Huang, Wei
105 publications
ICLR
2025
From Layers to States: A State Space Model Perspective to Deep Neural Network Layer Dynamics
ICCV
2025
GaRe: Relightable 3D Gaussian Splatting for Outdoor Scenes from Unconstrained Photo Collections
NeurIPS
2025
Generalization Bound of Gradient Flow Through Training Trajectory and Data-Dependent Kernel
NeurIPS
2025
Less Is More: An Attention-Free Sequence Prediction Modeling for Offline Embodied Learning
ICLR
2025
On the Optimization and Generalization of Two-Layer Transformers with Sign Gradient Descent
AISTATS
2025
Quantifying the Optimization and Generalization Advantages of Graph Neural Networks over Multilayer Perceptrons
NeurIPS
2025
Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics
NeurIPS
2025
Towards Unsupervised Training of Matching-Based Graph Edit Distance Solver via Preference-Aware GAN
ICLR
2024
A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error
IJCAI
2024
Enhancing Dual-Target Cross-Domain Recommendation with Federated Privacy-Preserving Learning
NeurIPS
2024
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
NeurIPS
2024
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
NeurIPS
2024
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
NeurIPS
2024
SLTrain: A Sparse Plus Low Rank Approach for Parameter and Memory Efficient Pretraining
ICLR
2024
Understanding Convergence and Generalization in Federated Learning Through Feature Learning Theory
NeurIPS
2024
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
NeurIPS
2023
Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning
NeurIPSW
2023
Graph Neural Networks Benefit from Structural Information Provably: A Feature Learning Perspective
ICCVW
2023
PCTrans: Position-Guided Transformer with Query Contrast for Biological Instance Segmentation
AutoML
2023
“No Free Lunch” in Neural Architectures? a Joint Analysis of Expressivity, Convergence, and Generalization