Yixiao Huang

Orcid: 0009-0007-0512-6031

Affiliations:
  • University of California, Berkeley, CA, USA
  • University of Michigan, Ann Arbor, MI, USA (former)
  • City University of Hong Kong, Department of Electrical and Engineering, Hong Kong (former)


According to our database1, Yixiao Huang authored at least 11 papers between 2022 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

Online presence:

On csauthors.net:

Bibliography

2025
Reinforcement Learning for Flow-Matching Policies.
CoRR, July, 2025

Spooky Action at a Distance: Normalization Layers Enable Side-Channel Spatial Communication.
CoRR, July, 2025

Generalization or Hallucination? Understanding Out-of-Context Reasoning in Transformers.
CoRR, June, 2025

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models.
CoRR, May, 2025

Fast Adversarial Training against Sparse Attacks Requires Loss Smoothing.
CoRR, February, 2025

On the Power of Convolution-Augmented Transformer.
Proceedings of the AAAI-25, Sponsored by the Association for the Advancement of Artificial Intelligence, February 25, 2025

2024
Towards Efficient Training and Evaluation of Robust Models against l<sub>0</sub> Bounded Adversarial Perturbations.
CoRR, 2024

Towards Efficient Training and Evaluation of Robust Models against l0 Bounded Adversarial Perturbations.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mechanics of Next Token Prediction with Self-Attention.
Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2022
Stratification and Survival Prediction for Amyotrophic Lateral Sclerosis Patients.
Proceedings of the IEEE-EMBS International Conference on Biomedical and Health Informatics, 2022


  Loading...