Difan Zou

Venues

Frequent coauthors

Papers

1. Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion
   COLT 2026 ·

   Xunpeng Huang

   DBLP profile ↗ORCID search ↗
2. Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction
   ACL 2026 ·

   Xingwu Chen

   DBLP profile ↗ORCID search ↗
3. Learning Diffusion Policy from Primitive Skills for Robot Manipulation
   AAAI 2026 ·

   Zhihao Gu

   DBLP profile ↗ORCID search ↗
4. SIDE: Surrogate Conditional Data Extraction from Diffusion Models
   AAAI 2026 ·

   Yunhao Chen

   DBLP profile ↗ORCID search ↗
5. Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability
   ICLR 2025 ·

   Yujin Han

   DBLP profile ↗ORCID search ↗
6. Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
   ICML 2025 ·

   Yujin Han

   DBLP profile ↗ORCID search ↗
7. F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
   NeurIPS 2025 ·

   Hangwei Zhang

   DBLP profile ↗ORCID search ↗
8. Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
   NeurIPS 2025 ·

   Hanru Bai

   DBLP profile ↗ORCID search ↗
9. How Does Critical Batch Size Scale in Pre-training?
   ICLR 2025 ·

   Hanlin Zhang

   DBLP profile ↗ORCID search ↗
10. How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
    NeurIPS 2025 ·

    Wei Huang

    DBLP profile ↗ORCID search ↗
11. HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
    ICLR 2025 ·

    Hanxiang Ren

    DBLP profile ↗ORCID search ↗
12. Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning
    NeurIPS 2025 ·

    Dechen Zhang

    DBLP profile ↗ORCID search ↗
13. Masked Autoencoders Are Effective Tokenizers for Diffusion Models
    ICML 2025 ·

    Hao Chen

    DBLP profile ↗ORCID search ↗
14. Model Unlearning via Sparse Autoencoder Subspace Guided Projections
    EMNLP 2025 ·

    Xu Wang

    DBLP profile ↗ORCID search ↗
15. On the Feature Learning in Diffusion Models
    ICLR 2025 ·

    Andi Han

    DBLP profile ↗ORCID search ↗
16. On the Robustness of Transformers against Context Hijacking for Linear Classification
    NeurIPS 2025 ·

    Tianle Li

    DBLP profile ↗ORCID search ↗
17. Parallelized Autoregressive Visual Generation
    CVPR 2025 ·

    Yuqing Wang

    DBLP profile ↗ORCID search ↗
18. SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
    ACL 2025 ·

    Chengxing Xie

    DBLP profile ↗ORCID search ↗
19. Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
    NeurIPS 2025 ·

    Yao Teng

    DBLP profile ↗ORCID search ↗
20. Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
    ICML 2025 ·

    Xu Wang

    DBLP profile ↗ORCID search ↗
21. Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
    NeurIPS 2025 ·

    Xuan Tang

    DBLP profile ↗ORCID search ↗
22. An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
    NeurIPS 2024 ·

    Yunzhe Hu

    DBLP profile ↗ORCID search ↗
23. Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
    ICLR 2024 ·

    Miao Lu

    DBLP profile ↗ORCID search ↗
24. Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data
    ICML 2024 ·

    Xuran Meng

    DBLP profile ↗ORCID search ↗
25. Faster Sampling via Stochastic Gradient Proximal Sampler
    ICML 2024 ·

    Xunpeng Huang

    DBLP profile ↗ORCID search ↗
26. Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
    COLT 2024 ·

    Xunpeng Huang

    DBLP profile ↗ORCID search ↗
27. How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
    ICLR 2024 ·

    Jingfeng Wu

    DBLP profile ↗ORCID search ↗
28. How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
    NeurIPS 2024 ·

    Xingwu Chen

    DBLP profile ↗ORCID search ↗
29. Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference
    ICML 2024 ·

    Yujin Han

    DBLP profile ↗ORCID search ↗
30. PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
    ICLR 2024 ·

    Junwei Su

    DBLP profile ↗ORCID search ↗
31. Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
    NeurIPS 2024 ·

    Xunpeng Huang

    DBLP profile ↗ORCID search ↗
32. Slight Corruption in Pre-training Data Makes Better Diffusion Models
    NeurIPS 2024 ·

    Hao Chen

    DBLP profile ↗ORCID search ↗
33. The Implicit Bias of Adam on Separable Data
    NeurIPS 2024 ·

    Chenyang Zhang

    DBLP profile ↗ORCID search ↗
34. What Can Transformer Learn with Varying Depth? Case Studies on Sequence Learning Tasks
    ICML 2024 ·

    Xingwu Chen

    DBLP profile ↗ORCID search ↗