 days ago • 309
TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs Paper • 2607.17423 • Published 17 days ago • 166
Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs Paper • 2505.11277 • Published May 16, 2025 • 64
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 20 days ago • 207
DataComp-VLM: Improved Open Datasets for Vision-Language Models Paper • 2606.28551 • Published Jun 26 • 53
Walking in the Implicit: Interactive World Exploration via Neural Scene Representation Paper • 2606.30045 • Published Jun 29 • 8
Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems Paper • 2606.18837 • Published Jun 17 • 58
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 253
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling Paper • 2606.18023 • Published Jun 16 • 210