Open Vision Banana: A Fully Open Recipe for Generative Visual Perception Paper • 2611.15844 • Published 4 days ago • 36
On the Design of Hyper-Connections: Simplification, Stability, and Scalability Paper • 2611.05984 • Published 11 days ago • 29
thinkingmachines/Inkling-2-Small Image-Text-to-Text • 594B • Updated about 5 hours ago • 7.33k • • 327
SWAM: Scaling World Action Models with Cross-Modal Alignment Paper • 2611.12870 • Published 6 days ago • 24
Training Vision Transformers to Focus: Emergence of Spatial Attention Head Specialization Paper • 2611.11890 • Published 6 days ago • 5
WorldFoundry: Towards Unified Infrastructure for World Intelligence Paper • 2611.10771 • Published 8 days ago • 59
AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 21 days ago • 23 • 4
AgentBaton: Efficient Model Collaboration in Agentic Tasks Paper • 2610.35959 • Published 21 days ago • 23
PCBRouteAgent: How Close Are LLM Agents to Becoming PCB Routing Engineers? Paper • 2611.08175 • Published 10 days ago • 43
SLA: Scaling Spatial-Language-Action Model via Continual Pre-training Paper • 2611.08373 • Published 10 days ago • 91
Human-to-Robot Transfer via Bridging Representation and Action Space in VLAs Paper • 2611.04391 • Published 12 days ago • 16
SwarmEvolve: Latent Agent Swarms for Evolutionary Discovery and Optimization Paper • 2611.08483 • Published 10 days ago • 14
Harness-S: Learning from Sibling Harnesses for Generalizable Agent Training Paper • 2611.04277 • Published 12 days ago • 71