Best AI papers explained
Un pódcast de Enoch H. Kang
550 Episodo
-
Learning dynamics of LLM finetuning
Publicado: 9/10/2025 -
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
Publicado: 9/10/2025 -
OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process
Publicado: 8/10/2025 -
Training Agents Inside of Scalable World Models
Publicado: 8/10/2025 -
Small Language Models are the Future of Agentic AI
Publicado: 7/10/2025 -
Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis
Publicado: 6/10/2025 -
Eliciting Secret Knowledge from Language Models
Publicado: 6/10/2025 -
Temporal difference flow
Publicado: 6/10/2025 -
Personalized reasoning: just-in-time personalization and why LLMs fail at it
Publicado: 5/10/2025 -
Prompt Curriculum Learning for Efficient LLM Post-Training
Publicado: 5/10/2025 -
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Publicado: 4/10/2025 -
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
Publicado: 4/10/2025 -
Learning to summarize user information for personalized reinforcement learning from human feedback
Publicado: 4/10/2025 -
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
Publicado: 3/10/2025 -
LIMI: Less is More for Agency
Publicado: 1/10/2025 -
LoRA Without Regret
Publicado: 1/10/2025 -
Actor-Critic without Actor: Critic-Guided Denoising for RL
Publicado: 29/9/2025 -
DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?
Publicado: 29/9/2025 -
Linear Transformers Implicitly Discover Unified Numerical Algorithms
Publicado: 29/9/2025 -
Regularizing Extrapolation in Causal Inference
Publicado: 27/9/2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
