Hi, I’m Andrew
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 & speculative decoding) and hardware-aware algorithms.
You can find me on LinkedIn, GitHub, Twitter, and Google Scholar
Publications
[1] Andrew Zhang, Anushka Sivakumar, Chia-Wei Tang, and Chris Thomas. Flexible-length text infilling for discrete diffusion models. In: Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2025.
[2] Anushka Sivakumar, Andrew Zhang, Zaber Ibn Abdul Hakim, and Chris Thomas. SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models. In: Findings of the Association for Computational Linguistics (EMNLP Findings). 2025.
[3] Md. Atabuzzaman, Andrew Zhang, and Chris Thomas. Zero-Shot Fine-Grained Image Classification Using Large Vision-Language Models. In: Findings of the Association for Computational Linguistics (EMNLP Findings). 2025.
[4] Hani Alomari, Anushka Sivakumar, Andrew Zhang, and Chris Thomas. Maximal Matching Matters: Preventing Representation Collapse for Robust Cross-Modal Retrieval. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL). 2025.
Get In Touch
Please email me at azhang42 [at] vt [dot] edu or DM me on Twitter