Defense
Scale is a sophisticated technical partner that provides artificial intelligence and machine learning solutions for critical U.S. government platforms, sensor systems, and data types. We set the commercial standard, lead the market, and apply those capabilities to our federal work.
Webinar: Beyond the Hype: Inside the AI Black Box for Enterprises
Join Scale AI researchers as they present their NeurIPS 2024 main track paper, Learning Goal-Conditioned Representations for Language Reward Models, introducing a novel approach to improving LLM alignment. This technical session will explore how goal-conditioned representations can enhance reward modeling and significantly reduce computational costs. Through a detailed examination of the methodology and results, we'll demonstrate how this approach achieves substantial improvements in both model performance and decoding efficiency. The presentation will be followed by an in-depth discussion of practical implementation considerations and future research directions.Key takeaways
- Discover a novel architecture for reward modeling that achieves large improvements on both math and natural language tasks.
- Learn how to implement goal-conditioned rewards into post-training and decoding pipelines to filter 55% of tokens without accuracy loss, significantly reducing computational costs.
- Explore how this research advances LLM alignment and control, setting new directions for developing more reliable, efficient, and interpretable AI systems.
Meet the Speakers
About Sean Hendryx | Speaker
Jessica Zhu is the tech lead of Scale's Generative AI Growth team. She has spent the past few years working on various products at the forefront of AI, including document processing, computer vision, and LLM infrastructure. In her free time she enjoys traveling, boxing, and playing board games.
About Vaskar Nath | Speaker
Jessica Zhu is the tech lead of Scale's Generative AI Growth team. She has spent the past few years working on various products at the forefront of AI, including document processing, computer vision, and LLM infrastructure. In her free time she enjoys traveling, boxing, and playing board games.
About Jessica Zhu | Moderator
Jessica Zhu is the tech lead of Scale's Generative AI Growth team. She has spent the past few years working on various products at the forefront of AI, including document processing, computer vision, and LLM infrastructure. In her free time she enjoys traveling, boxing, and playing board games.