AI Journal Club ft. Song Bian (NVIDIA)

Join Workato's AI Journal Club series—we're bringing together the best AI researchers to share papers and exchange perspectives on how AI research is shaping real world systems.

5:30–6:00 PM: Check-in and registration6:00–6:15 PM: Welcome to Workato  6:15–6:45 PM: Talk by Song Bian, NVIDIA Research6:45–7:00 PM: Q&A7:00–8:00 PM: Networking

Please arrive by 6:00 PM. We politely ask that attendees arrive by this time out of respect for our speaker.

Featured Speaker

Song Bian is a Research Scientist at NVIDIA Research. He earned his Ph.D. from the University of Wisconsin-Madison, where he was advised by Prof. Shivaram Venkataraman. His research focuses on building efficient training systems and designing large language models optimized for efficient inference.

Scaling Laws Meet Model Architecture: Toward Inference-Efficient Large Language Models

Scaling the number of parameters and the size of training data has proven to be an effective strategy for improving large language model (LLM) performance. Yet, as these models grow increasingly powerful and widely deployed, the cost of inference has become a pressing concern. In view of this, Song asks the following question: Can we explicitly capture the trade-off between inference efficiency and accuracy of large language models?In this talk, Song will demonstrate that the architecture of large language models significantly affects their inference efficiency. Motivated by this observation, we propose a conditional scaling law that extends the Chinchilla framework by incorporating architectural factors. They also introduce a search framework for discovering model architectures that are both inference-efficient and accurate. Finally, using the proposed scaling law and search framework, they predict optimized model architectures that outperform LLaMA‑3.2 in both accuracy and inference throughput, under the same training budget.

Who Should Attend

AI Researchers and practitioners working at the intersection of AI research and real world systems.​About Workato

Workato is the Enterprise MCP company, providing the connective layer that gives AI agents secure, governed access to enterprise systems and data. Built on a decade of integration expertise spanning 14,000+ applications, Workato's platform enables organizations to move from simple automation to agentic AI that can reason, act, and orchestrate work across the entire business. You can explore Workato's end-to-end capabilities in our developer sandbox here.