Best AI papers explained
Un pódcast de Enoch H. Kang
550 Episodo
-
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Publicado: 18/10/2025 -
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Publicado: 18/10/2025 -
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
Publicado: 18/10/2025 -
When can in-context learning generalize out of task distribution?
Publicado: 16/10/2025 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Publicado: 16/10/2025 -
A small number of samples can poison LLMs of any size
Publicado: 16/10/2025 -
Dual Goal Representations
Publicado: 14/10/2025 -
Welcome to the Era of Experience
Publicado: 14/10/2025 -
Value Flows: Flow-Based Distributional Reinforcement Learning
Publicado: 14/10/2025 -
Self-Adapting Language Models
Publicado: 12/10/2025 -
The Markovian Thinker
Publicado: 12/10/2025 -
Moloch’s Bargain: emergent misalignment when LLMs compete for audiences
Publicado: 12/10/2025 -
Transformer Predictor Dynamics and Task Diversity
Publicado: 11/10/2025 -
Base models know how to reason, thinking models learn when
Publicado: 11/10/2025 -
Spectrum tuning: Post-training for distributional coverage and in-context steerability
Publicado: 11/10/2025 -
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Publicado: 11/10/2025 -
MLPs Learn In-Context on Regression and Classification tasks
Publicado: 11/10/2025 -
Is Pre-Training Truly Better than Meta-Learning?
Publicado: 11/10/2025 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Publicado: 11/10/2025 -
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
Publicado: 9/10/2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
