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

530 episodes

Best AI papers explained, page 4

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 4

Rethinking the Evaluation of Harness Evolution for Agents

Evaluates “automatic harness evolution” for AI agents—whether letting a model rewrite its prompts/tools/control logic actually makes it smarter, or just exploits benchmark evaluation.

19 Jul 2026 · 23m · 13 chapters

From Reasoning Traces to Reusable Modules: Understanding Compositional Generalization in Language Model Reasoning

Compositional generalization in language-model reasoning—why supervised fine-tuning (SFT) can make models rigid, and how reinforcement learning (RL) “untangles” reasoning into reusable skill and…

18 Jul 2026 · 19m · 11 chapters

Position: Interpretability can be actionable

The episode argues that AI interpretability must become actionable—moving from passive “black box” observation to concrete interventions that improve real-world behavior, safety, and usability.

17 Jul 2026 · 25m · 12 chapters

High-accuracy sampling for diffusion models and log-concave distributions

A 2026 theoretical breakthrough on high-accuracy sampling for diffusion models and log-concave distributions using only first-order information (gradients), avoiding the “polynomial wall” of standard…

17 Jul 2026 · 22m · 9 chapters

Causal Inference with Video Features as Treatments

Causal inference for video persuasion—isolating the frame-by-frame causal effect of a fleeting visual feature (treated as a “treatment”) on changing human emotion, while correcting for confounding…

15 Jul 2026 · 22m · 11 chapters

What Does Thompson Sampling Optimize?

Exploit–explore tradeoffs in multi-armed bandits, focusing on what Thompson sampling optimizes and how new research “opens the black box” using Markov decision processes and Bellman equations.

15 Jul 2026 · 22m · 10 chapters

Globally Convergent Offline Reinforcement Learning with Smoothed Bellman Residual Minimization

Offline reinforcement learning safety via Globally Convergent Offline RL using Smoothed Bellman Residual Minimization (OffGladius), addressing the “deadly triad” (offline data + neural nets +…

13 Jul 2026 · 12m · 5 chapters

LLM-as-a-Verifier: A General-Purpose Verification Framework

LLM-as-a-Verifier proposes a general-purpose framework to verify LLM outputs by extracting internal uncertainty (logits) instead of using discrete AI “judges,” addressing a “verification crisis”…

10 Jul 2026 · 20m · 12 chapters

How Much Do Language Models Memorize?

How much do transformer language models memorize vs generalize, and what mathematical threshold triggers “grokking” (learning rules) instead of rote storage.

9 Jul 2026 · 24m · 9 chapters

Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering

The episode argues that uncertainty quantification (UQ) in large language models is mis-specified: mainstream UQ methods effectively measure internal consistency via unsupervised clustering of…

7 Jul 2026 · 22m · 12 chapters

Position: Agents Should Invoke External Tools ONLY When Epistemically Necessary

When AI agents should use external tools (search, APIs, code) versus rely on internal reasoning, arguing tools shouldn’t be used unless epistemically necessary.

6 Jul 2026 · 12m · 6 chapters

From conversations to mechanisms: aligning advertiser Incentives in ai-powered product recommendations

How AI preference-alignment methods (used in chatbots via RLHF/DPO) can fail when they assume a fixed logistic “link function” for human choices, and how semi-parametric preference optimization (SPO)…

5 Jul 2026 · 22m · 14 chapters

Is one layer enough? Training a single transformer layer can match full-parameter RL training

The episode explains research on reinforcement learning post-training (RLVR) in large transformer LLMs, arguing that training only a subset of layers—especially middle layers—can match or beat…

4 Jul 2026 · 23m · 11 chapters

RL Excursions during Pre-Training: Re-examining Policy Optimization for LLM training

The episode discusses a Harvard paper, “RL Excursions During Pre-Training,” arguing that reinforcement learning (RL) can be applied early during LLM pre-training—challenging the standard sequential…

2 Jul 2026 · 22m · 10 chapters

Language Generation with Feedback: Queries and Mistakes

How language-generation learning fails under “no feedback” math, but becomes robust when feedback is added; the episode centers on theorems using language generation in the limit, set-based…

1 Jul 2026 · 20m · 9 chapters

Quantifying Theoretical AI Alignment Guarantees: Receiver-Utility Bounds in Bayesian Persuasion

Bayesian persuasion limits for misaligned AI that has an information advantage and tries to steer a rational receiver’s decisions, quantified via receiver-utility bounds.

1 Jul 2026 · 22m · 9 chapters

SPIRAL: Learning to search and aggregate

The episode argues that AI “capability” is jagged: models can solve hard math (e.g., Erdos unit distance problem) yet fail on simple logic.

29 Jun 2026 · 22m · 10 chapters

Qwen-AgentWorld: Language World Models for General Agents

Qwen- AgentWorld describes “language world models” that let general AI agents simulate interactive computer environments internally before acting, reducing errors like clicking the wrong…

27 Jun 2026 · 21m · 10 chapters

When Does Trajectory-Level Supervision Permit Efficient Offline Reinforcement Learning?

When offline reinforcement learning can learn efficiently using only trajectory-level feedback (final outcomes or preferences) instead of step-by-step rewards, and when it becomes impossible.

27 Jun 2026 · 19m · 11 chapters

SuperThoughts: Reasoning Tokens in Superposition

The episode explains “SuperThoughts,” a framework to speed up LLM reasoning by generating two tokens per step using “superposition,” while preserving accuracy via confidence-based adaptive fallback.

26 Jun 2026 · 19m · 7 chapters

First-Explore PPO : Learning Meta-Exploration with Proximal Policy Optimization

Explore-vs-exploit in reinforcement learning under deceptive rewards, and a new method called First-Explore PPO (FEPPO) that learns meta-exploration efficiently.

25 Jun 2026 · 23m · 9 chapters

Self-Distillation for Data-Scarce Language Model Pretraining

Data-scarce pretraining for language models; why multi-epoch reuse overfits, and how self-distillation (teacher-student with identical architectures) improves learning using “dark knowledge” (soft…

24 Jun 2026 · 22m · 11 chapters

Meta-Harness for Agent-State Construction

Meta-harness for agent-state construction (SAIT): an outer-loop AI that writes and debugs the “harness” (working-memory management layer) for other agents, optimizing what gets…

21 Jun 2026 · 23m · 9 chapters

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