Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, 2025

2024

AtomThink: A Slow Thinking Framework for Multimodal Mathematical Reasoning.

[BibT_eX]

[DOI]

CoRR, 2024

CrystalX: Ultra-Precision Crystal Structure Resolution and Error Correction Using Deep Learning.

[BibT_eX]

[DOI]

CoRR, 2024

ATLAS: Adapter-Based Multi-Modal Continual Learning with a Two-Stage Learning Strategy.

[BibT_eX]

[DOI]

CoRR, 2024

Investigating the Impact of Model Complexity in Large Language Models.

[BibT_eX]

[DOI]

Jing Luo

Huiyuan Wang

Weiran Huang

CoRR, 2024

Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training.

[BibT_eX]

[DOI]

CoRR, 2024

An adapted large language model facilitates multiple medical tasks in diabetes care.

[BibT_eX]

[DOI]

CoRR, 2024

Can I understand what I create? Self-Knowledge Evaluation of Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

BreakGPT: A Large Language Model with Multi-stage Structure for Financial Breakout Detection.

[BibT_eX]

[DOI]

Kang Zhang

Osamu Yoshie

Weiran Huang

CoRR, 2024

ChemLLM: A Chemical Large Language Model.

[BibT_eX]

[DOI]

CoRR, 2024

The Information of Large Language Model Geometry.

[BibT_eX]

[DOI]

Zhiquan Tan

Chenghai Li

Weiran Huang

CoRR, 2024

Large Language Model Evaluation via Matrix Entropy.

[BibT_eX]

[DOI]

CoRR, 2024

SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

A Statistical Theory of Regularization-Based Continual Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Matrix Information Theory for Self-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Provable Contrastive Continual Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

OTMatch: Improving Semi-Supervised Learning with Optimal Transport.

[BibT_eX]

[DOI]

Zhiquan Tan

Kaipeng Zheng

Weiran Huang

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Information Flow in Self-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Unveiling the Dynamics of Information Interplay in Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

2023

Efficient Few-Shot Clinical Task Adaptation with Large Language Models.

[BibT_eX]

[DOI]

Kaipeng Zheng

Weiran Huang

Lichao Sun

CoRR, 2023

Understanding Grokking Through A Robustness Viewpoint.

[BibT_eX]

[DOI]

Zhiquan Tan

Weiran Huang

CoRR, 2023

InstructionGPT-4: A 200-Instruction Paradigm for Fine-Tuning MiniGPT-4.

[BibT_eX]

[DOI]

CoRR, 2023

FILM: How can Few-Shot Image Classification Benefit from Pre-Trained Language Models?

[BibT_eX]

[DOI]

CoRR, 2023

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

[BibT_eX]

[DOI]

Kaipeng Zheng

Huishuai Zhang

Weiran Huang

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Rethinking Weak Supervision in Helping Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Towards the Generalization of Contrastive Self-Supervised Learning.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023

2022

Learning with Noisily-labeled Class-imbalanced Data.

[BibT_eX]

[DOI]

CoRR, 2022

Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis.

[BibT_eX]

[DOI]

Jiaye Teng

Weiran Huang

Haowei He

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Towards the Generalization of Contrastive Self-Supervised Learning.

[BibT_eX]

[DOI]

Weiran Huang

Mingyang Yi

Xuyang Zhao

CoRR, 2021

Can Pretext-Based Self-Supervised Learning Be Boosted by Downstream Data? A Theoretical Analysis.

[BibT_eX]

[DOI]

Jiaye Teng

Weiran Huang

CoRR, 2021

2020

Locally Differentially Private (Contextual) Bandits Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, 2020

Boosting Few-Shot Learning With Adaptive Margin Loss.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

New Interpretations of Normalization Methods in Deep Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

Meta-Learning PAC-Bayes Priors in Model Averaging.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019

DARTS+: Improved Differentiable Architecture Search with Early Stopping.

[BibT_eX]

[DOI]

CoRR, 2019

Few-Shot Learning With Global Class Representations.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Modeling Local Dependence in Natural Language with Multi-Channel Recurrent Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence, 2019

2018

Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications (Extended Version).

[BibT_eX]

[DOI]

CoRR, 2018

Multi-Round Influence Maximization (Extended Version).

[BibT_eX]

[DOI]

CoRR, 2018

Community Exploration: From Offline Optimization to Online Learning.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Multi-Round Influence Maximization.

[BibT_eX]

[DOI]

Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2018

Combinatorial Pure Exploration with Continuous and Separable Reward Functions and Its Applications.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, 2018

2017

Partitioned Sampling of Public Opinions Based on Their Social Dynamics.

[BibT_eX]

[DOI]

Weiran Huang

Liang Li

Wei Chen

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2015

Partitioned Sampling of Public Opinions Based on Their Social Evolution.

[BibT_eX]

[DOI]

Weiran Huang

Liang Li

Wei Chen

CoRR, 2015

Weiran Huang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...