About Me

I am currently a Boya Postdoctoral Researcher at Peking University, (since Jul. 2024), working with Prof. Yonghong Tian (NSFC Distinguished Young Scholar).

I received my Ph.D. in Pattern Recognition and Intelligent Systems from the Shenyang Institute of Automation, Chinese Academy of Sciences (State Key Laboratory of Robotics) in June 2024, under the supervision of Prof. Yang Cong (recipient of the National Science Fund for Distinguished Young Scholars). During Sep. 2022 - Sep. 2023, I was a visiting Ph.D. student (supported by CSC) at National Center for Computer Vision Research (CVC) (CVC), Universitat Autònoma de Barcelona, Spain, working with Prof. Joost van de Weijer (Top 2% AI researchers in 2021).

Research Interests

Continual Learning, Parameter-Efficient Fine-Tuning, Computer Vision (2D/3D), AI4Science, Embodied AI

Academic Services

Reviewer for TPAMI, TRO, TMM, TCSVT, TNNLS, CVPR, ICCV, ICLR, NeurIPS, ICML, AAAI, ECCV

News

2026.03 ✨ BioProBench Data Splits Released! Official Train/Test splits for PQA, ORD, ERR, GEN, REA tasks now available.
2026.03 🔥 BioProAgent now live on AI4S LAB! Try autonomous wet-lab experiment ordering.
2026.03 🎉 BioProAgent accepted to ICLR 2026 LLA Workshop!
2026.03 📄 BioProAgent preprint available on arXiv!
2025.12 🎉 Awarded the 2025 Shenzhen Outstanding Postdoctoral Fellow (50 recipients per year) !
2025.11 Paper on Active Learning accepted to Top Journal IJCV!
2025.01 Oral Paper on LLM Safety accepted to AAAI 2026!
2025.01 Paper on MLLM Reasoning accepted to AAAI 2026!
2024.12 Paper accepted to ICLR 2025!
2024.12 Oral Paper accepted to COLING 2025!
2024.11 Granted China Postdoctoral Science Foundation (76th batch)!
2024.07 Paper accepted to ECCV 2024!
2024.06 🎉 Awarded Postdoctoral Innovative Talents Support Program (A)!
2024.02 Paper accepted to CVPR 2024!
2023.09 Paper accepted to NeurIPS 2023!
2023.07 Paper accepted to ICCV 2023!
2023.07 🏆 Won Innovation Award & Third Place at ICCV 2023 VCL Workshop!

Latest Research

Recent preprints, demos, and ongoing projects

BioProAgent Workshop

BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning

A neuro-symbolic framework that anchors LLM planning in deterministic Finite State Machines (FSM) for reliable wet-lab automation. Achieves 95.6% physical compliance for irreversible scientific experiments.

  • State-Augmented Planning: Design-Verify-Rectify workflow ensuring hardware compliance
  • Semantic Symbol Grounding: 6x token reduction through symbolic abstraction
  • 95.6% physical compliance vs 21.0% for ReAct on BioProBench
Yuyang Liu, et al. · 2026
arXiv Code Project
Platform Demo

AI4S LAB: The World's First "One-Stop" Digital Intelligent Life Science Research Platform

AI4S LAB deeply integrates computing power, data, models, and experiments. The platform achieves a closed-loop process: "theoretical prediction → experimental design → automated execution → data analysis".

  • 15+ professional datasets & 22 sets of high-throughput equipment
  • 30x efficiency improvement over traditional methods
  • Natural language dialogue for AI-driven experimental design
Yuyang Liu, et al. · 2025
Project
BioProBench Preprint

BioProBench: Comprehensive Benchmark for Biological Protocol Understanding

We introduce BioProBench – the first large-scale, multi-task benchmark for biological protocol understanding & reasoning, accelerating LLMs that truly understand lab procedures.

  • 27K real-world protocols
  • 556K instances across 5 core tasks
  • Protocol QA, Step Ordering, Error Correction, Generation & Reasoning
Yuyang Liu, et al. · 2025
arXiv Code
Continual Learning for VLMs Survey Survey

Continual Learning for Vision-Language Models: A Comprehensive Survey

The first systematic review of continual learning in Vision-Language Models, addressing how VLMs can learn efficiently without catastrophic forgetting while remaining parameter-efficient.

  • Three Core Challenges identified
  • Novel challenge-driven taxonomy proposed
  • Comprehensive analysis of protocols & metrics
Yuyang Liu, et al. · 2025
arXiv GitHub

Selected Publications

Full list on Google Scholar →
* Equal contribution  ·  † Corresponding author

2026
IJCV

Evidence Conflict Sampling for Open-set Active Learning

K Ning*, H Ke*, J Yao, Y Liu†, Y Tian, L Yuan†

International Journal of Computer Vision (IJCV), 2026

AAAI Oral

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin

S Yang, Q Zhang, Y Liu†, Y Huang, X Jia, K Ning, J Yao, J Wang, H Dai, Y Song, L Yuan†

AAAI Conference on Artificial Intelligence (AAAI), 2026

AAAI

Look-Back: Implicit Visual Re-focusing in MLLM Reasoning

S Yang, Y Niu, Y Liu†, Y Ye, B Lin, L Yuan†

AAAI Conference on Artificial Intelligence (AAAI), 2026

2025
ICLR

PiCO: Peer Review in LLMs based on the Consistency Optimization

K Ning, S Yang, Y Liu†, J Yao, Z Liu, Y Tian, Y Song, L Yuan†

International Conference on Learning Representations (ICLR), 2025

COLING Oral

Is Parameter Collision Hindering Continual Learning in LLMs?

S Yang, K Ning, Y Liu†, J Yao, Y Tian, Y Song, L Yuan†

International Conference on Computational Linguistics (COLING), 2025

ICME

CASA: Class-Agnostic Shared Attributes in Vision-Language Models for Efficient Incremental Object Detection

M Guo*, Y Liu*†, Z Lin, P Peng, Y Tian†

IEEE International Conference on Multimedia and Expo (ICME), 2025

IEEE TAI

ProLLaMA: A Protein Language Model for Multi-Task Protein Language Processing

L Lv, Z Lin, H Li, Y Liu, J Cui, C Chen, L Yuan†, Y Tian†

IEEE Transactions on Artificial Intelligence, 2025

2024
ECCV

Cs²K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation

W Cong, Y Cong, Y Liu, G Sun

European Conference on Computer Vision (ECCV), 2024

CVPR

Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning

D Goswami, A Soutif-Cormerais, Y Liu†, S Kamath, B Twardowski, J van de Weijer

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024

2023
NeurIPS

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

D Goswami, Y Liu†, B Twardowski, J van de Weijer

Advances in Neural Information Processing Systems (NeurIPS), 2023

ICCV

Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection

Y Liu, Y Cong, D Goswami, X Liu, J van de Weijer

IEEE/CVF International Conference on Computer Vision (ICCV), 2023

IEEE TCSVT

Self-paced Weight Consolidation for Continual Learning

W Cong, Y Cong, G Sun, Y Liu, J Dong

IEEE Transactions on Circuits and Systems for Video Technology, 2023

IEEE TNNLS

Open-ended Online Learning for Autonomous Visual Perception

H Yu, Y Cong, G Sun, D Hou, Y Liu, J Dong

IEEE Transactions on Neural Networks and Learning Systems, 2023

2022
IEEE TCSVT

Lifelong Visual-Tactile Spectral Clustering for Robotic Object Perception

Y Liu, Y Cong, G Sun, Z Ding

IEEE Transactions on Circuits and Systems for Video Technology, 2022

2021 & Earlier
IEEE TPAMI

What and How: Generalized Lifelong Spectral Clustering via Dual Memory

G Sun, Y Cong, J Dong, Y Liu, Z Ding, H Yu

IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021

IEEE TIP

L3DOC: Lifelong 3D Object Classification

Y Liu, Y Cong, G Sun, T Zhang, J Dong, H Liu

IEEE Transactions on Image Processing, 2021

AAAI

Generative Partial Visual-Tactile Fused Object Clustering

T Zhang, Y Cong, G Sun, J Dong, Y Liu, Z Ding

AAAI Conference on Artificial Intelligence, 2021

ECCV

CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation

J Dong, Y Cong, G Sun, Y Liu, X Xu

European Conference on Computer Vision (ECCV), 2020

Research Projects

Principal Investigator

Postdoctoral Innovative Talents Support Program (Grade A)

Research on Embodied Intelligence Learning Methods for Scientific Experiments Driven by Large Models

China Postdoctoral Science Foundation 2024.06 - Present

Principal Investigator

China Postdoctoral Science Foundation (76th Batch)

Research on Efficient Continual Learning Methods for Pre-trained Foundation Models

Postdoctoral Science Foundation 2024.11 - Present

Key Member

Shenzhen Key Basic Research Project

Research on AIGC Content Tampering Detection and Localization Methods

Shenzhen Science and Technology 2025.03 - 2028.03

Participant

National Key R&D Program of China

Dexterous Manipulation Skill Learning Platform Verification

Ministry of Science and Technology 2021.11 - 2025.12

Honors & Awards

2025

Shenzhen Outstanding Postdoctoral Fellow (50 recipients/year)

Shenzhen Postdoctoral Development Promotion Association

2024

Postdoctoral Innovative Talents Support Program (Grade A)

China Postdoctoral Science Foundation · Top national postdoc talent program

2023

Innovation Award & Third Place

ICCV 2023 Visual Continual Learning Workshop Challenge

2022

National Scholarship & CSC Scholarship

Ministry of Education & China Scholarship Council

2019-20

First-Class Academic Scholarship

University of Chinese Academy of Sciences

2015

National First Prize

National Undergraduate Electronics Design Contest

Visitor Statistics

Flag Counter