You are viewing content from a past/completed conference.
Improving Meta Generative Ad Text using Reinforcement Learning
Abstract
Reinforcement Learning with Performance Feedback (RLPF) unlocks a new way of turning generic GenAI models into customized models fine-tuned for specific tasks. This approach is especially powerful when combined with in-house data and performance metrics. In this talk we highlight the application of RLPF to the ad text generation system on the Facebook platform.
The presentation covers the core technical components required for production RLHF systems: preference data collection methodologies, reward model training approaches, and policy optimization techniques that maintain stability in production environments. We'll explore the theoretical foundations underlying these systems and how they translate into practical engineering solutions.
From the same track
Session
Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash
Tuesday Nov 18 / 03:55PM PST
In this talk, we’ll walk through how DoorDash is redefining personalization by tightly integrating cutting-edge large language models (LLMs) with deep learning architectures such as Two-Tower Embeddings (TTE) and Multi-Task Multi-Label (MTML) models.
Sudeep Das
Head of Machine Learning and Artificial Intelligence, New Business Verticals @DoorDash, Previously Machine Learning Lead @Netflix, 15+ Years in Machine Learning
Pradeep Muthukrishnan
Head of Growth for New Business Verticals @DoorDash, Previously Founder & CEO @TrustedFor, 15+ Years in Machine Learning
Dynamic Moments: Weaving LLMs into Deep Personalization at DoorDash
Session
AI Agents
From Content to Agents: Scaling LLM Post-Training Through Real-World Applications and Simulation
Tuesday Nov 18 / 02:45PM PST
This talk presents a comprehensive journey through modern AI post-training techniques, from Pinterest's production-scale content discovery systems to enterprise agent training through Veris AI’s simulation.
Faye Zhang
Staff Software Engineer @Pinterest, Tech Lead on GenAI Search Traffic Projects, Speaker, Expert in AI/ML with a Strong Background in Large Distributed System
Andi Partovi
Co-Founder @Veris AI, Making AI Agents World-Ready
From Content to Agents: Scaling LLM Post-Training Through Real-World Applications and Simulation
Session
AI/ML
Automating the Web With MCP: Infra That Doesn’t Break
Tuesday Nov 18 / 05:05PM PST
AI agents are only as strong as the infrastructure beneath them. In this talk, we’ll walk through the architecture behind Browserbase’s model context protocol (MCP), built to support stateful browser automation at scale.
Paul Klein
Founder @Browserbase, previously Director of Self-Service & Engineering Manager @Mux, Co-Founder & CTO @Stream Club, Technical Lead @Twilio Inc.
Automating the Web With MCP: Infra That Doesn’t Break
Session
Engineering AI for Creativity and Curiosity on Mobile
Tuesday Nov 18 / 11:45AM PST
This talk shares practical lessons from building production-grade AI for creativity and curiosity on mobile devices.
Bhavuk Jain
Tech Lead @Google
Engineering AI for Creativity and Curiosity on Mobile
Video is not available
Slides are not available
