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

530 episodes

Best AI papers explained, page 21

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 21

On Temporal Credit Assignment and Data-Efficient Reinforcement Learning

Temporal credit assignment in reinforcement learning—how to determine which earlier actions/states actually caused delayed outcomes, beyond recency-based methods.

15 Jul 2025 · 17m · 8 chapters

Bradley–Terry and Multi-Objective Reward Modeling Are Complementary

How reward models used in RLHF for LLM alignment can be exploited via reward hacking, especially out-of-distribution (OOD) prompts, and how SMORM (Joint, Single, and Multi-Objective Reward Model)…

15 Jul 2025 · 17m · 8 chapters

Probing Foundation Models for World Models

Tests whether foundation models learn “world models” (underlying rules) or just predict sequences via heuristics, using an “inductive bias probe” rather than accuracy alone.

15 Jul 2025 · 12m · 7 chapters

GenAI-Powered Statistical Inference (with Unstructured Data)

GenAI-Powered Inference (GPI), a statistical framework (Yamai & Nakamura, Harvard; paper dated July 8, 2025) that uses generative AI to do causal/predictive inference on unstructured data (text,…

14 Jul 2025 · 20m · 10 chapters

Interpretable Reward Modeling with Active Concept Bottlenecks

Interpretable Reward Modeling for RLHF—making reward models auditable by predicting human-interpretable concepts via Concept Bottleneck Reward Models (CBRM), trained with active learning to reduce…

14 Jul 2025 · 12m · 7 chapters

PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications

“PrefillOnly” inference engine for LLM applications where each request outputs exactly one token (e.g., yes/no, option A/B/C, label).

14 Jul 2025 · 14m · 4 chapters

A Collectivist, Economic Perspective on AI

The episode argues that today’s AI debate is “noisy” and too individualistic (thinking machines/AGI).

14 Jul 2025 · 21m · 11 chapters

Textual Bayes: Quantifying Uncertainty in LLM-Based Systems

The episode discusses the paper “Textual Bayes: Quantifying Uncertainty in LLM-Based Systems,” which aims to make LLM outputs more reliable by producing calibrated uncertainty estimates.

12 Jul 2025 · 9m · 6 chapters

The Winner's Curse in Data-Driven Decisions

The episode explains the “winner’s curse” in inference-then-optimization systems: even with unbiased estimates for each option, selecting the best-performing option based on noisy estimates makes the…

11 Jul 2025 · 30m · 14 chapters

SPIRAL: Self-Play for Reasoning Through Zero-Sum Games

Spiral is a self-play training framework for language-model reasoning in two-player zero-sum, multi-turn “language games,” aiming to reduce reliance on human-labeled data and expert supervision.

11 Jul 2025 · 17m · 9 chapters

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

The episode argues that today’s frontier LLMs (trained via statistical learning/next-token prediction) are misaligned with the deductive, zero-error reasoning needed for general intelligence and…

11 Jul 2025 · 22m · 11 chapters

Aligning Learning and Endogenous Decision-Making

The episode explains a research paper, “Aligning Learning and Endogenous Decision Making,” arguing that standard AI “predict-then-optimize” fails when actions change the data you observe (endogenous…

11 Jul 2025 · 16m · 11 chapters

Reliable Statistical Inference with Synthetic Data from Large Language Models

The episode argues that LLMs can generate fully synthetic survey/text data to overcome the high cost and slow timelines of collecting human social-science data, but only if synthetic data is combined…

11 Jul 2025 · 14m · 12 chapters

Multi-Turn Reinforcement Learning from Human Preference Feedback

Multi-turn reinforcement learning from human preference feedback (RLHF), arguing that training LLMs with feedback on whole conversations beats single-turn feedback because good actions can look bad…

10 Jul 2025 · 17m · 11 chapters

Provably Learning from Language Feedback

How large language models can learn from detailed natural-language critiques (LLF) instead of scalar reward scores, and when this yields provably faster learning.

9 Jul 2025 · 17m · 8 chapters

Markets with Heterogeneous Agents: Dynamics and Survival of Bayesian vs. No-Regret Learners

How competing learning algorithms in markets determine “survival” (nonzero wealth share) vs “vanishing” (wealth share goes to zero), comparing Bayesian learners to no-regret learners, and proposing a…

5 Jul 2025 · 21m · 10 chapters

Why Neural Network Can Discover Symbolic Structures with Gradient-based Training: An Algebraic and Geometric Foundation

A July 3, 2025 theoretical framework explains how gradient-based training of neural networks can yield discrete symbolic structures (neurosymbolic reasoning) from continuous optimization.

5 Jul 2025 · 14m · 4 chapters

Causal Abstraction with Lossy Representations

Projected abstractions for causal reasoning with lossy representations, addressing the abstract invariance condition (AIC) problem and enabling cross-layer inference (L1 observations to L2…

4 Jul 2025 · 26m · 13 chapters

The Winner's Curse in Data-Driven Decisions

Winner’s curse in data-driven decisions: when teams do “inference, then optimize” (estimate values from data, then pick the best), selection bias from noise makes the chosen option’s estimated lift…

4 Jul 2025 · 23m · 14 chapters

Embodied AI Agents: Modeling the World

Embodied AI agents that perceive (vision/audio/touch), model the physical and human “mental” context, plan and act with autonomy, and learn continuously; the episode covers research status (a July 4,…

4 Jul 2025 · 29m · 15 chapters

Beyond Statistical Learning: Exact Learning Is Essential for General Intelligence

The episode argues that today’s LLMs, trained via statistical learning (next-token prediction), are fundamentally misaligned with the kind of exact, deductive reasoning needed for general…

4 Jul 2025 · 20m · 12 chapters

What Has a Foundation Model Found? Inductive Bias Reveals World Models

An “inductive bias probe” tests whether foundation models learn true underlying world rules (Newton) or only learn shortcuts that predict outcomes (Kepler).

4 Jul 2025 · 12m · 6 chapters

Language Bottleneck Models: A Framework for Interpretable Knowledge Tracing and Beyond

Language Bottleneck Models (LBMs) for knowledge tracing: converting a student’s interaction history into a concise natural-language “knowledge state” summary that preserves predictive power while…

3 Jul 2025 · 23m · 12 chapters

Learning to Explore: An In-Context Learning Approach for Pure Exploration

The episode explains “pure exploration” in AI and a new method called In-Context Pure Exploration (ICPE), which learns how to choose the most informative next actions without being given explicit…

3 Jul 2025 · 17m · 9 chapters