Best AI papers explained
A podcast by Enoch H. Kang
515 Episoade
-
LoRA Without Regret
Publicat: 01.10.2025 -
Actor-Critic without Actor: Critic-Guided Denoising for RL
Publicat: 29.09.2025 -
DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?
Publicat: 29.09.2025 -
Linear Transformers Implicitly Discover Unified Numerical Algorithms
Publicat: 29.09.2025 -
Regularizing Extrapolation in Causal Inference
Publicat: 27.09.2025 -
DoubleGen - Debiased Generative Modeling of Counterfactuals
Publicat: 27.09.2025 -
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Publicat: 27.09.2025 -
Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision
Publicat: 27.09.2025 -
Learning without training: The implicit dynamics of in-context learning
Publicat: 24.09.2025 -
Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model
Publicat: 24.09.2025 -
Open Problems in Mechanistic Interpretability
Publicat: 21.09.2025 -
Maestro: Joint Graph & Config Optimization for Reliable AI Agents
Publicat: 21.09.2025 -
Thought Anchors: Which LLM Reasoning Steps Matter?
Publicat: 21.09.2025 -
Sample Complexity and Representation Ability of Test-time Scaling Paradigms
Publicat: 09.09.2025 -
RL's Razor: Why Online RL Forgets Less
Publicat: 07.09.2025 -
Why Language Models Hallucinate
Publicat: 06.09.2025 -
ALFA: Aligning LLMs to Ask Good Questions A Case Study in Clinical Reasoning
Publicat: 06.09.2025 -
Sample Efficient Preference Alignment in LLMs via Active Exploration
Publicat: 06.09.2025 -
Adventures in Demand Analysis Using AI
Publicat: 04.09.2025 -
Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
Publicat: 01.09.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
