Zhiyan Li（李芷妍）

Hi 👋 I am Zhiyan Li, a senior undergraduate in ACM Honors Class of Shanghai Jiao Tong University, majoring in Computer Science. Currently, I'm a visiting student at Harvard University, supervised by Prof. Yilun Du and Dr. Mengyu Wang, and actively working with Weirui Ye and Kaichen Zhou at MIT. Previously, I worked at MVIG-RHOS lab in Shanghai Jiao Tong University, co-advised by Prof. Cewu Lu and Prof. Yonglu Li.

My research interests include multimodal perception in robot learning (especially tactile modality), lifelong learning for robotics and test-time adaptation using steering policies and agentic methods.

I am seeking a PhD position in Fall 2027.

GitHub  /  Email  /  CV  / 

profile photo

News

Research and Projects
GEMA method overview: historical evidence is transformed into task-specific references for robot control
GEMA: Generative Memory for Robotic Manipulation
Zhiyan Li, Pembe Gizem Ozdil, Ben Zandonati, Ruojin Cai, Hang Le, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Weirui Ye†, Yilun Du†
Accepted by CoRL 2026 Workshop on Memory for Robot Foundation Models  ·  † Equal supervision
SteerAct method overview: offline sparse-feature selection and online temporally gated steering
SteerAct: Unlocking Action Models through Few-Shot Temporal Steering
Kaichen Zhou*, Zhiyan Li*, Chongkai Gao, Yuhan Wang, Wenlong Huang, Maggie Wang, Fangneng Zhan, Manling Li, Qianqian Wang, Mac Schwager, Zhuang Liu, Li Fei-Fei, Mengyu Wang†, Paul Pu Liang†
Under ICLR 2027 Review  ·  * Equal contribution; † Equal supervision
arXiv  /  web  /  code
VISTA multimodal baseline: RGB frames and sensor streams are fused with a vision-language model for assistive guidance
VISTA: A Multimodal Egocentric Benchmark for Goal-Oriented Perception and Assistance to Blind and Low-Vision Users
Noé Mosca*, Mohamed Rayan Barhdadi*, Muhammad Hamza*, Joshua Yeh*, Suryodaya Bikram Shahi*, Zhiyan Li, Selim-Antoine Lali, Weiyue Li, HASAN KURBAN, Erchin Serpedin, Gang Luo, Yue Zhang, Minghan Li, Mengyu Wang
Under ICLR 2027 Review  ·  * Equal contribution
arXiv
TactiLDM method: visual-text-tactile contrastive learning followed by vision- and text-conditioned latent diffusion training
TactiLDM for VLA: Learning Unified Visual-Text-Tactile Representations to Empower Vision-Language-Action Policies
Zhiyan Li*, Hantao Jiang*
web  /  paper  /  code
Decoformer: Enhancing CrossFormer with DLinear for Long-Term Forecasting
Core researcher  ·  May 2025
code  /  project paper

Replaced CrossFormer’s cross-time attention stage with DLinear decomposition for long-term forecasting, achieving 20% higher accuracy and 1.25× faster inference.
MxCompiler
Core researcher  ·  Oct. 2024
code

Implemented a Java compiler for the Mx language with semantic analysis, RISC-V code generation, and optimization passes including Mem2Reg, dead code elimination, sparse conditional constant propagation, and global-to-local variable promotion.
RISC-V CPU
Core researcher  ·  Oct. 2024
code  /  simulator

Designed a five-stage RV32IC processor in Verilog with Tomasulo-based out-of-order execution, and validated it through simulation and FPGA deployment.

Education
Harvard University logo Harvard University, Visiting Student, Present
Tsinghua University purple seal Tsinghua University, Visiting Student at the Institute for Interdisciplinary Information Sciences (IIIS), June–July 2025
Shanghai Jiao Tong University logo Shanghai Jiao Tong University, B.S. in Computer Science, 2023-2027 (Expected)

Awards and Scholarships

  • Foresight-Sequoia Talent Development Fund (5 Outstanding Students in ACM Class per year), 2025
  • Zhiyuan Honors Scholarship (top 5% students in SJTU annually), 2023,2024,2025
  • Shanghai Jiao Tong University Merit Scholarship, 2025
  • Provincial Second Prize , China Undergraduate Mathematical Contest in Modeling, 2024
  • Provincial Second Prize , The Chinese Mathematics Competition, 2024
  • Silver Medal, National Second Prize , 39th Chinese Physics Olympiad, 2022

Credits to Jon Barron for the website design.