Prova Storytel gratis i 30 dagar Ett universum fyllt av ljudböcker, klicka här för att komma igång

Best AI papers explained

En podcast av: Enoch H. Kang

Cut through the noise. We curate and break down the most important AI papers so you don’t have to

Our American listeners can also listen to Best AI papers explained at our American site

459 Avsnitt

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
Publicerades 2025-10-04

Learning to summarize user information for personalized reinforcement learning from human
Publicerades 2025-10-04
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
Publicerades 2025-10-03
LIMI: Less is More for Agency
Publicerades 2025-10-01
LoRA Without Regret
Publicerades 2025-10-01
Actor-Critic without Actor: Critic-Guided Denoising for RL
Publicerades 2025-09-29
DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?
Publicerades 2025-09-29
Linear Transformers Implicitly Discover Unified Numerical Algorithms
Publicerades 2025-09-29
Regularizing Extrapolation in Causal Inference
Publicerades 2025-09-27
DoubleGen - Debiased Generative Modeling of Counterfactuals
Publicerades 2025-09-27
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Publicerades 2025-09-27
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Publicerades 2025-09-27
Learning without training: The implicit dynamics of in-context learning
Publicerades 2025-09-24
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model
Publicerades 2025-09-24
Open Problems in Mechanistic Interpretability
Publicerades 2025-09-21
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
Publicerades 2025-09-21
Thought Anchors: Which LLM Reasoning Steps Matter?
Publicerades 2025-09-21
Sample Complexity and Representation Ability of Test-time Scaling Paradigms
Publicerades 2025-09-09
RL's Razor: Why Online RL Forgets Less
Publicerades 2025-09-07
Why Language Models Hallucinate
Publicerades 2025-09-06

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

459 Avsnitt

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

Learning to summarize user information for personalized reinforcement learning from human

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

LIMI: Less is More for Agency

LoRA Without Regret

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

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

Linear Transformers Implicitly Discover Unified Numerical Algorithms

Regularizing Extrapolation in Causal Inference

DoubleGen - Debiased Generative Modeling of Counterfactuals

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

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

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

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

Open Problems in Mechanistic Interpretability

Maestro: Joint Graph & Config Optimization for Reliable AI Agents

Thought Anchors: Which LLM Reasoning Steps Matter?

Sample Complexity and Representation Ability of Test-time Scaling Paradigms

RL's Razor: Why Online RL Forgets Less

Why Language Models Hallucinate