Best AI papers explained
Un podcast de Enoch H. Kang
506 Épisodes
-
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Publié: 24/10/2025 -
The Coverage Principle: How Pre-Training Enables Post-Training
Publié: 24/10/2025 -
The Era of Real-World Human Interaction: RL from User Conversations
Publié: 24/10/2025 -
Agent Learning via Early Experience
Publié: 24/10/2025 -
Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL
Publié: 22/10/2025 -
Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior
Publié: 22/10/2025 -
A Definition of AGI
Publié: 22/10/2025 -
Provably Learning from Language Feedback
Publié: 21/10/2025 -
In-Context Learning for Pure Exploration
Publié: 21/10/2025 -
On the Role of Preference Variance in Preference Optimization
Publié: 20/10/2025 -
Training LLM Agents to Empower Humans
Publié: 20/10/2025 -
Richard Sutton Declares LLMs a Dead End
Publié: 20/10/2025 -
Demystifying Reinforcement Learning in Agentic Reasoning
Publié: 19/10/2025 -
Emergent coordination in multi-agent language models
Publié: 19/10/2025 -
Learning-to-measure: in-context active feature acquisition
Publié: 19/10/2025 -
Andrej Karpathy's insights: AGI, Intelligence, and Evolution
Publié: 19/10/2025 -
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Publié: 18/10/2025 -
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Publié: 18/10/2025 -
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
Publié: 18/10/2025 -
When can in-context learning generalize out of task distribution?
Publié: 16/10/2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
