Wang's picture

2

Wang

VictorZheng

·

ZKBig

AI & ML interests

None yet

Recent Activity

upvoted a paper 2 days ago

Hidden States as Early Signals: Step-level Trace Evaluation and Pruning for Efficient Test-Time Scaling

upvoted a paper 4 months ago

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

authored a paper 4 months ago

Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning

View all activity

Organizations

Papers 1

arxiv:2510.04072

models 4

VictorZheng/DeepSeek-R1-Distill-Qwen-1.5B-GRPO

2B • Updated Jul 28, 2025

VictorZheng/Qwen2.5-1.5B-Open-R1-GRPO

Updated Jul 28, 2025

VictorZheng/Qwen2.5-1.5B-Instruct-GRPO

Updated Jul 28, 2025

VictorZheng/qwen-2.5-3b-r1-countdown

Updated Jul 18, 2025

datasets 5

VictorZheng/Qwen2.5-0.5B-Instruct-best_of_n-completions

Viewer • Updated Feb 26, 2025 • 2

VictorZheng/Llama-3.2-1B-Instruct-best_of_n-completions

Viewer • Updated Feb 26, 2025 • 1 • 2

VictorZheng/Qwen2.5-1.5B-Instruct-best_of_n-completions

Updated Feb 26, 2025

VictorZheng/Qwen2.5-3B-Instruct-best_of_n-completions

Updated Feb 26, 2025 • 2

VictorZheng/Llama-3.2-3B-Instruct-best_of_n-completions

Updated Feb 26, 2025