Today we’re joined by Markus Nagel, research scientist at Qualcomm AI Research, who helps us kick off our coverage of NeurIPS 2023. In our conversation with Markus, we cover his accepted papers at the conference, along with other work presented by Qualcomm AI Research scientists. Markus’ first paper, Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing, focuses on tackling activation quantization issues introduced by the attention mechanism and how to solve them. We also discuss Pruning vs Quantization: Which is Better?, which focuses on comparing the effectiveness of these two methods in achieving model weight compression. Additional papers discussed focus on topics like using scalarization in multitask and multidomain learning to improve training and inference, using diffusion models for a sequence of state models and actions, applying geometric algebra with equivariance to transformers, and applying a deductive verification of chain of thought reasoning performed by LLMs.
The complete show notes for this episode can be found at twimlai.com/go/663.
Stable Diffusion & Generative AI with Emad Mostaque - #604
Exploring Large Language Models with ChatGPT - #603
Accelerating Intelligence with AI-Generating Algorithms with Jeff Clune - #602
Programmatic Labeling and Data Scaling for Autonomous Commercial Aviation with Cedric Cocaud - #601
Engineering Production NLP Systems at T-Mobile with Heather Nolis - #600
Sim2Real and Optimus, the Humanoid Robot with Ken Goldberg - #599
The Evolution of the NLP Landscape with Oren Etzioni - #598
Live from TWIMLcon! The Great MLOps Debate: End-to-End ML Platforms vs Specialized Tools - #597
Live from TWIMLcon! You're not Facebook. Architecting MLOps for B2B Use Cases with Jacopo Tagliabue - #596
Building Foundational ML Platforms with Kubernetes and Kubeflow with Ali Rodell - #595
AI-Powered Peer Programming with Vasi Philomin - #594
The Top 10 Reasons to Register for TWIMLcon: AI Platforms 2022!
Applied AI/ML Research at PayPal with Vidyut Naware - #593
Assessing Data Quality at Shopify with Wendy Foster - #592
Transformers for Tabular Data at Capital One with Bayan Bruss - #591
Understanding Collective Insect Communication with ML, w/ Orit Peleg - #590
Multimodal, Multi-Lingual NLP at Hugging Face with John Bohannon and Douwe Kiela - #589
Synthetic Data Generation for Robotics with Bill Vass - #588
Multi-Device, Multi-Use-Case Optimization with Jeff Gehlhaar - #587
Causal Conceptions of Fairness and their Consequences with Sharad Goel - #586
Create your
podcast in
minutes
It is Free
20/20
The Dropout
Ten Percent Happier with Dan Harris
World News Tonight with David Muir
NEJM This Week