Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments Paper • 2605.30280 • Published 22 days ago • 145
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published 23 days ago • 426
FastContext: Training Efficient Repository Explorer for Coding Agents Paper • 2606.14066 • Published 7 days ago • 83
ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research Paper • 2606.07591 • Published 22 days ago • 91
OCC-RAG: Optimal Cognitive Core for Faithful Question Answering Paper • 2606.00683 • Published 20 days ago • 93
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models Paper • 2606.16140 • Published 4 days ago • 97
Your UnEmbedding Matrix is Secretly a Feature Lens for Text Embeddings Paper • 2606.07502 • Published 14 days ago • 95
DreamX-World 1.0: A General-Purpose Interactive World Model Paper • 2606.16993 • Published 4 days ago • 101
OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data Paper • 2606.13432 • Published 8 days ago • 101
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Paper • 2606.13673 • Published 8 days ago • 100
GrepSeek: Training Search Agents for Direct Corpus Interaction Paper • 2605.29307 • Published 22 days ago • 111
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Paper • 2606.09426 • Published 11 days ago • 101
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement Paper • 2606.11926 • Published 9 days ago • 112
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation Paper • 2605.31264 • Published 21 days ago • 114
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published 16 days ago • 122