Mateo Smith

msmith25's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper about 17 hours ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 5 days ago • 122

upvoted a paper about 19 hours ago

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published 1 day ago • 172

upvoted a paper 1 day ago

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published 3 days ago • 189

upvoted 2 papers 3 days ago

Cura 1T: Specialized Model for Agentic Healthcare

Paper • 2607.15314 • Published 8 days ago • 48

Loop the Loopies!

Paper • 2607.16051 • Published 6 days ago • 69

upvoted a paper 5 days ago

LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget

Paper • 2607.14952 • Published 7 days ago • 195

upvoted 3 papers 7 days ago

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Paper • 2607.12993 • Published 9 days ago • 131

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published 9 days ago • 215

Read It Back: Pretrained MLLMs Are Zero-Shot Reward Models for Text-to-Image Generation

Paper • 2607.11886 • Published 10 days ago • 84

upvoted a paper 15 days ago

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published 16 days ago • 95

upvoted a paper 16 days ago

PixWorld: Unifying 3D Scene Generation and Reconstruction in Pixel Space

Paper • 2607.05373 • Published 17 days ago • 65

upvoted a paper 28 days ago

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

Paper • 2606.17162 • Published Jun 15 • 177

upvoted a paper 30 days ago

OpenRath: Session-Centered Runtime State for Agent Systems

Paper • 2606.19409 • Published Jun 17 • 78

upvoted 7 papers about 1 month ago

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 483

LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling

Paper • 2606.18023 • Published Jun 16 • 210

DragMesh-2: Physically Plausible Dexterous Hand-Object Interaction with Articulated Objects

Paper • 2606.15133 • Published Jun 13 • 74

Learning from the Self-future: On-policy Self-distillation for dLLMs

Paper • 2606.18195 • Published Jun 16 • 77

Toward Generalist Autonomous Research via Hypothesis-Tree Refinement

Paper • 2606.11926 • Published Jun 10 • 128

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 487

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published Jun 4 • 70