Mateo Smith

msmith25's activity

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

upvoted a paper 5 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 6 days ago • 262

upvoted a paper 7 days ago

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 12 days ago • 164

upvoted 2 papers 8 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 9 days ago • 123

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published 9 days ago • 148

upvoted a paper 13 days ago

Spark-to-Paper: End-to-End Research Paper Generation as a Composable Skill

Paper • 2608.11924 • Published 14 days ago • 288

upvoted 2 papers 14 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 15 days ago • 184

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 17 days ago • 217

upvoted a paper 15 days ago

AgentStream: How Well Do Self-Evolving LLM Agents Perform Under Streaming Tasks?

Paper • 2608.00155 • Published 26 days ago • 25

upvoted a paper 19 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 19 days ago • 248

upvoted a paper 21 days ago

Deferred Exposure of Future Trajectories for Verifiable Reasoning in Autonomous Driving VLMs

Paper • 2608.01755 • Published 23 days ago • 142

upvoted a paper 23 days ago

TARS: Timestep-Aware Data Scaling for 3D-Free Video Re-Shooting

Paper • 2607.28261 • Published 27 days ago • 116

upvoted 3 papers 26 days ago

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 28 days ago • 272

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

Paper • 2607.28227 • Published 27 days ago • 309

DistillAlign: Coordinating Mode Covering and Mode Seeking in Autoregressive Video Distillation

Paper • 2607.26811 • Published 28 days ago • 93

upvoted 2 papers 27 days ago

CoRT: Counterfactual Replay for Token-Level Rubric-Guided Policy Optimization

Paper • 2607.25659 • Published 29 days ago • 84

TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM

Paper • 2607.27205 • Published 28 days ago • 140

upvoted 2 papers 28 days ago

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published 29 days ago • 158

Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

Paper • 2607.21655 • Published Jul 22 • 193

upvoted 2 papers about 1 month ago

Two-Level Meta-Rubrics for Evaluating Open-Ended Generation: GAMUT, a Benchmark for Factual Completeness

Paper • 2607.19322 • Published Jul 21 • 11

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

Paper • 2607.16617 • Published Jul 18 • 143