Lil'Log (Lilian Weng)
Deep learning research explainers from Lilian Weng.
Read from its RSS feedAppears in:AI
Latest from Lil'Log (Lilian Weng)
- Harness Engineering for Self-Improvement2026-07-04
- Scaling Laws, Carefully2026-06-24
- Why We Think2025-05-01
- Reward Hacking in Reinforcement Learning2024-11-28
- Extrinsic Hallucinations in LLMs2024-07-07
- Diffusion Models for Video Generation2024-04-12
- Thinking about High-Quality Human Data2024-02-05
- Adversarial Attacks on LLMs2023-10-25
- LLM Powered Autonomous Agents2023-06-23
- Prompt Engineering2023-03-15
- The Transformer Family Version 2.02023-01-27
- Large Transformer Model Inference Optimization2023-01-10
- Some Math behind Neural Tangent Kernel2022-09-08
- Generalized Visual Language Models2022-06-09
- Learning with not Enough Data Part 3: Data Generation2022-04-15
- Learning with not Enough Data Part 2: Active Learning2022-02-20
- Learning with not Enough Data Part 1: Semi-Supervised Learning2021-12-05
- How to Train Really Large Models on Many GPUs?2021-09-24
- What are Diffusion Models?2021-07-11
- Contrastive Representation Learning2021-05-31
- Reducing Toxicity in Language Models2021-03-21
- Controllable Neural Text Generation2021-01-02
- How to Build an Open-Domain Question Answering System?2020-10-29
- Neural Architecture Search2020-08-06
- Exploration Strategies in Deep Reinforcement Learning2020-06-07
- The Transformer Family2020-04-07
- Curriculum for Reinforcement Learning2020-01-29
- Self-Supervised Representation Learning2019-11-10
- Evolution Strategies2019-09-05
- Meta Reinforcement Learning2019-06-23