Zhiyuan He
- Papers
- 7
Cite
Notes
Only stored in your browser.
7papers
Authored papers
7World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
arXiv 2026
From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company
arXiv 2026
Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction
arXiv 2026
Agent Lightning: Train ANY AI Agents with Reinforcement Learning
arXiv 2025
Do Not Let Low-Probability Tokens Over-Dominate in RL for LLMs
arXiv 2025
$ΔL$ Normalization: Rethink Loss Aggregation in RLVR
arXiv 2025
Designing Network Algorithms via Large Language Models
arXiv 2024
Affiliations
No known affiliations.
Frequent co-authors
10from 7 papers