Research agenda

AI for Adjuvant Design

I study structured, knowledge-grounded AI for formalizing adjuvant research questions, evaluating scientific reasoning, and testing generated designs against literature evidence and mechanistic constraints.

Benchmarking Knowledge modeling Verifiable reasoning

About

Structured data modeling for scientific AI

I am a PhD candidate in Pattern Recognition and Intelligent Systems at the State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), jointly trained with Zhongguancun Academy. I am advised by Prof. Cheng-Lin Liu.

My related work covers reliable and efficient multimodal models, embodied reasoning, scientific agents, and online handwriting recognition and generation. These projects share an emphasis on structured data modeling across perception, language, scientific knowledge, and action.

Research

Research agenda and methodological foundations

The three layers connect a central scientific problem with its methodological foundations and broader applications.

Primary agenda

AI for Adjuvant Design

Formalizing adjuvant knowledge, benchmarking open-ended scientific reasoning, and verifying generated designs through literature-grounded mechanism chains.

Technical foundation

Structured Multimodal Modeling

Reliable reasoning, spatial grounding, adaptive visual representations, token efficiency, and factuality alignment for multimodal systems.

Broader capabilities

Science, Action & Sequential Data

Scientific agents, materials and weather applications, embodied navigation, video understanding, and online Chinese handwriting.

01

Formalize

Represent adjuvant design principles and immune mechanisms.

02

Benchmark

Evaluate open-ended, multimodal scientific reasoning.

03

Verify

Check proposed designs against precedent, outcomes, and mechanisms.

Updates

Research milestones

  1. MR-ALIGN was accepted to ACL 2026 Findings, extending our work on factuality alignment for reasoning models.
  2. Data-constrained machine learning for materials science was accepted to Materials Genome Engineering Advances.
  3. MeteorPred, ChartAgent, and fine-grained VLM quantization were accepted to CVPR 2026.
  4. Our adjuvant benchmark was accepted to ICLR 2026, alongside work on adaptive patching; RANGER was accepted to ICRA 2026.

Selected work

Problem definition, benchmarking, and verification

The first two projects form a continuous research program in AI for adjuvant design.

AI for Adjuvant Design

Preprint · 2026 SAVANT neuro-symbolic verification framework

Design generation & verification

SAVANT: A Neuro-Symbolic Verification Framework for Adjuvant Design

Yi Chen, Yu Zhang, Jian Xu, Xu-Yao Zhang, Hua Yue, Xinming Wang, Zequan Lyu, Boran Wang, Hongyi Liu, Yan Wang, Peiyuan Cao, Wei Wei, Cheng-Lin Liu

  • Frames adjuvant design verification as literature-grounded mechanistic proof checking.
  • Checks precedent, immune outcomes, and mechanism chains while exposing evidence gaps.

Selected Technical Foundations

Preprint · 2026 VisTopo topology-aware spatial grounding framework

Topology-Aware Visual Prompts are Weakly Supervised Spatial Grounding Learners

Yi Chen, MingMing Yu, Boran Wang, Jie Gu, Chu Tang, Jingmin Chen, Rui-Qi Wang

Uses explicit referent-relation modeling and topology-aware prompting for weakly supervised spatial grounding.

Publications

Publications by research area

Select a research area to filter the list. * denotes equal contribution.

Order: newest year first; within each year, earlier Yi Chen author positions first.

Core research agenda

AI for Adjuvant Design

Technical foundations

Structured Multimodal Modeling & Reasoning

Broader capabilities

Scientific, Embodied & Domain Work

Background

Education, recognition & service

Education

  1. PhD Candidate, Pattern Recognition and Intelligent SystemsMAIS, CASIA
  2. MS, Electronic InformationNLPR, CASIA
  3. Detection, Guidance and Control TechnologySchool of Space Science and Technology, Xidian University

Selected Honors

  • 2026ICML Gold Reviewer
  • 2025Academic Research Star, Zhongguancun Academy
  • 2025Best Paper Award, AIHCIR
  • 20243rd Place, ICDAR Multi-Font Group Recognition & OCR Competition

Academic Service

  • JournalsIEEE TCSVT, TMLR
  • Program committeeAAAI 2026, AAAI 2027
  • Conference reviewerICLR 2026, CVPR 2026, ICML 2026, ECCV 2026

Open Source

PaddleScience contributor. Integrated Crystal Graph CNN for materials chemistry, including crystal data processing and graph-network training.

View merged PR #977

Contact

Research collaboration and contact

State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · Beijing, China

yi.chen@nlpr.ia.ac.cn