Sophia Tang
sophtang [at] engineering.upenn.edu
Hi! I'm a final-year undergraduate at the University of Pennsylvania building foundations of generative modeling for science, currently in the Chatterjee Lab and visiting the Kempner Institute at Harvard.
Research areas · hover to preview, click to filter my papers
Methods
Applications
↑ pick a research area
I also write long-form tutorial papers on foundational topics in machine learning and shorter technical articles on my Substack, Alchemy Bio. Featured below ↓
Aside from research, I study computer science and statistics in the Jerome Fisher Program in Management & Technology. I'm always exploring new theoretical ideas and thinking about interesting problems to apply them to. If any of these topics sparks your interest, I would love to connect!
Updates
| Sep 24, 2026 | Four papers accepted at NeurIPS 2026 main: Expanding Flow Maps 🌊, EntangledSBM ⚛️, ActFlow 🧬, and Beckmann Transport Models 💫! See you in Sydney 🇦🇺 |
|---|---|
| Sep 15, 2026 | Discrete Beckmann Transport Models 🛸 is out! We introduce a framework for discrete generation that learns an autonomous transport map for one- and few-step language modeling and reasoning! Also be sure to check out Beckmann Transport Models |
| Aug 23, 2026 | I am co-organizing the Beyond Next Token Prediction (BeNTo) 🍱 workshop at NeurIPS 2026 in Sydney! Submit your newest work in generative modeling via OpenReview by August 29th! |
| Jul 24, 2026 | Expanding Flow Maps 🌊 is out! We develop a generalizable framework for learning generative flows with dynamically increasing dimensionality! |
| Jun 15, 2026 | A2D2 🃏 and mRNAutilus 🧬 are out! A new framework for reward-alignment of any-length discrete diffusion with adaptive decoding, and an experimentally-validated multi-objective mRNA generative model! |
| Mar 20, 2026 | New tutorial paper on the Foundations of Schrödinger Bridges for Generative Modeling (220 pages, 24 figures) is out on arXiv! |
| Jan 26, 2026 | Branched Schrödinger Bridge Matching is accepted at ICLR 2026 main! 🌳🧫 Looking forward to presenting in Rio! 🇧🇷 |
| Jan 23, 2026 | Awarded the CRA Outstanding Undergraduate Researcher Award (1 of 8 across North America)! Read the news article here! |
| Nov 11, 2025 | EntangledSBM is out! Read our paper on simulating interacting multi-particle systems with a novel Schrödinger bridge matching framework! |
| Sep 30, 2025 | TR2-D2 is out! Read our paper on off-policy RL for discrete diffusion fine-tuning with multi-objective rewards! |
| May 01, 2025 | PepTune: De Novo Generation of Therapeutic Peptides with Multi-Objective-Guided Discrete Diffusion accepted at ICML 2025! Come by us at Poster Session 4 to chat (+ free PepTune stickers) |
Selected Publications
-
Advances in Neural Information Processing Systems (NeurIPS 2026), Aug 2026 -
Advances in Neural Information Processing Systems (NeurIPS 2026), Jun 2026 -
International Conference on Machine Learning (ICML 2026) Spotlight, May 2026 -
arXiv, Preprint, Mar 2026 - Advances in Neural Information Processing Systems (NeurIPS 2026), Nov 2025
- arXiv, Preprint, Sep 2025
-
arXiv, Preprint, May 2025
Invited Talks
- Sep 2026Discrete Beckmann Transport Models for One-Step Language Modeling and ReasoningDiscrete Diffusion Reading Group
- July 2026
- July 2026Spherical Equivariant Graph TransformersCambridge Ellis Unit Summer School on Probabilistic Machine Learning 2026
- Nov 2025
- July 2025