Best AI papers explained

En podcast av Enoch H. Kang

546 Avsnitt

Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Publicerades: 2025-10-24
The Coverage Principle: How Pre-Training Enables Post-Training
Publicerades: 2025-10-24
The Era of Real-World Human Interaction: RL from User Conversations
Publicerades: 2025-10-24
Agent Learning via Early Experience
Publicerades: 2025-10-24
Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL
Publicerades: 2025-10-22
Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior
Publicerades: 2025-10-22
A Definition of AGI
Publicerades: 2025-10-22
Provably Learning from Language Feedback
Publicerades: 2025-10-21
In-Context Learning for Pure Exploration
Publicerades: 2025-10-21
On the Role of Preference Variance in Preference Optimization
Publicerades: 2025-10-20
Training LLM Agents to Empower Humans
Publicerades: 2025-10-20
Richard Sutton Declares LLMs a Dead End
Publicerades: 2025-10-20
Demystifying Reinforcement Learning in Agentic Reasoning
Publicerades: 2025-10-19
Emergent coordination in multi-agent language models
Publicerades: 2025-10-19
Learning-to-measure: in-context active feature acquisition
Publicerades: 2025-10-19
Andrej Karpathy's insights: AGI, Intelligence, and Evolution
Publicerades: 2025-10-19
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Publicerades: 2025-10-18
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Publicerades: 2025-10-18
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
Publicerades: 2025-10-18
When can in-context learning generalize out of task distribution?
Publicerades: 2025-10-16

3 / 28

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

Visit the podcast's native language site

546 Avsnitt

Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences

The Coverage Principle: How Pre-Training Enables Post-Training

The Era of Real-World Human Interaction: RL from User Conversations

Agent Learning via Early Experience

Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL

Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior

A Definition of AGI

Provably Learning from Language Feedback

In-Context Learning for Pure Exploration

On the Role of Preference Variance in Preference Optimization

Training LLM Agents to Empower Humans

Richard Sutton Declares LLMs a Dead End

Demystifying Reinforcement Learning in Agentic Reasoning

Emergent coordination in multi-agent language models

Learning-to-measure: in-context active feature acquisition

Andrej Karpathy's insights: AGI, Intelligence, and Evolution

Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections

When can in-context learning generalize out of task distribution?