Difan Zou
~Difan_Zou1
32
论文总数
16.0
年均投稿
平均评分
接收情况22/32
会议分布
ICLR
16
NeurIPS
12
ICML
4
发表论文 (32 篇)
202518 篇
4
Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory
NeurIPS 2025Poster
4
Towards a Theoretical Understanding of Memorization in Diffusion Models
ICLR 2025withdrawn
4
Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks
NeurIPS 2025Poster
4
F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning
NeurIPS 2025Poster
6
On the Feature Learning in Diffusion Models
ICLR 2025Poster
4
Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability
ICLR 2025Poster
4
On the Robustness of Transformers against Context Hijacking for Linear Classification
NeurIPS 2025Poster
5
How Does Critical Batch Size Scale in Pre-training?
ICLR 2025Poster
3
On the Robustness of Transformers against Context Hijacking for Linear Classification
ICML 2025Rejected
4
Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning
NeurIPS 2025Poster
4
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
ICML 2025Poster
5
Label Noise Gradient Descent Improves Generalization in the Low SNR Regime
ICLR 2025Rejected
3
Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller
ICLR 2025Rejected
4
Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis
ICML 2025Poster
5
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
NeurIPS 2025Poster
4
HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
ICLR 2025Poster
4
Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation
NeurIPS 2025Poster
4
Masked Autoencoders Are Effective Tokenizers for Diffusion Models
ICML 2025Spotlight
202414 篇
4
The Implicit Bias of Adam on Separable Data
NeurIPS 2024Poster
4
Less is More: On the Feature Redundancy of Pretrained Models When Transferring to Few-shot Tasks
ICLR 2024Rejected
5
Recursive Score Estimation Accelerates Diffusion-Based Monte Carlo
ICLR 2024Rejected
4
An In-depth Investigation of Sparse Rate Reduction in Transformer-like Models
NeurIPS 2024Poster
5
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
NeurIPS 2024Spotlight
4
DISK: Domain Inference for Discovering Spurious Correlation with KL-Divergence
ICLR 2024Rejected
4
ON LEARNABILITY AND EXPERIENCE REPLAY METHODS FOR GRAPH INCREMENTAL LEARNING ON EVOLVING GRAPHS
ICLR 2024Rejected
5
Benign Overfitting in Two-Layer ReLU Convolutional Neural Networks for XOR Data
ICLR 2024Rejected
4
How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
ICLR 2024Spotlight
2
PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
ICLR 2024Poster
4
Private Overparameterized Linear Regression without Suffering in High Dimensions
ICLR 2024Rejected
4
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
NeurIPS 2024Poster
3
Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
ICLR 2024Poster
4
Slight Corruption in Pre-training Data Makes Better Diffusion Models
NeurIPS 2024Spotlight