Publications
Publications & Preprints
\(*\) equal contribution.
2024
- ICMLKIVI: A Tuning-Free Asymmetric 2bit Quantization for KV CachearXiv preprint arXiv:2402.02750, 2024
- arXivLoRA-as-an-Attack! Piercing LLM Safety Under The Share-and-Play ScenarioarXiv preprint arXiv:2403.00108, 2024
2023
- NeurIPSSetting the trap: Capturing and defeating backdoors in pretrained language models through honeypotsAdvances in Neural Information Processing Systems, 2023
- AMIALarge language models for healthcare data augmentation: An example on patient-trial matchingIn AMIA Annual Symposium Proceedings, 2023
- AMIATowards fair patient-trial matching via patient-criterion level fairness constraintIn AMIA Annual Symposium Proceedings, 2023
- ACM-BCBCan Attention Be Used to Explain EHR-Based Mortality Prediction Tasks: A Case Study on Hemorrhagic StrokeIn Proceedings of the 14th ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics, 2023
- DACRobust tickets can transfer better: Drawing more transferable subnetworks in transfer learningIn 2023 60th ACM/IEEE Design Automation Conference (DAC), 2023
- DACNetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep GiantsIn 2023 60th ACM/IEEE Design Automation Conference (DAC), 2023
- IEEE MicroEyeCoD: Eye Tracking System Acceleration via FlatCam-based Algorithm&Hardware Co-DesignIEEE Micro, 2023
- ISCAGen-NeRF: Efficient and Generalizable Neural Radiance Fields via Algorithm-Hardware Co-DesignIn Proceedings of the 50th Annual International Symposium on Computer Architecture, 2023
- ICASSPERSAM: Neural Architecture Search for Energy-Efficient and Real-Time Social Ambiance MeasurementIn ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2023
2022
- ICMLDepthShrinker: a new compression paradigm towards boosting real-hardware efficiency of compact neural networksIn International Conference on Machine Learning, 2022
- ISCAEyeCoD: eye tracking system acceleration via flatcam-based algorithm & accelerator co-designIn Proceedings of the 49th Annual International Symposium on Computer Architecture, 2022