Portrait of Anant Gupta

Anant Gupta

M.S. in Computer Science · Georgia Institute of Technology

I'm a master's student at Georgia Tech, where I am fortunate to be working with Christopher MacLellan in the Teachable AI Lab and Vijay Ganesh in the Reasoning and Learning Group.

Humans and AI systems overlap in some ways and differ in others. Sometimes they share a property but express it differently. My working belief is that many intuitions about how people learn can be formalized in models. I hope to find which intuitions transfer, understand why others don't, and turn the ones that do into learning methods for these systems.

Most of my work is in continual learning and meta-learning. In continual learning, I ask when and how a model should take in new information without forgetting. In meta-learning, I ask how a model can learn to learn: efficiently, continually, and from unstructured data. In the long run, I want models that learn efficiently on their own.

I also love to teach, and have been a TA for four semesters. Grading in large courses takes TAs a long time, so I have worked on training models to give students feedback in the meantime.

Read the longer version

News

  • Trust Region Continual Learning as an Implicit Meta-Learner was accepted to NeurIPS 2026.
  • CobwebTM was accepted to Findings of ACL 2026.
  • Avoid Catastrophic Forgetting with Rank-1 Fisher was accepted to ICLR 2026.
  • Gave an oral presentation on Hierarchical Semantic Retrieval with Cobweb at ACS 2025.

Research

Continual learningMeta-learning

Continual Learning in Diffusion Models

with Christopher MacLellan

We show that the empirical Fisher of a diffusion model is rank-1 in low-SNR regimes. Using this, we define a rank-1 EWC penalty and show that, combined with replay, the model forgets less. We then show that this formulation is equivalent to one-step MAML under local approximations, and observe the effect directly: the model re-learns previous tasks faster than other methods.

Constraining how much you update is already a form of learning to learn.

Meta-continual learning

Self-Consolidating Language Models

with Christopher MacLellan

The same intuition as the diffusion work, but at LLM scale the Fisher is too expensive to compute, so SCoL lets the model learn it: meta-RL decides which of its own layers to change when it absorbs a passage. Trained only on short contexts, it beats in-context baselines that see the whole passage on LongBench v2.

Consolidation with autonomy: the model decides where new knowledge goes.

Continual learning

Hierarchical and Incremental Concept Formation

with Christopher MacLellan

Cobweb builds a concept hierarchy incrementally, one example at a time. As a retrieval index it matches dense encoders and stays robust where kNN collapses; CobwebTM extends it to lifelong hierarchical topic modeling and matches or beats prior incremental methods.

The external-memory side: a retrieval structure that is itself continual.

Transfer/composition

Multi-Role Reinforcement Learning

with Christopher MacLellan · ongoing

One language model is trained in several study roles over the same examples — comparing problems, identifying subgoals, explaining. Roles that never produce an answer still improve answer accuracy.

People study the same material in several ways; so can a model.

Transfer/composition

Test-Time Compositional Generalization

with Christopher MacLellan

From a single out-of-distribution query, recover concept prototypes by score-based mode finding across the noise levels of a pretrained diffusion model, then compose them into a product-of-experts teacher.

People compose familiar concepts freely; here a diffusion model does too.

Human errors

Simulating Student Misconceptions

with Vijay Ganesh · ongoing

Given a specific misconception, can a model produce the wrong answer a real student holding it would produce, in a single turn? A counterfactual generation problem.

Human-like errors can benchmark and train models; here, for grading theoretical computer science, where partial credit is hard.

Selected publications

* denotes equal contribution.

  1. NeurIPS 2026

    Trust Region Continual Learning as an Implicit Meta-Learner

    Zekun Wang*, Anant Gupta*, Christopher J. MacLellan

    Conference on Neural Information Processing Systems · Main Track · Poster · Atlanta, Dec 2026

  2. ICLR 2026

    Avoid Catastrophic Forgetting with Rank-1 Fisher from Diffusion Models

    Zekun Wang*, Anant Gupta*, Zihan Dong, Christopher J. MacLellan

    International Conference on Learning Representations · Main Track · Poster · Rio de Janeiro, Apr 2026

  3. Preprint 2026

    Cross-Task Transfer via Multi-Role Reinforcement Learning

    Anant Gupta, Zekun Wang, Wei Xu, Christopher J. MacLellan

    2026

  4. Preprint 2026

    Self-Consolidating Language Models: Continual Knowledge Incorporation from Context

    Zekun Wang*, Anant Gupta*, Zihan Dong, Christopher J. MacLellan

    arXiv:2605.07076, 2026

All publications · also on Google Scholar

Teaching

Four semesters of TAing Automata and Complexity shaped how I think about learning in both humans and machines — and led directly to my work on LLMs for education.

  • Jan 2024 – Dec 2025

    Teaching Assistant — CS 4510: Automata and Complexity

    Georgia Institute of Technology · Head TA, Spring 2025

    Delivered two lectures to 300+ students, led 12 review sessions, and wrote homework and exam problems.

  • Jan 2023 – Aug 2023

    College of Computing Tutor

    Georgia Institute of Technology

    Tutored 150+ hours across AI, algorithms, data structures, and discrete mathematics.

Service

  • Reviewer, International Conference on Learning Representations (ICLR 2027)
  • Reviewer, NeurIPS 2026 Workshop on Towards Test-Time Continual Learning Agents (TTCL)

Education

  • M.S. Computer Science, Georgia Tech — expected May 2027
    GPA 4.0/4.0
  • B.S. Computer Science & B.S. Mathematics, Georgia Tech — May 2025
    GPA 4.0/4.0 · Putnam 2022 Honorable Mention (top 500 of 4500+)

Get in touch

I'm always happy to talk about continual learning, meta-learning, or LLMs for education — and I'm glad to hear from students thinking about research. The fastest way to reach me is email.

agupta886@gatech.edu
  • Happy to chat about Research collaborations, my papers, or PhD applications
  • Find me Google Scholar · GitHub · LinkedIn
  • Based in Atlanta, GA — Georgia Institute of Technology