Generative AI 2.0 Foundations and Beyond

Generative AI 2.0 Foundations, AGI, Applications, and Beyond

The goal of this cluster is to develop a fundamental algorithmic and system framework for building and deploying orders of magnitude complex GenAI systems, compared to that of today, without creating a compute and energy crisis.

Cluster MembersGenAI

  • Lead PI: Anshumali Shrivastava (Computer Science, Electrical & Computer Engineering, Statistics, Rice University)
  • Richard Baraniuk (Electrical & Computer Engineering, Statistics, Computer Science, Rice University)
  • Ankit Patel (Electrical & Computer Engineering, Rice University; Neuroscience, Baylor College of Medicine)

Collaborators

Selected Publications

Cluster faculty highlighted in bold.

  • Tianyi Zhang, Jonah Wonkyu Yi, Zhaozhuo Xu, Anshumali Shrivastava. "KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization" [To appear]. Neural Information Processing Systems (NeurIPS) 2024.
  • Tianyi Zhang, Jonah Wonkyu Yi, Bowen Yao, Zhaozhuo Xu, Anshumali Shrivastava. "NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention" [To appear]. Neural Information Processing Systems (NeurIPS) 2023.
  • Aditya Desai, Kimia Saedi, Apoorv Walia, Jihyeong Lee, Keren Zhou, Anshumali Shrivastava. "Accelerating Inference with Fast and Expressive Sketch Structured Transform" [To appear]. Neural Information Processing Systems (NeurIPS) 2024.
  • Zhaozhuo Xu, Zirui Liu, Beidi Chen, Shaochen Zhong, Yuxin Tang, Jue WANG, Kaixiong Zhou, Xia Hu, Anshumali Shrivastava. "Soft Prompt Recovers Compressed LLMs, Transferably" [pdf coming soon]. International Conference on Machine Learning (ICML) 2024.
  • Aditya Desai and Anshumali Shrivastava. "In defense of parameter sharing for model-compression." International Conference on Learning Representations (ICLR) 2024.

Spin-Offs

Updates will be posted to the following web page, managed by the cluster: https://www.cs.rice.edu/~as143/GenAI2.O/index.html