Thomas Sanchez

thomas-sanchez's activity

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

upvoted a paper 11 days ago

PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?

Paper • 2609.18605 • Published 14 days ago • 41

upvoted a paper 18 days ago

MetroLLM-Bench: Evaluating Language Models as Transit Kiosk Runtimes

Paper • 2609.10016 • Published 21 days ago • 29

upvoted a paper 19 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 482

upvoted a paper 20 days ago

Omni Interaction Agent Technical Report

Paper • 2609.08977 • Published 22 days ago • 97

upvoted a paper 21 days ago

BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference

Paper • 2609.04971 • Published 26 days ago • 43

upvoted a paper 25 days ago

Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance

Paper • 2609.02373 • Published 28 days ago • 14

upvoted a paper 26 days ago

LLaDA-Image: Building Strong Image Generators with Fully Open Training Recipes

Paper • 2609.03796 • Published 27 days ago • 186

upvoted 6 papers about 1 month ago

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

Paper • 2608.08466 • Published Aug 9 • 14

SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation

Paper • 2608.17426 • Published Aug 18 • 161

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

Paper • 2608.17253 • Published Aug 19 • 100

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 Aug 14 • 286

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published Aug 14 • 126

Hybrid-Policy Self-Editing for Composable Unstructured Knowledge Editing

Paper • 2608.11660 • Published Aug 12 • 11

upvoted 7 papers about 2 months ago

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

Paper • 2608.05604 • Published Aug 6 • 81

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

Paper • 2608.00677 • Published Aug 1 • 266

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

Paper • 2608.08389 • Published Aug 9 • 11

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 181

RynnValue: Scaling Robotic Value Foundation Models with Temporal Distance

Paper • 2608.09853 • Published Aug 10 • 16

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

Paper • 2608.06020 • Published Aug 6 • 36

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

Paper • 2608.05747 • Published Aug 6 • 47