Haruto Sato

harusat2001's activity

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

upvoted a paper about 21 hours ago

When EOS Tokens Disagree: Understanding Length Inflation in On-Policy Distillation

Paper • 2609.20511 • Published 11 days ago • 110

upvoted 3 papers 3 days ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published 27 days ago • 433

GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation

Paper • 2609.24981 • Published 7 days ago • 70

RULER: Instance-aware Rubric Rewards for SVG Generation

Paper • 2609.25270 • Published 7 days ago • 101

upvoted a paper 4 days ago

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Paper • 2609.13814 • Published 16 days ago • 223

upvoted a paper 5 days ago

OmniVChat: Synthesizing, Benchmarking, and Training for Native Audio-Visual Dialogue

Paper • 2609.21465 • Published 10 days ago • 149

upvoted a paper 6 days ago

PACT: Can Enterprise AI Assistants Be Trusted Under Pressure?

Paper • 2609.18605 • Published 12 days ago • 41

upvoted a paper 7 days ago

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

Paper • 2609.17708 • Published 13 days ago • 76

upvoted a paper 8 days ago

StepAudio 3 Realtime Technical Report

Paper • 2609.14005 • Published 16 days ago • 129

upvoted 2 papers 9 days ago

ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMs

Paper • 2609.15635 • Published 14 days ago • 8

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published 13 days ago • 146

upvoted a paper 10 days ago

ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement

Paper • 2609.14857 • Published 14 days ago • 214

upvoted a paper 11 days ago

RSIAgent: Autonomous Exploration for Recursive Self-improvement in New Environments

Paper • 2609.15364 • Published 14 days ago • 84

upvoted a paper 12 days ago

How Far Can Synthetic Data Take Thai OCR?

Paper • 2609.03595 • Published 25 days ago • 3

upvoted a paper 13 days ago

DRG-MAPPO: Hierarchical Dynamic Role-Graph Multi-Agent Reinforcement Learning for Cooperative Air Combat

Paper • 2609.11155 • Published 18 days ago • 28

upvoted a paper 14 days ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published 19 days ago • 161