Weiran Huang

Affiliations

Shanghai Jiao Tong University

papers

458

total citations

papers (13)

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

NEURIPS 2023arXiv

citations

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

NEURIPS 2023arXiv

citations

Provable Contrastive Continual Learning

ICML 2024arXiv

citations

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

NEURIPS 2025arXiv

citations

OTMatch: Improving Semi-Supervised Learning with Optimal Transport

ICML 2024arXiv

citations

Unveiling the Dynamics of Information Interplay in Supervised Learning

ICML 2024arXiv

citations

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

NEURIPS 2025arXiv

citations

Weiran Huang

Affiliations

papers (13)

Boosting Few-Shot Learning With Adaptive Margin Loss

Locally Differentially Private (Contextual) Bandits Learning

When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method

A Statistical Theory of Regularization-Based Continual Learning

Matrix Information Theory for Self-Supervised Learning

Information Flow in Self-Supervised Learning

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

Provable Contrastive Continual Learning

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

OTMatch: Improving Semi-Supervised Learning with Optimal Transport

Unveiling the Dynamics of Information Interplay in Supervised Learning

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

papers (13)

Boosting Few-Shot Learning With Adaptive Margin Loss

Locally Differentially Private (Contextual) Bandits Learning

When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method

A Statistical Theory of Regularization-Based Continual Learning

Matrix Information Theory for Self-Supervised Learning

Information Flow in Self-Supervised Learning

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

Provable Contrastive Continual Learning

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

OTMatch: Improving Semi-Supervised Learning with Optimal Transport

Unveiling the Dynamics of Information Interplay in Supervised Learning

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling