Itai Shapira

itai-sh's activity

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

upvoted a paper about 2 hours ago

Internalizing Agent Experience into Diffusion Model Weights via On-Policy Context Distillation

Paper • 2610.07250 • Published 8 days ago • 14

upvoted a paper 1 day ago

Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing

Paper • 2609.37334 • Published 14 days ago • 45

upvoted a paper 2 days ago

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

Paper • 2610.04933 • Published 9 days ago • 17

upvoted a paper 3 days ago

Harness Engineering for Software Engineering via Modular Executable Dev-Primitives

Paper • 2610.07832 • Published 7 days ago • 13

upvoted a paper 4 days ago

Memadapter: Counterfactual Adaptation Against Memory-induced Sycophancy

Paper • 2610.05162 • Published 9 days ago • 60

upvoted a paper 5 days ago

Octrees as an Explicit 3D Language

Paper • 2610.02388 • Published 12 days ago • 17

upvoted a paper 6 days ago

Video Generation Models: A Survey of Post-Training and Alignment

Paper • 2610.00812 • Published 13 days ago • 63

upvoted a paper 7 days ago

Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI

Paper • 2609.38143 • Published 14 days ago • 85

upvoted a paper 8 days ago

Omni-Decision: Evidence-Ledger Planning for Omni-Modal Agents

Paper • 2607.11433 • Published 19 days ago • 31

upvoted a paper 9 days ago

What Makes World Action Models Generalize? An Empirical Study of Test-Time Future Modeling

Paper • 2609.34981 • Published 14 days ago • 138

upvoted a paper 10 days ago

Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR

Paper • 2609.37868 • Published 14 days ago • 65

upvoted a paper 11 days ago

Self-Evolving Coding Agents: From Digital Programs to Physical-World Intelligence

Paper • 2609.35432 • Published 15 days ago • 109

upvoted a paper 14 days ago

SpeakerMem-R1: Speaker-Centered Dual-Track Memory for Multi-Party Dialogue

Paper • 2609.26780 • Published 21 days ago • 103

upvoted a paper 15 days ago

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

Paper • 2609.24981 • Published 22 days ago • 76