corpus.blog
Most cited
Talked about
Blogs
41554 blogs · [ { "id": "01a08792-8d08-7327-8673-c704637cbd5a", "title": "RL should be the same shape as pretraining", "url": "https://justinchiu.netlify.app/blog/opinionatedrl/", "published_at": "2026-06-10T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb53739bb", "title": "MCTS is a replay buffer is a gradient estimator", "url": "https://justinchiu.netlify.app/blog/treerl/", "published_at": "2026-06-10T00:00:00+00:00" }, { "id": "01a08792-8d08-7327-8673-c70462dcb2be", "title": "Differentiating through optimization with the IFT", "url": "https://justinchiu.netlify.app/blog/ift/", "published_at": "2026-03-26T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb71645c4", "title": "Why Routing Replay in MoE RL is Necessary", "url": "https://justinchiu.netlify.app/blog/weakening/", "published_at": "2025-12-03T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb46b4c7d", "title": "Sum-and-Sample RL: Replay Buffers", "url": "https://justinchiu.netlify.app/blog/sumsamplerl/", "published_at": "2025-08-09T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb5f7e595", "title": "Variational Autoencoders from First Principles", "url": "https://justinchiu.netlify.app/blog/vae/", "published_at": "2025-08-04T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb30b8eae", "title": "SFT is bad RL", "url": "https://justinchiu.netlify.app/blog/sftrl/", "published_at": "2025-07-14T00:00:00+00:00" }, { "id": "01a08792-8d08-7327-8673-c70462e68f7d", "title": "Definitions of Memorization", "url": "https://justinchiu.netlify.app/blog/memorization/", "published_at": "2025-06-16T00:00:00+00:00" }, { "id": "01a08792-8d08-7327-8673-c704622d23e6", "title": "Character prefix completion", "url": "https://justinchiu.netlify.app/blog/completion/", "published_at": "2025-01-09T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb36cc44a", "title": "What objective is STaR optimizing?", "url": "https://justinchiu.netlify.app/blog/star/", "published_at": "2024-04-27T00:00:00+00:00" }, { "id": "01a08792-8d08-7327-8673-c70463bd447c", "title": "Differentiating through an associative parallel scan", "url": "https://justinchiu.netlify.app/blog/pscan_diff/", "published_at": "2024-01-08T00:00:00+00:00" }, { "id": "01a08792-8d09-71d1-a60c-621cb6169a65", "title": "Variational inference: Ising models", "url": "https://justinchiu.netlify.app/blog/vi/", "published_at": "2023-12-30T00:00:00+00:00" }, { "id": "01a08792-8d08-7327-8673-c704644d7d36", "title": "First post", "url": "https://justinchiu.netlify.app/blog/setup/", "published_at": "2023-12-20T00:00:00+00:00" } ] posts
Claim your blog
Back to justinchiu.netlify.app
Blog · corpus.blog/blogs/justinchiu.netlify.app/posts
justinchiu.netlify.app
justinchiu.netlify.app
2026
RL should be the same shape as pretraining
original ↗
10 Jun 2026
MCTS is a replay buffer is a gradient estimator
original ↗
10 Jun 2026
Differentiating through optimization with the IFT
original ↗
26 Mar 2026
2025
Why Routing Replay in MoE RL is Necessary
original ↗
3 Dec 2025
Sum-and-Sample RL: Replay Buffers
original ↗
9 Aug 2025
Variational Autoencoders from First Principles
original ↗
4 Aug 2025
SFT is bad RL
original ↗
14 Jul 2025
Definitions of Memorization
original ↗
16 Jun 2025
Character prefix completion
original ↗
9 Jan 2025
2024
What objective is STaR optimizing?
original ↗
27 Apr 2024
Differentiating through an associative parallel scan
original ↗
8 Jan 2024
2023
Variational inference: Ising models
original ↗
30 Dec 2023
First post
original ↗
20 Dec 2023