Thomas Perez

thomas-perez's activity

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

upvoted a paper 14 days ago

Confidence Comes from Experience: Experiential Confidence Estimation from Reasoning to Agents

Paper • 2609.17708 • Published 16 days ago • 77

upvoted a paper 15 days ago

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 24 days ago • 376

upvoted a paper 20 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 484

upvoted a paper 21 days ago

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 23 days ago • 327

upvoted a paper 26 days ago

Let Confidence Change, Not the Prediction: Prediction-Preserving Repair for Post-hoc Calibration

Paper • 2609.01072 • Published 29 days ago • 13

upvoted a paper 27 days ago

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

Paper • 2609.03796 • Published 28 days ago • 186

upvoted 5 papers about 1 month ago

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

Training Chemical Plausibility-Aware Large Language Models for Single-Step Retrosynthesis

Paper • 2608.18940 • Published Aug 19 • 35

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

upvoted 6 papers about 2 months ago

Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

Paper • 2607.29211 • Published Jul 31 • 14

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

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published Aug 9 • 181

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published Aug 10 • 122

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

Paper • 2608.02023 • Published Aug 3 • 161

upvoted a paper 2 months ago

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

Paper • 2607.28227 • Published Jul 30 • 158