Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
- Zhiqing Sun
- Longhui Yu
- et al.
- 2024
- NeurIPS 2024
Bio
Yikang Shen obtained a Ph.D. in Mila lab at the University of Montreal and received the ICLR 2019 best paper award. His research lies in natural language processing and machine learning, focusing on the fundamental mechanisms that allow deep learning methods to understand the latent structure of human language and model its compositional phenomenons. He has over 20 publications in top-tier conferences and journals, including ACL, EMNLP, NAACL, NeurIPS, ICLR, and AAAI.
Publications
LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
- Chen-chia Chang
- Yikang Shen
- et al.
- 2024
- ICML 2024
Scaling Granite Code Models to 128K Context
- Matthew Stallone
- Vaibhav Saxena
- et al.
- 2024
- arXiv
Granite code models: A family of open foundation models for code intelligence
- Mayank Mishra
- Matthew Stallone
- et al.
- 2024
- arXiv
Visual Chain-of-Thought Prompting for Knowledge-based Visual Reasoning
- Zhenfang Chen
- Qinhong Zhou
- et al.
- 2024
- AAAI 2024
Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
- Zhiqing Sun
- Yikang Shen
- et al.
- 2023
- NeurIPS 2023
Adaptive Online Replanning with Diffusion Models
- Siyuan Zhou
- Yilun Du
- et al.
- 2023
- NeurIPS 2023
Learning Task Decomposition with Order-Memory Policy Network
- Yuchen Lu
- Yikang Shen
- et al.
- 2021
- ICLR 2021
Projects
Dromedary
Training language models to better follow user intentions and make them more truthful
Top collaborators
DC
David D. Cox
VP, AI Models; IBM Director, MIT-IBM Watson AI Lab
ND
Nirmit Desai
Director, Data for AI Models
RP
Ruchir Puri
Chief Scientist, IBM Research; IBM Fellow; Vice President, IBM Technology & Technical Community
ZC
