Podcast Episodes
Back to Search
Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings
This research explores whether pairwise comparisons used to rank generative models actually reflect ground-truth accuracy. By converting multiple ben…
2 months, 3 weeks ago
Critical Batch Size for LLM Policy Optimization
This paper investigates the critical batch size (CBS) for Large Language Model (LLM) policy optimization, specifically focusing on the GRPO algorithm…
2 months, 4 weeks ago
Self-supervised User Profile Generation for Personalization
This paper describes a self-supervised framework called BUMP, which is designed to improve how large language models deliver personalized content. Tr…
2 months, 4 weeks ago
From Augmentation to Reconstruction: Guiding the AI Disruption to the Good Place
This paper explores the evolution of artificial intelligence through a three-stage framework of augmentation, automation, and reconstruction. The aut…
3 months ago
Self-Distilled Agentic Reinforcement Learning
The research paper introduces SDAR (Self-Distilled Agentic Reinforcement Learning), a new framework designed to improve the training of large languag…
3 months ago
Subliminal Learning Is Steering Vector Distillation
This research explores subliminal learning, a phenomenon where a student language model inherits behavioral traits from a teacher model even when tra…
3 months ago
Subsidizing Sequential Search
This paper explores a market model where competing firms use subsidies to reduce the cost of product inspection for consumers. Through a subsidy-sort…
3 months ago
Meta-Harness: End-to-End Optimization of Model Harnesses
This paper introduces Meta-Harness, an innovative system designed to automate harness engineering for large language models. Unlike traditional metho…
3 months ago
Self-Improving Language Models with Bidirectional Evolutionary Search
Researchers have developed Bidirectional Evolutionary Search (BES) to overcome the limitations of standard language model sampling, which often strug…
3 months ago
Generative Modeling via Drifting
This paper discusses Drifting Models, a novel generative modeling paradigm that enables high-quality, one-step image generation without the iterative…
3 months, 1 week ago