It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
- Chen Chen
- Ruizhe Li
- et al.
- 2024
- ICLR 2024
Bio
Pin-Yu Chen is a Principal Research Staff Member of the Trusted AI Group, IBM Thomas J. Watson Research Center. He is also the Chief Scientist of RPI-IBM AI Research Collaboration program and a PI of MIT-IBM Watson AI Lab projects.
His recent research focuses on adversarial machine learning of neural networks for robustness and safety, and more broadly, making machine learning trustworthy.
♦ Pin-Yu's research highlights can be found from HERE
♦ Pin-Yu is open to collaboration with highly motivated researchers!
Pin-Yu received his Ph.D. degree in electrical engineering and computer science (EECS) and M.A. degree in Statistics from the University of Michigan Ann Arbor in 2016, under the supervision of Prof. Alfred Hero.
♦ Please refer to his personal webpage for more details - www.pinyuchen.com
Publications
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
- Yu-Lin Tsai
- Chia-yi Hsu
- et al.
- 2024
- ICLR 2024
The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
- Yan Liu
- Yu Liu
- et al.
- 2024
- ICLR 2024
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
- Ming Jin
- Shiyu Wang
- et al.
- 2024
- ICLR 2024
AutoVP: An Automated Visual Prompting Framework and Benchmark
- Hsi-ai Tsao
- Lei Hsiung
- et al.
- 2024
- ICLR 2024
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
- Yuchen Hu
- Chen Chen
- et al.
- 2024
- ICLR 2024
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
- Ming-yu Chung
- Sheng-yen Chou
- et al.
- 2024
- ICLR 2024
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
- Xiangyu Qi
- Yi Zeng
- et al.
- 2024
- ICLR 2024
MulBERRY: Enabling Bit-Error Robustness for Energy-Efficient Multi-Agent Autonomous Systems
- Zishen Wan
- Nandhini Chandramoorthy
- et al.
- 2024
- ASPLOS 2024
DDI-CoCo: A Dataset For Understanding The Effect Of Color Contrast In Machine-Assisted Skin Disease Detection
- Ming-chang Chiu
- Yingfei Wang
- et al.
- 2024
- ICASSP 2024
Patents
- 25 Jan 2024
- CN
- ZL 202010055649.9
- 22 Jan 2024
- US
- 11880765
- 25 Dec 2023
- US
- 11853702
- 25 Dec 2023
- US
- 11853713
- 04 Dec 2023
- US
- 11836256
- 17 Aug 2023
- CN
- ZL201910306083.X
- 10 Aug 2023
- CN
- ZL202010020033.8
- 19 Jul 2023
- JP
- 7316722
- 01 May 2023
- US
- 11640532
- 10 Apr 2023
- US
- 11625487
Blog posts
What is red teaming for generative AI?
ExplainerKim Martineau- Adversarial Robustness and Privacy
- AI
- AI Testing
- Fairness, Accountability, Transparency
- Foundation Models
- Natural Language Processing
- Security
- Trustworthy AI
Accelerating molecular optimization with AI
Deep DivePayel Das, Samuel Hoffman, Vijil Chenthamarakshan, Kahini Wadhawan, and Pin-Yu Chen11 minute read- Accelerated Discovery
- Generative AI
- Healthcare
- Materials Discovery
- Trustworthy AI
- Trustworthy Generation
Securing AI systems with adversarial robustness
Deep DivePin-Yu Chen8 minute read- Adversarial Robustness and Privacy
- AI
- Data and AI Security
Preparing deep learning for the real world – on a wide scale
ResearchPin-Yu Chen3 minute read- Adversarial Robustness and Privacy
- AI
- Machine Learning
- Trustworthy AI
Top collaborators
KS
Karthik Swaminathan
Senior Research Scientist, Efficient and Resilient Systems