PaperHub

Difan Zou

~Difan_Zou1

32
论文总数
16.0
年均投稿
6.1
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

7.8
4

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory

NeurIPS 2025Poster
3.8
4

Towards a Theoretical Understanding of Memorization in Diffusion Models

ICLR 2025withdrawn
8.2
4

Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

NeurIPS 2025Poster
6.4
4

F-Adapter: Frequency-Adaptive Parameter-Efficient Fine-Tuning in Scientific Machine Learning

NeurIPS 2025Poster
6.0
6

On the Feature Learning in Diffusion Models

ICLR 2025Poster
5.8
4

Beyond Surface Structure: A Causal Assessment of LLMs' Comprehension ability

ICLR 2025Poster
7.3
4

On the Robustness of Transformers against Context Hijacking for Linear Classification

NeurIPS 2025Poster
6.8
5

How Does Critical Batch Size Scale in Pre-training?

ICLR 2025Poster
5.5
3

On the Robustness of Transformers against Context Hijacking for Linear Classification

ICML 2025Rejected
7.3
4

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

NeurIPS 2025Poster
6.6
4

Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?

ICML 2025Poster
5.6
5

Label Noise Gradient Descent Improves Generalization in the Low SNR Regime

ICLR 2025Rejected
5.3
3

Self-Control of LLM Behaviors by Compressing Suffix Gradient into Prefix Controller

ICLR 2025Rejected
5.5
4

Towards Understanding Fine-Tuning Mechanisms of LLMs via Circuit Analysis

ICML 2025Poster
6.8
5

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

NeurIPS 2025Poster
7.0
4

HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation

ICLR 2025Poster
7.3
4

Speculative Jacobi-Denoising Decoding for Accelerating Autoregressive Text-to-image Generation

NeurIPS 2025Poster
6.6
4

Masked Autoencoders Are Effective Tokenizers for Diffusion Models

ICML 2025Spotlight

202414