Best AI papers explained
Podcast autorstwa Enoch H. Kang
523 Odcinki
-
Large Language Models as Markov Chains
Opublikowany: 28.05.2025 -
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
Opublikowany: 28.05.2025 -
Selective induction heads: how transformers select causal structures in context
Opublikowany: 28.05.2025 -
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Opublikowany: 28.05.2025 -
How Transformers Learn Causal Structure with Gradient Descent
Opublikowany: 28.05.2025 -
Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming
Opublikowany: 28.05.2025 -
Automated Design of Agentic Systems
Opublikowany: 28.05.2025 -
What’s the Magic Word? A Control Theory of LLM Prompting
Opublikowany: 28.05.2025 -
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
Opublikowany: 27.05.2025 -
RL with KL penalties is better viewed as Bayesian inference
Opublikowany: 27.05.2025 -
Asymptotics of Language Model Alignment
Opublikowany: 27.05.2025 -
Qwen 2.5, RL, and Random Rewards
Opublikowany: 27.05.2025 -
Theoretical guarantees on the best-of-n alignment policy
Opublikowany: 27.05.2025 -
Score Matching Enables Causal Discovery of Nonlinear Additive Noise Models
Opublikowany: 27.05.2025 -
Improved Techniques for Training Score-Based Generative Models
Opublikowany: 27.05.2025 -
Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator
Opublikowany: 27.05.2025 -
AlphaEvolve: A coding agent for scientific and algorithmic discovery
Opublikowany: 27.05.2025 -
Harnessing the Universal Geometry of Embeddings
Opublikowany: 27.05.2025 -
Goal Inference using Reward-Producing Programs in a Novel Physics Environment
Opublikowany: 27.05.2025 -
Trial-Error-Explain In-Context Learning for Personalized Text Generation
Opublikowany: 27.05.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
