Best AI papers explained
A podcast by Enoch H. Kang
550 Episodio
-
Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
Pubblicato: 29/05/2025 -
LLM Populations Form Social Conventions and Collective Bias
Pubblicato: 29/05/2025 -
LLM Generated Persona is a Promise with a Catch
Pubblicato: 29/05/2025 -
Large Language Models for Digital Twin Simulation
Pubblicato: 29/05/2025 -
From RL Distillation to Autonomous LLM Agents
Pubblicato: 29/05/2025 -
Prompting, Auto-Prompting, and Human-AI Communication
Pubblicato: 29/05/2025 -
Textual Gradients for LLM Optimization
Pubblicato: 29/05/2025 -
Large Language Models as Markov Chains
Pubblicato: 28/05/2025 -
Metastable Dynamics of Chain-of-Thought Reasoning: Provable Benefits of Search, RL and Distillation
Pubblicato: 28/05/2025 -
Selective induction heads: how transformers select causal structures in context
Pubblicato: 28/05/2025 -
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Pubblicato: 28/05/2025 -
How Transformers Learn Causal Structure with Gradient Descent
Pubblicato: 28/05/2025 -
Planning anything with rigor: general-purpose zero-shot planning with llm-based formalized programming
Pubblicato: 28/05/2025 -
Automated Design of Agentic Systems
Pubblicato: 28/05/2025 -
What’s the Magic Word? A Control Theory of LLM Prompting
Pubblicato: 28/05/2025 -
BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
Pubblicato: 27/05/2025 -
RL with KL penalties is better viewed as Bayesian inference
Pubblicato: 27/05/2025 -
Asymptotics of Language Model Alignment
Pubblicato: 27/05/2025 -
Qwen 2.5, RL, and Random Rewards
Pubblicato: 27/05/2025 -
Theoretical guarantees on the best-of-n alignment policy
Pubblicato: 27/05/2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
