Junxiao (Cody) Wang
 |
Postdoctoral Fellow |
About Me
I'm broadly interested in artificial intelligence system with a special focus on generative AI, distributed machine learning, AI security, privacy and interpretability.If you're interested in a research internship (remote), I welcome applicants of all levels (PhD/MSc/BSc). Don't hesitate to send me an email!
Recent Activities
Reviewer, IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025, 2024.11
Reviewer, International Conference on Artificial Intelligence and Statistics (AISTATS) 2025, 2024.09
Reviewer, International Joint Conference on Artificial Intelligence (IJCAI) 2024, 2024.03
Reviewer, European Conference on Computer Vision (ECCV) 2024, 2024.01
Reviewer, International Conference on Artificial Intelligence and Statistics (AISTATS) 2024, 2023.09
Reviewer, International Conference on Computer Vision (ICCV) 2023, 2023.05
Postdoctoral Fellow, working with Assistant Prof. Di Wang, at Division of Computer, Electrical and Mathematical Sciences and Engineering (CEMSE), King Abdullah University of Science and Technology (KAUST), 2023.02
Invited Talk, Ritsumeikan University and CCF Dalian International Seminar, 2022.03
Postdoctoral Fellow, working with IEEE Fellow, Prof. Song Guo, at Department of Computing (COMP), The Hong Kong Polytechnic University (PolyU), 2021.03
Visitor, working with Prof. Steve Uhlig, at School of Electronic Engineering and Computer Science (EECS), Queen Mary University of London (QMUL), 2018.09
PhD Candidate, supervised by IEEE Fellow, Prof. Keqiu Li, at School of Computer Science and Technology (CS), Dalian University of Technology (DUT), 2016.09
News
Oct 2024 Our paper entitled "ZO-Offloading: Fine-Tuning LLMs with 100 Billion Parameters on a Single GPU" was accepted by Workshop on Adaptive Foundation Models (AFM) of NeurIPS2024.
Oct 2024 Our paper entitled "FlashDP: Memory-Efficient and High-Throughput DP-SGD Training for Large Language Models" was accepted by Workshop on Adaptive Foundation Models (AFM) of NeurIPS2024.
Sep 2024 Our paper entitled "Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing" was accepted by NeurIPS2024.
Jul 2024 Our paper entitled "Explore and Cure: Unveiling Sample Effectiveness with Context-Aware Federated Prompt Tuning" was accepted by IEEE Transactions on Mobile Computing.
May 2024 Our paper entitled "Autonomous Workflow for Multimodal Fine-Grained Training Assistants Towards Mixed Reality" was accepted by Findings of ACL2024.
Apr 2024 Our paper entitled "Exploring Amplified Heterogeneity Arising from Heavy-Tailed Distributions in Federated Learning" was accepted by IEEE Transactions on Mobile Computing.
Apr 2024 Our paper entitled "Towards Light Adaptation of Large Language Models For Personal Hardware" was accepted by Workshop on Edge and Mobile Foundation Models (EdgeFM) of MobiSys2024.
Apr 2024 Our paper entitled "Rethinking Personalized Client Collaboration in Federated Learning" was accepted by IEEE Transactions on Mobile Computing.
Jan 2024 Our paper entitled "Faithful Vision-Language Interpretation via Concept Bottleneck Models" was accepted by ICLR2024.
Sep 2023 Our paper entitled "Towards Test-Time Refusals via Concept Negation" was accepted by NeurIPS2023.
Aug 2023 Our paper entitled "PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models — Federated Learning in Age of Foundation Model" was accepted by IEEE Transactions on Mobile Computing.
Jun 2023 Our paper entitled "On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directions" was available in arxiv.org.
May 2023 Our paper entitled "Investigating Trojan Attacks on Pre-trained Language Model-powered Database Middleware" was accepted by KDD2023.
Mar 2023 Our paper entitled "DualMix: Unleashing the Potential of Data Augmentation for Online Class-Incremental Learning" was available in arxiv.org.
Feb 2023 Our paper entitled "PMR: Prototypical Modal Rebalance for Multimodal Learning" was accepted by CVPR2023.
Jan 2023 Our paper entitled "pFedPrompt: Learning Personalized Prompt for Vision-Language Models in Federated Learning" was accepted by WWW2023.
Nov 2022 Our paper entitled "Demystify Self-Attention in Vision Transformers from a Semantic Perspective: Analysis and Application" was available in arxiv.org.
Nov 2022 Our paper entitled "PMR: Prototypical Modal Rebalance for Multimodal Learning" was available in arxiv.org.
Nov 2022 Our paper entitled "FedTune: A Deep Dive into Efficient Federated Fine-Tuning with Pre-trained Transformers" was available in arxiv.org.
Aug 2022 Our paper entitled "PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models — Federated Learning in Age of Foundation Model" was available in arxiv.org.
Aug 2022 Our paper entitled "Federated Unlearning: Guarantee the Right of Clients to Forget" was accepted by IEEE Network.
Apr 2022 Our paper entitled "Efficient Integrity Authentication Scheme for Large-scale RFID Systems" was accepted by IEEE Transactions on Mobile Computing.
Apr 2022 Our paper entitled "A Survey on Gradient Inversion: Attacks, Defenses and Future Directions" was accepted by IJCAI2022.
Feb 2022 Our paper entitled "Vertical Machine Unlearning: Selectively Removing Sensitive Information From Latent Feature Space" was available in arxiv.org.
Jan 2022 Our paper entitled "Federated Unlearning via Class-Discriminative Pruning" was accepted by WWW2022.
Dec 2021 Our paper entitled "Protect Privacy from Gradient Leakage Attack in Federated Learning" was accepted by INFOCOM2022.
Oct 2021 Our paper entitled "Federated Unlearning via Class-Discriminative Pruning" was available in arxiv.org.
Feb 2020 Our paper entitled "Click-UP: Toward the Software Upgrade of Click-Based Modular Network Function" was accepted by IEEE Systems Journal.
Jun 2018 Our paper entitled "CLICK-UP: Towards Software Upgrades of Click-driven Stateful Network Elements" was accepted by Demo track of SIGCOMM2018.