Yifan Kang

new_pfp.jpg

I’m a junior at MIT, double-majoring in Artificial Intelligence (Course 6-4) and Mathematics (Course 18). I’m advised by Leslie Kaelbling in the Learning & Intelligent Systems Group.

I’m interested in building robots that can learn efficiently at deployment time, adapting to new tasks from a handful of demonstrations rather than another training run. Right now I’m exploring better ways to combine coding agents with robot foundation models.

Outside the lab, I enjoy long-distance running, watching anime, rhythm games (Arcaea and Maimai), and singing.

Selected research all →

ENCORE

ENCORE: Few-Shot Agentic Discovery of Manipulation Strategies

Oral, NeurIPS 2026 Robot Learning Workshop

Diffusion LM interpretability

Interpreting Diffusion Language Models Over Denoising Time

CoLM 2026 Workshop on Non-Autoregressive Language Models

Doodle Agent

Doodle Agent: Exploring Freeform Visual Generation with Multimodal LLMs

ICCV 2025 Workshop on AI for Visual Arts

Experience

  • Research Intern, 2077AI — Jun 2026 to present
  • Student Researcher, MIT, with Leslie Pack Kaelbling — Jun 2025 to present
  • Student Researcher, MIT, with Antonio Torralba — summer 2025

Elsewhere

  • Writing — course surveys, final projects and lecture notes.
  • Coursework — what I have taken at MIT, by term.

Latest posts all →

May 28, 2026 Sutton's Big World Hypothesis
Feb 07, 2026 Classes that I am taking this semester (Spring 2026)
Feb 02, 2026 The Alchemist’s Shadow in a Chemist’s World