Mateo Smith

msmith25's activity

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

upvoted 2 papers 1 day ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 3 days ago • 72

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 6 days ago • 173

upvoted 2 papers 2 days ago

Occamy-1.0: Open Pareto-frontier 35B Intelligence for Co-work

Paper • 2609.11977 • Published 16 days ago • 111

Generalized Agent Iteration: One Formal Framework for Iterative Policy Improvement and Recursive Self-Improvement

Paper • 2609.13406 • Published 9 days ago • 36

upvoted a paper 3 days ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 5 days ago • 124

upvoted 2 papers 4 days ago

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper • 2609.13356 • Published 9 days ago • 250

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 6 days ago • 229

upvoted a paper 5 days ago

DataFlex-RL: An Evaluation Platform for RLVR Data Policies

Paper • 2609.06107 • Published 15 days ago • 81

upvoted a paper 6 days ago

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

Paper • 2609.07470 • Published 13 days ago • 23

upvoted a paper 10 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 12 days ago • 171

upvoted a paper 11 days ago

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published 20 days ago • 62

upvoted a paper 14 days ago

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

Paper • 2609.03199 • Published 18 days ago • 31

upvoted 2 papers 16 days ago

Aspire: Can Models Self-Evolve from Vague Goals?

Paper • 2608.31111 • Published 20 days ago • 82

HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?

Paper • 2609.01437 • Published 19 days ago • 117

upvoted 2 papers 17 days ago

Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving

Paper • 2609.00111 • Published 20 days ago • 311

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 19 days ago • 333

upvoted a paper 18 days ago

Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling

Paper • 2608.30821 • Published 20 days ago • 66

upvoted 2 papers 22 days ago

Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World Models

Paper • 2608.25518 • Published 25 days ago • 59

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 25 days ago • 69

upvoted a paper 23 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 25 days ago • 88