ZhangXiaoyun's picture

ZhangXiaoyun

DadaCloud01

·

AI & ML interests

None yet

Recent Activity

authored a paper 7 days ago

Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

authored a paper 7 days ago

Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters

authored a paper 7 days ago

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy

View all activity

Organizations

upvoted 2 papers 8 days ago

Rediscovering Entropy Regularization: Adaptive Coefficient Unlocks Its Potential for LLM Reinforcement Learning

Paper • 2510.10959 • Published Oct 13, 2025 • 2

Reasoner for Real-World Event Detection: Scaling Reinforcement Learning via Adaptive Perplexity-Aware Sampling Strategy

Paper • 2507.01327 • Published Jul 2, 2025 • 1

upvoted a paper 9 days ago

TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

Paper • 2603.16448 • Published 9 days ago • 56

upvoted a paper 17 days ago

Lost in Stories: Consistency Bugs in Long Story Generation by LLMs

Paper • 2603.05890 • Published 21 days ago • 91

upvoted a paper 3 months ago

Step-DeepResearch Technical Report

Paper • 2512.20491 • Published Dec 23, 2025 • 87

upvoted 2 papers 10 months ago

Adversarial Contrastive Decoding: Boosting Safety Alignment of Large Language Models via Opposite Prompt Optimization

Paper • 2406.16743 • Published Jun 24, 2024 • 1

When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning

Paper • 2505.15400 • Published May 21, 2025 • 23