Wei Huang
~Wei_Huang6
27
论文总数
13.5
年均投稿
平均评分
接收情况22/27
会议分布
NeurIPS
11
ICLR
9
ICML
7
发表论文 (27 篇)
202516 篇
5
How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
NeurIPS 2025Poster
5
Label Noise Gradient Descent Improves Generalization in the Low SNR Regime
ICLR 2025Rejected
3
On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
ICLR 2025Spotlight
4
Test-Time Graph Neural Dataset Search With Generative Projection
ICML 2025Poster
3
The Role of Label Noise in the Feature Learning Process
ICLR 2025Rejected
3
On the Role of Label Noise in the Feature Learning Process
ICML 2025Poster
3
Multinoulli Extension: A Lossless Yet Effective Probabilistic Framework for Subset Selection over Partition Constraints
ICML 2025Poster
3
Provable In-Context Vector Arithmetic via Retrieving Task Concepts
ICML 2025Poster
4
Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
NeurIPS 2025Poster
6
On the Feature Learning in Diffusion Models
ICLR 2025Poster
4
Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
ICML 2025Poster
4
Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images?
ICML 2025Poster
5
Node-wise Filtering in Graph Neural Networks: A Mixture of Experts Approach
ICLR 2025Rejected
4
Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
NeurIPS 2025Poster
4
Scaling Diffusion Transformers Efficiently via $\mu$P
NeurIPS 2025Poster
4
GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
ICML 2025Poster
202411 篇
3
On the Comparison between Multi-modal and Single-modal Contrastive Learning
NeurIPS 2024Poster
5
Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective
ICLR 2024Rejected
4
Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
ICLR 2024Poster
5
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
NeurIPS 2024Poster
5
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
NeurIPS 2024Poster
4
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
NeurIPS 2024Poster
4
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
NeurIPS 2024Poster
4
Provable and Efficient Dataset Distillation for Kernel Ridge Regression
NeurIPS 2024Poster
3
Vulnerable Region Discovery through Diverse Adversarial Examples
ICLR 2024Rejected
3
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
NeurIPS 2024Poster
3
Graph Lottery Ticket Automated
ICLR 2024Poster