Mateo Smith

msmith25's activity

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

upvoted 2 papers 3 days ago

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

Paper • 2608.25518 • Published 5 days ago • 182

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

Paper • 2608.25593 • Published 5 days ago • 111

upvoted a paper 4 days ago

VGI-Bench: Probing Visual Intelligence in Video Generation Models

Paper • 2608.19583 • Published 5 days ago • 174

upvoted a paper 5 days ago

WarpSAC: Towards the Pinnacle of Scalable Off-policy RL by Rethinking Exploration and Exploitation

Paper • 2608.24479 • Published 6 days ago • 138

upvoted a paper 10 days ago

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published 11 days ago • 273

upvoted a paper 12 days ago

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

Paper • 2608.14036 • Published 17 days ago • 169

upvoted 2 papers 13 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 14 days ago • 339

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

Paper • 2608.16072 • Published 14 days ago • 150

upvoted a paper 18 days ago

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

Paper • 2608.11924 • Published 19 days ago • 289

upvoted 2 papers 19 days ago

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published 20 days ago • 187

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 22 days ago • 218

upvoted a paper 20 days ago

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

Paper • 2608.00155 • Published Jul 31 • 25

upvoted a paper 24 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 24 days ago • 250

upvoted a paper 26 days ago

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

Paper • 2608.01755 • Published 28 days ago • 142

upvoted a paper 28 days ago

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

Paper • 2607.28261 • Published Jul 30 • 116

upvoted 5 papers about 1 month ago

Metis: Memory Foundation Model

Paper • 2607.26760 • Published Jul 29 • 272

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

Paper • 2607.28227 • Published Jul 30 • 309

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

Paper • 2607.26811 • Published Jul 29 • 93

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

Paper • 2607.25659 • Published Jul 28 • 84

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

Paper • 2607.27205 • Published Jul 29 • 140