Best AI papers explained
A podcast by Enoch H. Kang
550 Episoade
-
PREFDISCO: Evaluating Proactive Personalization through Interactive Preference Discovery
Publicat: 12.11.2025 -
Reusing pre-training data at test time is a compute multiplier
Publicat: 10.11.2025 -
Scaling Agent Learning via Experience Synthesis
Publicat: 09.11.2025 -
Continuous Autoregressive Language Models
Publicat: 08.11.2025 -
Toward a Theory of Agents as Tool-Use Decision-Makers
Publicat: 07.11.2025 -
Nested Learning: The Illusion of Deep Learning Architectures
Publicat: 05.11.2025 -
GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding
Publicat: 05.11.2025 -
Beyond a million tokens: benchmarking and enhancing long-term memory in llms
Publicat: 04.11.2025 -
Agentic Economic Modeling
Publicat: 03.11.2025 -
Emergent Introspective Awareness in Large Language Models
Publicat: 03.11.2025 -
Can Large reasoning models self-train?
Publicat: 01.11.2025 -
ALITA-G: Self-Evolving Generative Agent for Agent Generation
Publicat: 01.11.2025 -
Self-improving LLM agents at test-time
Publicat: 30.10.2025 -
Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
Publicat: 30.10.2025 -
Language models are injective and hence invertible
Publicat: 30.10.2025 -
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
Publicat: 29.10.2025 -
RLAD: Training LLMs to Discover Abstractions
Publicat: 29.10.2025 -
How to Train Your Advisor: Steering Black-Box LLMs with ADVISOR MODELS
Publicat: 29.10.2025 -
Self-improving LLM agents at Test-Time
Publicat: 27.10.2025 -
KL-Regularized Reinforcement Learning is designed to Mode Collapse
Publicat: 27.10.2025
Cut through the noise. We curate and break down the most important AI papers so you don’t have to.
