Research Profile

Yichen Zhang

Incoming Research Student, Osaka University

My primary research focus is Generative AI for drug discovery. I am also broadly interested in vision-language models and embodied AI.

I recently completed my M.S. in Computer Engineering at NYU and will join Osaka University in June 2026, working toward a Ph.D. on generative and foundation-model approaches to molecular and biological sequence design.

Primary Direction

Generative AI for Drug Discovery

Explore

Yichen Zhang
  • 2026 Joining Osaka University as a Research Student in June 2026, preparing for Ph.D. studies in Generative AI for Drug Discovery.
  • 2026 Graduated from NYU with an M.S. in Computer Engineering (Jan 2026).
  • 2025 Open-sourced weights and demo for schema-constrained food extraction with fine-tuned SmolVLM2-500M.
  • 2025 Published efficiency analysis of Tiny Recursive Models on Sudoku-Extreme reasoning tasks.
  • 2025 Open-sourced GeneLM-Evo2, a zero-shot genomic variant pathogenicity scoring pipeline built on Evo2 7B.

Generative AI for Drug Discovery

Generative and foundation-model methods for molecules, biological sequences, and scientific discovery. This is my primary research direction.

Vision-Language Models

Multimodal models for perception, reasoning, and structured generation.

Embodied AI & Robotics

Agents that connect language, vision, and action for grounded decision-making in interactive environments.

VLM Fine-tuning for Schema-Constrained Food Extraction

2025

Fine-tuned SmolVLM2-500M for reliable JSON extraction from food images and released reproducible weights for downstream integration.

GeneLM-Evo2: Zero-shot Genomic Variant Pathogenicity Analysis

2025

Built a zero-shot pathogenicity scoring pipeline around Evo2 7B with long-context genomic inference and a scalable GPU serving stack.

Efficiency Analysis of Tiny Recursive Models for Reasoning

2025

Reproduced Tiny Recursive Models and measured how accuracy, throughput, and compute budgets interact on Sudoku-Extreme reasoning tasks.