Podcast Episodes
Back to Search
Instance-Optimal Estimation with Multiple LLM Judges on a Budget
This paper addresses the cost-efficient evaluation of large language models (LLMs) by utilizing multiple AI "judges" with different price points and …
3 months, 1 week ago
Robust AI Personalization Will Require a Human Context Protocol
This paper proposes the Human Context Protocol (HCP), a technical framework designed to give individuals direct control over how their personal prefe…
3 months, 1 week ago
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
This paper introduces Equilibrium Reasoners (EqR), a novel framework that conceptualizes iterative AI reasoning as a dynamical system converging towa…
3 months, 2 weeks ago
Position: The Pre/Post-Training Boundary Should Govern IP in Industry–Academia ML Collaborations
This paper proposes a new contractual framework called PBOS to resolve persistent intellectual property conflicts in industry-academia machine learni…
3 months, 2 weeks ago
MEMO: Memory as a Model
MEMO (Memory as a Model), a modular framework designed to integrate new, domain-specific knowledge into Large Language Models (LLMs) without the nee…
3 months, 2 weeks ago
Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces
This research introduces Agent Bazaar, a multi-agent simulation framework designed to evaluate and improve the Economic Alignment of Large Language M…
3 months, 2 weeks ago
General Preference Reinforcement Learning
This paper introduces General Preference Reinforcement Learning (GPRL), a novel post-training framework designed to align large language models with …
3 months, 2 weeks ago
Explaining and Preventing Alignment Collapse in Iterative RLHF
This paper investigates alignment collapse, a phenomenon where iterative reinforcement learning from human feedback (RLHF) fails because the model le…
3 months, 2 weeks ago
Curriculum Learning-Guided Progressive Distillation in Large Language Models
This paper introduces Curriculum Learning-Guided Progressive Distillation (CLPD), a novel framework designed to enhance the reasoning capabilities of…
3 months, 3 weeks ago
Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents
The provided text introduces **VEGAS (Verifier-Guided Action Selection)**, a novel framework designed to improve the reliability of **multimodal larg…
3 months, 3 weeks ago