Zhihao Zhang
- Papers
- 10
Cite
Notes
Only stored in your browser.
Authored papers
10Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models
arXiv 2026
Reasoning or Memorization? Unreliable Results of Reinforcement Learning Due to Data Contamination
arXiv 2025
PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts
arXiv 2025
BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
arXiv 2025
Less Is More: Training-Free Sparse Attention with Global Locality for Efficient Reasoning
arXiv 2025
SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
arXiv 2025
TidalDecode: Fast and Accurate LLM Decoding with Position Persistent Sparse Attention
arXiv 2024
RU-AI: A Large Multimodal Dataset for Machine-Generated Content Detection
arXiv 2024
Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature
arXiv 2022
GradSign: Model Performance Inference with Theoretical Insights
gradsign-model-performance-inference-with
Affiliations
Frequent co-authors
10from 10 papers