Best AI papers explained
En podkast av Enoch H. Kang
490 Episoder
-
Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
Publisert: 18.10.2025 -
Representation-Based Exploration for Language Models: From Test-Time to Post-Training
Publisert: 18.10.2025 -
The attacker moves second: stronger adaptive attacks bypass defenses against LLM jail- Breaks and prompt injections
Publisert: 18.10.2025 -
When can in-context learning generalize out of task distribution?
Publisert: 16.10.2025 -
The Art of Scaling Reinforcement Learning Compute for LLMs
Publisert: 16.10.2025 -
A small number of samples can poison LLMs of any size
Publisert: 16.10.2025 -
Dual Goal Representations
Publisert: 14.10.2025 -
Welcome to the Era of Experience
Publisert: 14.10.2025 -
Value Flows: Flow-Based Distributional Reinforcement Learning
Publisert: 14.10.2025 -
Self-Adapting Language Models
Publisert: 12.10.2025 -
The Markovian Thinker
Publisert: 12.10.2025 -
Moloch’s Bargain: emergent misalignment when LLMs compete for audiences
Publisert: 12.10.2025 -
Transformer Predictor Dynamics and Task Diversity
Publisert: 11.10.2025 -
Base models know how to reason, thinking models learn when
Publisert: 11.10.2025 -
Spectrum tuning: Post-training for distributional coverage and in-context steerability
Publisert: 11.10.2025 -
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Publisert: 11.10.2025 -
MLPs Learn In-Context on Regression and Classification tasks
Publisert: 11.10.2025 -
Is Pre-Training Truly Better than Meta-Learning?
Publisert: 11.10.2025 -
Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
Publisert: 11.10.2025 -
Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMs
Publisert: 9.10.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
