Thomas Sanchez

thomassanchez's activity

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

upvoted a paper 7 days ago

EXIMO: VLM Guided Exploration of VLA Policies

Paper • 2608.19891 • Published 9 days ago • 16

upvoted 2 papers 8 days ago

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published 11 days ago • 157

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

Paper • 2608.17253 • Published 10 days ago • 94

upvoted 2 papers 11 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 15 days ago • 280

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 15 days ago • 170

upvoted a paper 12 days ago

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published 29 days ago • 113

upvoted a paper 13 days ago

Are You Sure You're Sure? On the Impact of Instruction Tuning on Confidence and Lexical Diversity

Paper • 2608.13430 • Published 16 days ago • 13

upvoted 2 papers 15 days ago

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

Paper • 2608.05604 • Published 23 days ago • 80

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

Paper • 2608.00677 • Published 28 days ago • 262

upvoted 2 papers 16 days ago

JigShape: Evaluating Visual-Geometric Reasoning in VLMs through Jigsaw Puzzles

Paper • 2607.27670 • Published 25 days ago • 8

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 20 days ago • 218

upvoted a paper 22 days ago

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published 23 days ago • 35

upvoted 2 papers 24 days ago

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 26 days ago • 60

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

Paper • 2608.02023 • Published 26 days ago • 157

upvoted a paper 28 days ago

Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Paper • 2607.28568 • Published 30 days ago • 185