Best AI papers explained

En podcast av Enoch H. Kang

546 Avsnitt

Natural emergent misalignment from reward hacking in production RL
Publicerades: 2025-11-25
Evolution Strategies at the Hyperscale
Publicerades: 2025-11-25
The Path Not Taken: RLVR Provably Learns Off the Principals
Publicerades: 2025-11-23
Back to Basics: Let Denoising Generative Models Denoise
Publicerades: 2025-11-23
LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization
Publicerades: 2025-11-22
Black-Box On-Policy Distillation of Large Language Models
Publicerades: 2025-11-20
Solving a million step LLM task with zero errors
Publicerades: 2025-11-20
Not All Thoughts Matter: Selective Attention for Efficient Reasoning
Publicerades: 2025-11-19
Sample-Efficient Parametric Learning from Natural Language
Publicerades: 2025-11-19
Bayesian Optimization in Language space: An Eval-Efficient AI Self-Improvement Framework
Publicerades: 2025-11-18
Context Engineering: Sessions, Memory
Publicerades: 2025-11-16
The Era of Agentic Organization: Learning to Organize with Language Models
Publicerades: 2025-11-15
Understanding neural networks through sparse circuits
Publicerades: 2025-11-14
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Publicerades: 2025-11-14
Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution
Publicerades: 2025-11-14
LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics
Publicerades: 2025-11-14
PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery
Publicerades: 2025-11-12
Reusing pre-training data at test time is a compute multiplier
Publicerades: 2025-11-10
Scaling Agent Learning via Experience Synthesis
Publicerades: 2025-11-09
Continuous Autoregressive Language Models
Publicerades: 2025-11-08

1 / 28

Cut through the noise. We curate and break down the most important AI papers so you don’t have to.

Visit the podcast's native language site

546 Avsnitt

Natural emergent misalignment from reward hacking in production RL

Evolution Strategies at the Hyperscale

The Path Not Taken: RLVR Provably Learns Off the Principals

Back to Basics: Let Denoising Generative Models Denoise

LLM Prompt Duel Optimizer: Efficient Label-Free Prompt Optimization

Black-Box On-Policy Distillation of Large Language Models

Solving a million step LLM task with zero errors

Not All Thoughts Matter: Selective Attention for Efficient Reasoning

Sample-Efficient Parametric Learning from Natural Language

Bayesian Optimization in Language space: An Eval-Efficient AI Self-Improvement Framework

Context Engineering: Sessions, Memory

The Era of Agentic Organization: Learning to Organize with Language Models

Understanding neural networks through sparse circuits

Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning

Multi-Agent Evolve: LLM Self-Improvement Through Co-Evolution

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery

Reusing pre-training data at test time is a compute multiplier

Scaling Agent Learning via Experience Synthesis

Continuous Autoregressive Language Models