Best AI papers explained
Ein Podcast von Enoch H. Kang
506 Folgen
-
Direct Preference Optimization with Unobserved Preference Heterogeneity: The Necessity of Ternary Preferences
Vom: 24.10.2025 -
The Coverage Principle: How Pre-Training Enables Post-Training
Vom: 24.10.2025 -
The Era of Real-World Human Interaction: RL from User Conversations
Vom: 24.10.2025 -
Agent Learning via Early Experience
Vom: 24.10.2025 -
Demystifying the Mechanisms Behind Emergent Exploration in Goal-conditioned RL
Vom: 22.10.2025 -
Rewriting History: A Recipe for Interventional Analyses to Study Data Effects on Model Behavior
Vom: 22.10.2025 -
A Definition of AGI
Vom: 22.10.2025 -
Provably Learning from Language Feedback
Vom: 21.10.2025 -
In-Context Learning for Pure Exploration
Vom: 21.10.2025 -
On the Role of Preference Variance in Preference Optimization
Vom: 20.10.2025 -
Training LLM Agents to Empower Humans
Vom: 20.10.2025 -
Richard Sutton Declares LLMs a Dead End
Vom: 20.10.2025 -
Demystifying Reinforcement Learning in Agentic Reasoning
Vom: 19.10.2025 -
Emergent coordination in multi-agent language models
Vom: 19.10.2025 -
Learning-to-measure: in-context active feature acquisition
Vom: 19.10.2025 -
Andrej Karpathy's insights: AGI, Intelligence, and Evolution
Vom: 19.10.2025 -
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Vom: 18.10.2025 -
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Vom: 18.10.2025 -
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
Vom: 18.10.2025 -
When can in-context learning generalize out of task distribution?
Vom: 16.10.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
