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

530 episodes

Best AI papers explained, page 6

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 6

Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents

Why embodied robots fail despite strong multimodal “digital genius,” and how VEGAS (Verifier-Guided Action Selection) improves reliability by replacing greedy decoding with verifier-guided…

19 May 2026 · 26m · 12 chapters

How Much Should a Conversational Recommender System Converse?

How conversational AI shopping assistants decide how many clarifying questions to ask, balancing “preference matching” against user “abandonment hazard,” and how this differs by product type and…

17 May 2026 · 22m · 11 chapters

FUSE: Ensembling Verifiers with Zero Labeled Data

The episode explains FU-SE (Fully Unsupervised Score Ensembling), a Stanford/Google method for ranking AI-generated answers using multiple AI verifiers without any labeled data or answer keys.

14 May 2026 · 20m · 8 chapters

EVOLM: Self-Evolving Language Models through Co-Evolved Discriminative Rubrics

EVOLM (evolutionary language model) trains a language model to generate its own grading rubrics via co-evolution, avoiding human-written or opaque “scalar reward” grading.

14 May 2026 · 23m · 14 chapters

Personalized Alignment Revisited: The Necessity and Sufficiency of User Diversity

Why AI personalization can fail even when users provide their personal data; the episode argues that success requires “decision-relevant user diversity” (full-rank variation in user-specific…

12 May 2026 · 22m · 14 chapters

OGPO: Sample Efficient Full-Finetuning of Generative Control Policies

OGPO (Off-policy Generative Policy Optimization) for sample-efficient full-finetuning of diffusion-based generative control policies in robotics, addressing brittleness of behavior cloning and data…

11 May 2026 · 22m · 11 chapters

Adaptive Querying with AI Persona Priors

How “AI persona priors” enable adaptive questionnaires that infer a user’s latent traits from only 5–15 questions, avoiding classical calibration and computation bottlenecks.

9 May 2026 · 23m · 12 chapters

Rethinking the Role of LLMs in Time Series Forecasting

Whether large language models (LLMs) can improve time series forecasting, and when they should be used versus traditional numeric models.

8 May 2026 · 22m · 11 chapters

Robust Representation Learning through Explicit Environment Modeling

Multi-environment/out-of-distribution generalization in AI, arguing that “invariance” methods fail when the environment changes the label, and proposing explicit environment modeling via generalized…

7 May 2026 · 23m · 11 chapters

Magentic Marketplace: An Open-Source Environment for studying Agentic Markets

The episode explains “Magnetic Marketplace,” an open-source simulation for studying two-sided agentic markets where consumer and business AI proxies negotiate and execute real transactions end-to-end.

5 May 2026 · 22m · 15 chapters

Hyperloop Transformers

MIT’s Hyperloop Transformer architecture for running large language models offline on smartphones by cutting model size roughly in half while preserving intelligence, addressing the “memory wall” and…

5 May 2026 · 22m · 11 chapters

Scaling Self-Play with Self-Guidance

Unbounded AI learning via self-play, focusing on “self-guided self-play” (SGS) to prevent self-play training from plateauing.

4 May 2026 · 20m · 9 chapters

RL Token: Bootstrapping Online RL with Vision-Language-Action Models

The “last millimeter problem” in robotics—vision-language-action (VLA) models fail at sub-millimeter, high-precision tasks like plugging in cables or threading flexible parts.

3 May 2026 · 22m · 13 chapters

Agentic Data Environments

How to safely transition AI from read-only assistants to read-write autonomous agents by building “agentic data environments” (Columbia Deep Lab), covering retrieval, structured data management,…

3 May 2026 · 25m · 18 chapters

AI organizations are more effective but less aligned than individual agents

Multi-agent “AI organizations” (autonomous teams with roles like project manager, compliance officer, etc.) outperform single agents on business goals but become less ethically aligned, mirroring…

1 May 2026 · 20m · 11 chapters

Text-to-Distribution Prediction with Quantile Tokens and Neighbor Context

The episode discusses a paper, “Text to Distribution Prediction with Quantile Tokens and Neighbor Context,” arguing that point estimates (means/medians) hide risk and tail behavior.

28 Apr 2026 · 23m · 16 chapters

Distortion of AI alignment revisited: RLHF is a decent utilitarian aligner

The episode revisits a claimed “mathematical panic” that RLHF (reinforcement learning from human feedback) fails with diverse, conflicting user preferences.

27 Apr 2026 · 18m · 12 chapters

Llms get lost in multi-turn conversation

LLMs “get lost” in multi-turn, underspecified conversations, showing a large reliability collapse versus single-turn benchmarks.

25 Apr 2026 · 21m · 10 chapters

Transformers are inherently succint

The episode argues that transformers’ power comes from extreme computational succinctness (packing information into very few parameters), not from broad formal-language variety.

23 Apr 2026 · 21m · 13 chapters

The Coasean Singularity? Demand, Supply, and Market Design with AI Agents

How autonomous AI agents will reshape markets by nearly eliminating transaction costs, enabling machine-to-machine negotiation and matching, and forcing changes to internet infrastructure, identity…

23 Apr 2026 · 22m · 16 chapters

Demystifying the unreasonable effectiveness of online alignment methods

The episode explains why online AI alignment methods (online RLHF and online DPO) work better in practice than theory predicts, arguing the mismatch comes from a flawed evaluation metric rather than…

21 Apr 2026 · 18m · 9 chapters

Specialization after generalization: towards understanding test-time training in foundation models

Explains test-time training (TTT) for foundation models: instead of permanently scaling models, they temporarily “specialize after generalization” at inference to reduce interference from…

21 Apr 2026 · 22m · 12 chapters

Exploration and Exploitation Errors Are Measurable for Language Model Agents

A policy-agnostic evaluation framework measures exploration vs exploitation errors in language model agents by observing actions in a symbolic “fog of war” 2D grid with a task DAG (prerequisite…

20 Apr 2026 · 23m · 11 chapters

A Mechanistic Analysis of Looped Reasoning Language Models

Looped reasoning language models that reuse a recurrent block in a circular “roundabout” to spend more compute time, instead of the usual feed-forward one-pass transformer.

19 Apr 2026 · 19m · 8 chapters