Best AI papers explained
En podkast av Enoch H. Kang
490 Episoder
-
Learning dynamics of LLM finetuning
Publisert: 9.10.2025 -
Iterative Data Smoothing: Mitigating Reward Overfitting and Overoptimization in RLHF
Publisert: 9.10.2025 -
OpenAI Agent Builder and n8n: Orchestrating Reasoning Versus Automating Process
Publisert: 8.10.2025 -
Training Agents Inside of Scalable World Models
Publisert: 8.10.2025 -
Small Language Models are the Future of Agentic AI
Publisert: 7.10.2025 -
Activation Steering in Generative Settings via Contrastive Causal Mediation Analysis
Publisert: 6.10.2025 -
Eliciting Secret Knowledge from Language Models
Publisert: 6.10.2025 -
Temporal difference flow
Publisert: 6.10.2025 -
Personalized reasoning: just-in-time personalization and why LLMs fail at it
Publisert: 5.10.2025 -
Prompt Curriculum Learning for Efficient LLM Post-Training
Publisert: 5.10.2025 -
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Publisert: 4.10.2025 -
Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward
Publisert: 4.10.2025 -
Learning to summarize user information for personalized reinforcement learning from human feedback
Publisert: 4.10.2025 -
Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
Publisert: 3.10.2025 -
LIMI: Less is More for Agency
Publisert: 1.10.2025 -
LoRA Without Regret
Publisert: 1.10.2025 -
Actor-Critic without Actor: Critic-Guided Denoising for RL
Publisert: 29.9.2025 -
DELTA-Code: How Does RL Unlock and Transfer New Programming Algorithms in LLMs?
Publisert: 29.9.2025 -
Linear Transformers Implicitly Discover Unified Numerical Algorithms
Publisert: 29.9.2025 -
Regularizing Extrapolation in Causal Inference
Publisert: 27.9.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
