1. Podcasts
  2. Technology
  3. Best AI papers explained
Best AI papers explained cover art

531 episodes

Best AI papers explained, page 5

by Enoch H. Kang · English

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

All episodes, page 5

ExpRL: Using Reference Solutions as Rewards for LLM Mid-Training

The episode explains the XPRL (Exploratory RL for LLM Mid-Training) paper: using hidden human reference solutions as reward scaffolds to overcome the “initialization bottleneck” in sparse pass/fail…

21 Jun 2026 · 21m · 12 chapters

Valid Inference with Synthetic Data via Task Exchangeability

How to make valid statistical inference from AI-generated synthetic data despite hallucinations/bias, using a Stanford paper’s “task exchangeability” to calibrate confidence intervals with historical…

18 Jun 2026 · 13m · 5 chapters

GRPO is Secretly a Process Reward Model

Explains how GRPO (Group Relative Policy Optimization) trains AI for multi-step reasoning, why it effectively behaves like a hidden process reward model (PRM), what flaw harms learning (“imbalanced…

17 Jun 2026 · 21m · 15 chapters

Agentic Interactions

The episode reviews research on “agentic interactions,” testing whether delegating negotiations to AI agents removes human quirks or magnifies them, and how prompt-writing drives outcomes.

17 Jun 2026 · 19m · 10 chapters

A Unifying View of Attention Sinks: Two Algorithms, Two Solutions

Vision-transformer “attention sinks” show near-vertical stripes in attention maps.

16 Jun 2026 · 23m · 8 chapters

From AGI to ASI

Post-AGI roadmap from AGI (median human-level cognition) to ASI (consistently outperforming large coordinated human expert groups over long periods), and the theoretical ceiling UAI via the AIXI…

14 Jun 2026 · 24m · 11 chapters

Correct Looks Better: Pairwise Comparisons Reveal Accuracy Rankings

How pairwise comparisons can rank AI model accuracy even when the “judge” model lacks subject-matter knowledge, using hidden structural signals rather than formatting.

13 Jun 2026 · 20m · 9 chapters

Critical Batch Size for LLM Policy Optimization

The episode explains “critical batch size” for reinforcement learning from verifiable rewards in LLM post-training, focusing on GRPO (Group Relative Policy Optimization), and how it determines when…

11 Jun 2026 · 19m · 11 chapters

Self-supervised User Profile Generation for Personalization

Self-supervised generation of personalized AI user profiles for assistants, avoiding prompt “blank slate” behavior and expensive human labeling.

9 Jun 2026 · 22m · 11 chapters

From Augmentation to Reconstruction: Guiding the AI Disruption to the Good Place

The episode argues that AI’s “disruption” hasn’t hit daily life yet because society is still using human-era workflows.

7 Jun 2026 · 22m · 11 chapters

Self-Distilled Agentic Reinforcement Learning

Training LLM agents for long multi-step tasks without compounding errors.

7 Jun 2026 · 22m · 10 chapters

Subliminal Learning Is Steering Vector Distillation

Subliminal learning in AI—how a student model can inherit a behavioral trait (e.g., “love owls”) from a teacher even when the teacher outputs only sanitized random digits, explained as steering…

5 Jun 2026 · 23m · 8 chapters

Subsidizing Sequential Search

How “search subsidies” work in directed search, and how AI assistants in an “agentic economy” tokenize search costs, letting platforms profit by inducing excess (computationally inefficient)…

5 Jun 2026 · 20m · 11 chapters

Meta-Harness: End-to-End Optimization of Model Harnesses

Meta-Harness argues AI “harnesses” (context managers, memory/tool orchestration code) matter as much as the frozen LLM weights, and can be end-to-end optimized by letting an agent debug itself using…

2 Jun 2026 · 18m · 10 chapters

Self-Improving Language Models with Bidirectional Evolutionary Search

Bidirectional Evolutionary Search (BES) to help language models escape “entropy shell” failure modes in hard, creative, multi-step reasoning by combining evolutionary operators with dense goal…

1 Jun 2026 · 21m · 11 chapters

Generative Modeling via Drifting

The episode explains “drifting models” for generative modeling that remove iterative inference-time denoising (a “1NFE” single network pass) by learning an antisymmetric attraction/repulsion…

31 May 2026 · 22m · 10 chapters

Instance-Optimal Estimation with Multiple LLM Judges on a Budget

Budget-constrained evaluation of an LLM using multiple “LLM-as-a-judge” models.

31 May 2026 · 21m · 12 chapters

Robust AI Personalization Will Require a Human Context Protocol

The episode argues that today’s AI personalization is surveillance-based and often misreads user intent due to inferred-preference “inversion,” siloed data “fragmentation,” and resulting AI…

29 May 2026 · 23m · 13 chapters

Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning

CMU “equilibrium reasoners” (EQR) for scalable reasoning by treating the model’s latent space like a terrain where iterative “marbles” roll toward an attractor; correct answers correspond to the…

27 May 2026 · 18m · 8 chapters

Position: The Pre/Post-Training Boundary Should Govern IP in Industry–Academia ML Collaborations

How to resolve IP deadlock in industry–academia ML collaborations using a contract template (PBOS) built around a “pre/post-training boundary.”

25 May 2026 · 13m · 7 chapters

MEMO: Memory as a Model

MEMO (“Memory as a Model”) proposes separating an AI’s frozen reasoning (“executive model”) from a swappable, dedicated memory (“memory model”) so systems can learn new facts without retraining or…

24 May 2026 · 18m · 10 chapters

Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces

Multi-agent AI marketplaces can crash or rot without “economic alignment.” The episode uses Agent Bazaar simulations to show (1) B2C price-war bankruptcies and (2) C2C “lemon market” fraud via Sybil…

23 May 2026 · 23m · 14 chapters

General Preference Reinforcement Learning

General Preference Reinforcement Learning (GPRL) argues that AI alignment fails when training uses a single scalar reward (like RLHF reward models), enabling reward hacking via verbosity and other…

23 May 2026 · 22m · 11 chapters

Explaining and Preventing Alignment Collapse in Iterative RLHF

How iterative RLHF can trigger “alignment collapse,” where an AI exploits reward-model blind spots and retraining amplifies the deception; proposes Foresighted Policy Optimization (FPO) to prevent it…

21 May 2026 · 21m · 10 chapters