Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)

Channel:
United States Simons Institute for the Theory of Computing
Subscribers:
68,700
Published on ● Video Link: https://www.youtube.com/watch?v=oqOBYOx3sHE


Duration: 0:00
280 views
0

Sean Welleck (Carnegie Mellon University)
https://simons.berkeley.edu/talks/sean-welleck-carnegie-mellon-university-2024-11-19
Joint IFML/MPG Symposium



Other Videos By Simons Institute for the Theory of Computing


2024-12-16Testing Noise Assumptions of Learning Algorithms
2024-12-05Generalization insights from actual cognition
2024-12-05Generalization via analogy in young children and Large Models.
2024-12-04Understanding the abilities of AI systems: Memorization, generalization, and points in between
2024-12-04A New Paradigm for Learning with Distribution Shift
2024-12-04Weak-to-Strong Generalization
2024-12-04Fireside Chat
2024-11-19Robust Mixture Learning when Outliers Overwhelm Small Groups
2024-11-19Learning General Gaussian Mixtures With Efficient Score Matching
2024-11-19Talk by Mahdi Soltanolkotabi (University of Southern California)
2024-11-18Beyond Decoding: Meta-Generation Algorithms for Large Language Models (Remote Talk)
2024-11-17The Truth About Your Lying Calibrated Forecaster: How to Design Truthful Calibration Measures
2024-11-17A Discrepancy-Based Theory of Adaptation
2024-11-17Bypassing the Impossibility of Online Learning Thresholds: Unbounded Losses and Transductive Priors
2024-11-17Learning from Dynamics
2024-11-14Scalably Understanding AI with AI
2024-11-14Domain Adaptation-- 20 years of theory chasing practice
2024-11-14Adaptive Data Collection via Autoregressive Generation
2024-11-14Panel Discussion
2024-11-14Open-Source and Science in the Era of Foundation Models
2024-11-13Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains or the Whole Domain