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

531 episodes

Best AI papers explained, page 18

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 18

Learning to summarize user information for personalized reinforcement learning from human feedback

PLUS (pluralistic alignment via summarization) improves RLHF personalization for diverse users by replacing a single-average Bradley-Terry-Luce reward model with user-specific, text-based preference…

4 Oct 2025 · 16m · 8 chapters

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

How RLHF preference learning hides “hidden context” from annotators and, via its aggregation math, implicitly implements a social choice rule (Borda count), leading to strategic manipulability and…

3 Oct 2025 · 16m · 8 chapters

LIMI: Less is More for Agency

“Age of AI Agency” and the LIME/LiMI research (“Less is More for Intelligent Agency”) arguing that autonomous AI agents can be trained with far fewer examples by using high-quality “trajectories”…

1 Oct 2025 · 14m · 5 chapters

LoRA Without Regret

LoRA (low-rank adaptation) for adapting large language models efficiently, focusing on when it matches full fine-tuning (“low regret”), plus operational benefits, compute/FLOPs savings, and behavior…

1 Oct 2025 · 22m · 9 chapters

Actor-Critic without Actor: Critic-Guided Denoising for RL

Actor-Critic Without Actor (ACA) for reinforcement learning replaces the usual actor network with critic-guided denoising, aiming to remove policy lag and cut model size while retaining multimodal…

29 Sep 2025 · 16m · 11 chapters

DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?

Whether reinforcement learning (RL) can make large language models (LLMs) acquire genuinely new programming algorithms, and whether that skill transfers beyond the training distribution.

29 Sep 2025 · 16m · 6 chapters

Linear Transformers Implicitly Discover Unified Numerical Algorithms

A linear transformer trained on masked matrix block completion implicitly discovers a unified numerical solver, EGLE (Emergent Algorithm for Global Low-Rank Estimation), a two-line update rule…

29 Sep 2025 · 14m · 7 chapters

Regularizing Extrapolation in Causal Inference

Regularizing extrapolation in causal inference when source and target groups differ (positivity violations).

27 Sep 2025 · 15m · 10 chapters

DoubleGen - Debiased Generative Modeling of Counterfactuals

DoubleGen, a framework for generating unbiased counterfactuals (“what if” outcomes) from biased observational data by debiasing confounding and avoiding misspecification.

27 Sep 2025 · 13m · 6 chapters

What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT

Effective reasoning in large reasoning models (LRMs) is driven by structure and failure management, not by longer chain-of-thought (CoT) or more “review” tokens.

27 Sep 2025 · 17m · 10 chapters

Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision

Compute as Teacher (CAT) turns a model’s inference-time exploration into reference-free supervision for training specialized skills, reducing the “supervision gap” when gold labels are scarce or…

27 Sep 2025 · 16m · 8 chapters

Learning without training: The implicit dynamics of in-context learning

Explains in-context learning (ICL) as implicit optimization during inference, not “magic” or explicit weight updates.

24 Sep 2025 · 14m · 7 chapters

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model

Tests whether reinforcement learning with verifiable rewards (RLVR) truly increases LLM reasoning capacity beyond the base model, or only improves sampling efficiency within existing capabilities.

24 Sep 2025 · 13m · 7 chapters

Open Problems in Mechanistic Interpretability

Open problems in mechanistic interpretability (MI): how to reverse-engineer neural networks’ internal computations to enable trust, control, and scientific discovery despite “black box” behavior.

21 Sep 2025 · 19m · 12 chapters

Maestro: Joint Graph & Config Optimization for Reliable AI Agents

The episode explains a study on “thought anchors,” sentence-level reasoning steps that disproportionately determine how an LLM reaches its answer, making chain-of-thought more interpretable and…

21 Sep 2025 · 12m · 5 chapters

Thought Anchors: Which LLM Reasoning Steps Matter?

“Thought anchors” for LLM chain-of-thought—identifying which reasoning sentences most causally determine final answers in hard math, using intermediate-level abstraction rather than token-level…

21 Sep 2025 · 16m · 9 chapters

RL's Razor: Why Online RL Forgets Less

Catastrophic forgetting in continual learning, and a MIT paper’s claim that “RL’s razor” explains why online reinforcement learning (RL) forgets less than supervised fine-tuning (SFT).

7 Sep 2025 · 25m · 12 chapters

Why Language Models Hallucinate

Why large language models hallucinate (produce plausible but false statements) and why hallucinations persist due to training objectives and benchmark evaluation incentives; proposes changing…

6 Sep 2025 · 18m · 8 chapters

ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning

ALFA (Alignment Via Fine-Grained Attributes) teaches LLMs to ask better follow-up questions for clinical reasoning by decomposing “good questions” into attributes, synthesizing targeted training…

6 Sep 2025 · 16m · 12 chapters

Sample Efficient Preference Alignment in LLMs via Active Exploration

The episode discusses the paper “Sample Efficient Preference Alignment in LLMs via Active Exploration,” arguing that aligning LLMs to be helpful/harmless is costly because it requires many human…

6 Sep 2025 · 15m · 5 chapters

Adventures in Demand Analysis Using AI

Using AI to estimate consumer demand price elasticity from product details, improving on traditional econometric methods that understate price effects due to confounding factors.

4 Sep 2025 · 14m · 5 chapters

Memento: Fine-tuning LLM Agents without Fine-tuning LLMs

Memento proposes “fine-tuning LLM agents without fine-tuning LLMs” by enabling continuous, real-time learning for autonomous LLM agents using an external memory (case bank) rather than retraining the…

1 Sep 2025 · 19m · 9 chapters

On the Theoretical Limitations of Embedding-Based Retrieval

Theoretical and empirical limits of embedding-based (single-vector) retrieval models, showing they cannot represent all possible “top-K relevant document sets” for a query unless the embedding…

31 Aug 2025 · 17m · 12 chapters

Performance Prediction for Large Systems via Text-to-Text Regression

A Google Research approach for predicting performance of large, complex industrial systems using text-to-text regression with regression language models (RLMs), avoiding lossy tabular feature…

30 Aug 2025 · 16m · 8 chapters