Andrew Zhang

AWS Trainium inference

Virginia Tech BS/MS

azhang42 [at] vt [dot] edu

I currently work on accelerating inference on AWS Trainium devices. I did a 4 year BS/MS at Virginia Tech under Dr. Chris Thomas. I am interested in multi-token generation (discrete diffusion and speculative decoding) and hardware-aware algorithms.

You can find me on LinkedIn, GitHub, X, and Google Scholar.

Get in Touch

Please email me at azhang42 [at] vt [dot] edu or DM me on X.

latest posts

Jan 13, 2026	Thought on TTT-E2E
Jan 06, 2026	Recent Trend in Architectures
Dec 04, 2025	Published 4 Papers!
Dec 04, 2025	November & December 2025 Reading List
Oct 21, 2025	Discrete Diffusion for Text Infilling
Mar 25, 2025	Multimodal Paper Reviews

selected publications

Flexible-length text infilling for discrete diffusion models

Andrew Zhang, Anushka Sivakumar, Chia-Wei Tang, and Chris Thomas

In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025

Bib

@inproceedings{zhang2025flexible,
  title = {Flexible-length text infilling for discrete diffusion models},
  author = {Zhang, Andrew and Sivakumar, Anushka and Tang, Chia-Wei and Thomas, Chris},
  booktitle = {Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP)},
  year = {2025},
}

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models

Anushka Sivakumar, Andrew Zhang, Zaber Ibn Abdul Hakim, and Chris Thomas

In Findings of the Association for Computational Linguistics (EMNLP Findings), 2025

Bib

@inproceedings{sivakumar2025steervlm,
  title = {SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models},
  author = {Sivakumar, Anushka and Zhang, Andrew and Hakim, Zaber Ibn Abdul and Thomas, Chris},
  booktitle = {Findings of the Association for Computational Linguistics (EMNLP Findings)},
  year = {2025},
}

Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models

Md. Atabuzzaman, Andrew Zhang, and Chris Thomas

In Findings of the Association for Computational Linguistics (EMNLP Findings), 2025

Bib

@inproceedings{atabuzzaman2025zeroshot,
  title = {Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models},
  author = {Atabuzzaman, Md. and Zhang, Andrew and Thomas, Chris},
  booktitle = {Findings of the Association for Computational Linguistics (EMNLP Findings)},
  year = {2025},
}

Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval

Hani Alomari, Anushka Sivakumar, Andrew Zhang, and Chris Thomas

In Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025

Bib

@inproceedings{alomari2025maximal,
  title = {Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval},
  author = {Alomari, Hani and Sivakumar, Anushka and Zhang, Andrew and Thomas, Chris},
  booktitle = {Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL)},
  year = {2025},
}