Thomas Sanchez

thomas-sanchez's activity

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

upvoted a paper about 8 hours ago

Hierarchical Self-Improvement: A Framework for Task-Specific Evolvable Agent Harnesses

Paper • 2608.08466 • Published 13 days ago • 8

upvoted 2 papers 2 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 4 days ago • 155

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

Paper • 2608.17253 • Published 3 days ago • 91

upvoted 2 papers 5 days ago

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published 8 days ago • 277

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 8 days ago • 167

upvoted a paper 6 days ago

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

Paper • 2608.11660 • Published 10 days ago • 11

upvoted 3 papers 9 days ago

SkillZip: Contract-Preserving Graph Compression for Scalable Agent Skill Libraries

Paper • 2608.05604 • Published 16 days ago • 77

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published 21 days ago • 261

Not Worth Another Token: Marginal Value Estimation for Efficient Deep Research Agents

Paper • 2608.08389 • Published 13 days ago • 12

upvoted 2 papers 10 days ago

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 13 days ago • 216

RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance

Paper • 2608.09853 • Published 12 days ago • 14

upvoted a paper 14 days ago

From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models

Paper • 2608.06020 • Published 16 days ago • 35

upvoted a paper 15 days ago

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

Paper • 2608.05747 • Published 16 days ago • 46

upvoted a paper 17 days ago

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 18 days ago • 23

upvoted a paper 18 days ago

SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks

Paper • 2608.02023 • Published 19 days ago • 156

upvoted a paper 22 days ago

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

Paper • 2607.28227 • Published 23 days ago • 307