Shenzhi Wang

shenzhi-wang's activity

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

authored 2 papers 7 days ago

OS Agents: A Survey on MLLM-based Agents for General Computing Devices Use

Paper • 2508.04482 • Published Aug 6, 2025 • 9

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published 9 days ago • 68

upvoted a paper 8 days ago

The Flexibility Trap: Why Arbitrary Order Limits Reasoning Potential in Diffusion Language Models

Paper • 2601.15165 • Published 9 days ago • 68

upvoted a paper 2 months ago

Soft Adaptive Policy Optimization

Paper • 2511.20347 • Published Nov 25, 2025 • 40

upvoted 2 papers 4 months ago

IMG: Calibrating Diffusion Models via Implicit Multimodal Guidance

Paper • 2509.26231 • Published Sep 30, 2025 • 18

Variational Reasoning for Language Models

Paper • 2509.22637 • Published Sep 26, 2025 • 69

upvoted a paper 5 months ago

T2R-bench: A Benchmark for Generating Article-Level Reports from Real World Industrial Tables

Paper • 2508.19813 • Published Aug 27, 2025 • 28

upvoted a paper 6 months ago

Group Sequence Policy Optimization

Paper • 2507.18071 • Published Jul 24, 2025 • 316

upvoted a paper 7 months ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published Jun 9, 2025 • 263

authored a paper 8 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 188

upvoted a paper 8 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 188

commented a paper 8 months ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2, 2025 • 188 •

7

upvoted a paper 8 months ago

Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space

Paper • 2505.13308 • Published May 19, 2025 • 27

upvoted 2 papers 9 months ago

WorldPM: Scaling Human Preference Modeling

Paper • 2505.10527 • Published May 15, 2025 • 34

Qwen3 Technical Report

Paper • 2505.09388 • Published May 14, 2025 • 324

authored a paper 9 months ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published May 6, 2025 • 189

upvoted 2 papers 9 months ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published May 6, 2025 • 189

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Paper • 2504.13837 • Published Apr 18, 2025 • 139

authored 2 papers 10 months ago

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

Paper • 2504.05535 • Published Apr 7, 2025 • 44

COIG-P: A High-Quality and Large-Scale Chinese Preference Dataset for Alignment with Human Values

Paper • 2504.05535 • Published Apr 7, 2025 • 44