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

530 episodes

Best AI papers explained, page 3

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 3

Recursive Experiential–Working Memory Evolution for Long-Horizon Agent Harnesses

Recurus architecture for long-horizon autonomous agents, addressing “omitted actions” where models claim completion without executing tool/API steps.

31 Aug 2026 · 21m · 12 chapters

TailSFT: Filtered Fine-Tuning Improves Post-Training Performance

TailSFT (Filtered Fine-Tuning) fixes the “SFT trap” where standard supervised fine-tuning collapses probability mass onto easy majority answers, hurting later reinforcement learning (RL) that needs…

30 Aug 2026 · 22m · 10 chapters

SPADE: Self-Play in Adaptive Synthetic Executable Environments

SPADE (Self-Play in Adaptive Synthetic Executable Environments) proposes self-play training where one LLM acts as both environment designer and reasoning agent, generating infinite executable Python…

29 Aug 2026 · 22m · 10 chapters

Evaluating Skills, Not Just Agents: Agentic Continuous Evaluation of Skills

The episode argues that evaluating AI “skills” via static checks (format/LLM-as-judge/linters/security scanners) is unsafe because skills aren’t executed; instead it promotes ACS (Agentic Continuous…

27 Aug 2026 · 28m · 13 chapters

Impression Share Prediction: An Offline Evaluation Task for Ranking Systems

How Meta researchers improve offline evaluation of ranking/recommendation algorithms by predicting “impression share shift” across objective buckets (clicks, video views, conversions) before…

25 Aug 2026 · 22m · 16 chapters

Q-Learning with World Models

QWM (Q-Learning with World Models) for faster, safer robotic learning by combining model-free Q-learning with short-horizon world-model lookahead to avoid compounding simulation bias.

23 Aug 2026 · 25m · 15 chapters

Conformal Language Modeling via Posterior Sampling

Conformal language modeling via posterior sampling, a MIT statistical method to reduce LLM hallucinations during text generation by conditioning token sampling on a calibrated “high-trust” region,…

20 Aug 2026 · 22m · 10 chapters

BoNVoyage: Learning Better Rewards without Ranking

Explains why RLHF reward models trained with pairwise rankings (Bradley-Terry) fail under adversarial distribution shift, enabling reward hacking, and presents Bon Voyage, a method to train reward…

20 Aug 2026 · 22m · 10 chapters

Demystifying Agent Skills: Why They Work—Until They Don’t

Why AI “agent skills” (distilled procedural checklists) improve performance, and when they fail.

18 Aug 2026 · 20m · 12 chapters

Jagged Judges: Epistemic Stability Under Silence, Pressure, and Persistence

Epistemic stability of AI “judges” (LLMs used for grading, moderation, and reward modeling) under silence, pressure, and persistence; argues that standard accuracy tests are misleading because models…

15 Aug 2026 · 20m · 11 chapters

Predicting Neural Scaling Laws without Training: A Data Manifold Oracle

The episode explains the “Data Manifold Oracle” (DMO), a training-free method to predict neural scaling laws (the “floor” error limit and the “slope” learning rate) from raw text using standard…

15 Aug 2026 · 22m · 12 chapters

Making Interpretable Discoveries from Unstructured Data: A High-Dimensional Multiple Hypothesis Testing

A July 2026 research framework for making interpretable, bias-resistant discoveries from unstructured text using sparse autoencoders, high-dimensional multiple-hypothesis testing (KFWER), Gaussian…

11 Aug 2026 · 24m · 14 chapters

Overcoming the Incentive Collapse Paradox

The “incentive collapse paradox” in AI-human workflows: if pay depends only on final accuracy, near-perfect AI makes workers rationally free-ride (exert less effort), potentially requiring infinite…

11 Aug 2026 · 21m · 11 chapters

Position: Modular Memory is the Key to Continual Learning Agents

Continual learning agents that learn over a lifetime without catastrophic forgetting, using modular memory (core model + working memory + long-term memory) and two regimes: external interaction and…

10 Aug 2026 · 27m · 14 chapters

Harness RL is Meta-Learning: Training to Self-Improve at Test Time

Harness RL for meta-learning/self-improvement at test time by moving adaptation from updating model weights to revising the “harness” (instructions, memory, tool rules, verification).

8 Aug 2026 · 22m · 9 chapters

Escaping the Nash Trap: Structural Estimation and Alignment of Strategic Reasoning in Large Language Models

The episode argues that large language models often fail in strategic settings because they assume opponents are perfectly rational “Nash-type” optimizers, creating “Nash traps” where the…

7 Aug 2026 · 22m · 10 chapters

When Does LeJEPA Learn a World Model?

When LeJEPA (Joint Embedding Predictive Architecture) learns a reliable “world model,” i.e., linearly identifiable latent variables from pixel observations, and when that guarantee fails in real…

7 Aug 2026 · 23m · 17 chapters

Do Modules Stay in Their Lane? Role Drift in Compound LLM Systems

The episode explains “role drift” in compound LLM systems trained with outcome-only reinforcement learning, where modules abandon their intended roles while still achieving high final accuracy.

3 Aug 2026 · 21m · 13 chapters

Do you really need to pretrain Q-functions for online RL fine-tuning?

Whether online reinforcement learning fine-tuning needs a pre-trained Q-function (critic) and why naive offline Q pretraining can hurt.

1 Aug 2026 · 24m · 10 chapters

The Evolution of Digital Search: From Blue Links to Delegated Decision-Making

The episode argues that traditional keyword “blue link” search is dying and being replaced by AI-native delegated decision-making, where consumer agents interpret intent, evaluate options invisibly,…

29 Jul 2026 · 19m · 8 chapters

Ask, Don’t Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement

How to evaluate LLM outputs reliably without opaque “holistic” scores, using binary yes/no checklists (Binavol) to catch specific errors and enable automated self-correction.

28 Jul 2026 · 5m · 4 chapters

Understanding Reasoning from Pretraining to Post-Training

How reasoning emerges from the standard AI pipeline (pretraining + supervised fine-tuning + reinforcement learning), using chess and math as controlled testbeds; includes scaling laws, compute…

24 Jul 2026 · 22m · 12 chapters

A Positive Case for Faithfulness: LLM Self-Explanations Help Predict Model Behavior

Whether LLM “self-explanations” (the reasons they give alongside answers) are faithful to their actual internal decision logic, and whether explanations improve prediction of future behavior.

23 Jul 2026 · 15m · 9 chapters

Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference

How inference-time “parallel reasoning” works for language models using sequential Monte Carlo (SMC) with process reward models (PRMs), including math guarantees and why theory can fail on real…

19 Jul 2026 · 23m · 11 chapters