Tianyang Hu

Affiliations:

Chinese University of Hong Kong - Shenzhen (CUHK-SZ), School of Data Science, Shenzhen, China
National University of Singapore, Singapore (former)
Purdue University, West Lafayette, IN, USA (former, PhD)

According to our database¹, Tianyang Hu authored at least 46 papers between 2018 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

The Structural Origin of Attention Sink: Variance Discrepancy, Super Neurons, and Dimension Disparity.

[BibT_eX]

[DOI]

CoRR, May, 2026

Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation.

[BibT_eX]

[DOI]

CoRR, May, 2026

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow.

[BibT_eX]

[DOI]

Bowen Zheng

Yihong Luo

Tianyang Hu

CoRR, May, 2026

Autoregressive Visual Generation Needs a Prologue.

[BibT_eX]

[DOI]

CoRR, May, 2026

TDM-R1: Reinforcing Few-Step Diffusion Models with Non-Differentiable Reward.

[BibT_eX]

[DOI]

CoRR, March, 2026

Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences.

[BibT_eX]

[DOI]

CoRR, February, 2026

2025

Reinforcing Diffusion Models by Direct Group Preference Optimization.

[BibT_eX]

[DOI]

Yihong Luo

Tianyang Hu

Jing Tang

CoRR, October, 2025

SeedPrints: Fingerprints Can Even Tell Which Seed Your Large Language Model Was Trained From.

[BibT_eX]

[DOI]

CoRR, September, 2025

Any-Order GPT as Masked Diffusion Model: Decoupling Formulation and Architecture.

[BibT_eX]

[DOI]

CoRR, June, 2025

Prefix-Tuning+: Modernizing Prefix-Tuning by Decoupling the Prefix from Attention.

[BibT_eX]

[DOI]

CoRR, June, 2025

Variational Autoencoding Discrete Diffusion with Enhanced Dimensional Correlations Modeling.

[BibT_eX]

[DOI]

CoRR, May, 2025

Rewards Are Enough for Fast Photo-Realistic Text-to-image Generation.

[BibT_eX]

[DOI]

CoRR, March, 2025

AlgoFormer: An Efficient Transformer Framework with Algorithmic Structures.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2025

Minimax Optimal Deep Neural Network Classifiers Under Smooth Decision Boundary.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2025

Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

Getting More Juice Out of Your Data: Hard Pair Refinement Enhances Visual-Language Models Without Extra Data.

[BibT_eX]

[DOI]

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

Elucidating the design space of language models for image generation.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Adding Additional Control to One-Step Diffusion with Joint Distribution Matching.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Learning Few-Step Diffusion Models by Trajectory Distribution Matching.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

2024

Random Smoothing Regularization in Kernel Gradient Descent Learning.

[BibT_eX]

[DOI]

J. Mach. Learn. Res., 2024

On the Expressive Power of a Variant of the Looped Transformer.

[BibT_eX]

[DOI]

CoRR, 2024

Deciphering the Projection Head: Representation Evaluation Self-supervised Learning.

[BibT_eX]

[DOI]

Jiajun Ma

Tianyang Hu

Wenjia Wang

Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence, 2024

The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling.

[BibT_eX]

[DOI]

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

Referee Can Play: An Alternative Approach to Conditional Generation via Model Inversion.

[BibT_eX]

[DOI]

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

Exact Conversion of In-Context Learning to Model Weights in Linearized-Attention Transformers.

[BibT_eX]

[DOI]

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

Elucidating the design space of classifier-guided diffusion generation.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Accelerating Diffusion Sampling with Optimized Time Steps.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023

Continual Learning by Modeling Intra-Class Variation.

[BibT_eX]

[DOI]

Trans. Mach. Learn. Res., 2023

Training Energy-Based Models with Diffusion Contrastive Divergences.

[BibT_eX]

[DOI]

CoRR, 2023

ConsistentNeRF: Enhancing Neural Radiance Fields with 3D Consistency for Sparse View Synthesis.

[BibT_eX]

[DOI]

CoRR, 2023

Boosting Visual-Language Models by Exploiting Hard Samples.

[BibT_eX]

[DOI]

CoRR, 2023

Exact Count of Boundary Pieces of ReLU Classifiers: Towards the Proper Complexity Measure for Classification.

[BibT_eX]

[DOI]

Pawel Piwek

Adam Klukowski

Tianyang Hu

Proceedings of the Uncertainty in Artificial Intelligence, 2023

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models.

[BibT_eX]

[DOI]

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

Complexity Matters: Rethinking the Latent Space for Generative Modeling.

[BibT_eX]

[DOI]

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

Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

ContraNeRF: Generalizable Neural Radiance Fields for Synthetic-to-real Novel View Synthesis via Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Inducing Neural Collapse in Deep Long-tailed Learning.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2023

2022

Understanding Square Loss in Training Overparametrized Neural Network Classifiers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

ZooD: Exploiting Model Zoo for Out-of-Distribution Generalization.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

2021

Regularization Matters: A Nonparametric Perspective on Overparametrized Neural Network.

[BibT_eX]

[DOI]

Proceedings of the 24th International Conference on Artificial Intelligence and Statistics, 2021

2020

Optimal Rate of Convergence for Deep Neural Network Classifiers under the Teacher-Student Setting.

[BibT_eX]

[DOI]

Tianyang Hu

Zuofeng Shang

Guang Cheng

CoRR, 2020

2018

Stein Neural Sampler.

[BibT_eX]

[DOI]

CoRR, 2018

Tianyang Hu

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...