haoran he's picture

haoran he

haoranhe

·

tinnerhrhe

AI & ML interests

None yet

Recent Activity

upvoted a paper 11 days ago

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward

upvoted a paper about 1 month ago

OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language World Models

upvoted a paper 2 months ago

UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation

View all activity

Organizations

None yet

New activity in haoranhe/ROVER-Qwen3-8B 8 months ago

Improve model card: Add metadata, paper, and GitHub links

#1 opened 8 months ago by

New activity in haoranhe/ROVER-Qwen3-4B 8 months ago

Improve model card: Add metadata, paper, project page, and GitHub links

#1 opened 8 months ago by

New activity in haoranhe/ROVER-countdown-3B 8 months ago

Improve model card: Add pipeline tag, library name, paper, and GitHub links

#1 opened 8 months ago by

commented a paper 8 months ago

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards

Paper • 2509.24981 • Published Sep 29, 2025 • 29 •