Allen Nie
@allenanie.bsky.social
Stanford CS PhD working on RL and LLMs with Emma Brunskill and Chris Piech. Co-creator of Trace. Prev @GoogleDeepMind @MicrosoftResearch
Specifically
- Offline RL
- In-context RL
- Causality
https://anie.me/about
Unverified hot takes go to this account
Specifically
- Offline RL
- In-context RL
- Causality
https://anie.me/about
Unverified hot takes go to this account
Pinned
Allen Nie
@allenanie.bsky.social
· Nov 19
Wow, I guess 🦋 is taking off 😆 If you don't know me or my work, here are some highlights:
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
Check out Tianwei’s latest work on using unlikelihood objective to distill search traces back to base model to boost reasoning capabilities of LLMs!
Can we make LLMs reason effectively without a huge inference time cost?
We show a powerful approach through learning and forgetting!
Our recipe: ⬇️
We show a powerful approach through learning and forgetting!
Our recipe: ⬇️
April 23, 2025 at 11:12 PM
Check out Tianwei’s latest work on using unlikelihood objective to distill search traces back to base model to boost reasoning capabilities of LLMs!
For all the RL PhDs and people interested in Planning and MDPs, there's a summer internship opportunity at AWS Science that specializes in LLM post-training, RLHF, LLM agents, and benchmarks like WebArena. Interested students can send their CV to fakoor@amazon.com
February 7, 2025 at 7:52 PM
For all the RL PhDs and people interested in Planning and MDPs, there's a summer internship opportunity at AWS Science that specializes in LLM post-training, RLHF, LLM agents, and benchmarks like WebArena. Interested students can send their CV to fakoor@amazon.com
For education and psychometrics people, this dataset is very useful!
Do you need educational and psychological item response data to do your research? The IRW has 600 item response datasets (more coming!), distributed in a standardized format and ready for analysis.
December 11, 2024 at 7:52 AM
For education and psychometrics people, this dataset is very useful!
People say Ching-an and I are indistinguishable…is that true 🤣
December 10, 2024 at 11:15 PM
People say Ching-an and I are indistinguishable…is that true 🤣
Come check us out near the Tesla Booth in West Exhibition Hall A 3-5pm! Come and claim your mug 🤣 we have an identity crisis — people keep thinking we are from IBM for some reason…
December 10, 2024 at 11:05 PM
Come check us out near the Tesla Booth in West Exhibition Hall A 3-5pm! Come and claim your mug 🤣 we have an identity crisis — people keep thinking we are from IBM for some reason…
Unveiling Trace v0.1.3 at NeurIPS 2024, a library for building an RL-style AI Agent that learns from the environment and human feedback. Today's LLM Agent libraries are not RL agents. They specify a workflow, and it remains unchanged regardless of user feedback. #NotRL vimeo.com/1036224270
Trace Overview
This is "Trace Overview" by Allen Nie on Vimeo, the home for high quality videos and the people who love them.
vimeo.com
December 10, 2024 at 7:52 PM
Unveiling Trace v0.1.3 at NeurIPS 2024, a library for building an RL-style AI Agent that learns from the environment and human feedback. Today's LLM Agent libraries are not RL agents. They specify a workflow, and it remains unchanged regardless of user feedback. #NotRL vimeo.com/1036224270
Reposted by Allen Nie
arxiv.org/abs/2411.17668 Our postdoc zihan slays another COLT open problem! proceedings.mlr.press/v247/kornows...
Anytime Acceleration of Gradient Descent
This work investigates stepsize-based acceleration of gradient descent with {\em anytime} convergence guarantees. For smooth (non-strongly) convex optimization, we propose a stepsize schedule that all...
arxiv.org
November 27, 2024 at 1:03 PM
arxiv.org/abs/2411.17668 Our postdoc zihan slays another COLT open problem! proceedings.mlr.press/v247/kornows...
For people who like RL theory, this is a must follow!
the most important social media outlet ever has just made its transition to @bsky.app --- follow @rl-theory.bsky.social if you don't want to miss out on the latest research on RL theory!
We are on Bluesky as well! We will keep posting on both X and here.
November 26, 2024 at 5:08 PM
For people who like RL theory, this is a must follow!
Reposted by Allen Nie
Hello...world?
Trying to reconstruct my academic networks over here :) Follow me if we know each other or if you're interested in machine learning for healthcare/social equity! Please retweet, or resky, or whatever they call it over here.
Trying to reconstruct my academic networks over here :) Follow me if we know each other or if you're interested in machine learning for healthcare/social equity! Please retweet, or resky, or whatever they call it over here.
November 23, 2024 at 4:46 PM
Hello...world?
Trying to reconstruct my academic networks over here :) Follow me if we know each other or if you're interested in machine learning for healthcare/social equity! Please retweet, or resky, or whatever they call it over here.
Trying to reconstruct my academic networks over here :) Follow me if we know each other or if you're interested in machine learning for healthcare/social equity! Please retweet, or resky, or whatever they call it over here.
Reposted by Allen Nie
Here is a list of ML OSS & Open Source / Science enthusiasts I found on Bluesky 🦋
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
November 21, 2024 at 5:19 AM
Here is a list of ML OSS & Open Source / Science enthusiasts I found on Bluesky 🦋
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
go.bsky.app/8MFcfXd
Let me know if you find such people here!
I'm still new here and probably the list misses many must-add people, so let's built it together💪
How to save/bookmark posts on 🦋?
November 23, 2024 at 1:38 AM
How to save/bookmark posts on 🦋?
Reposted by Allen Nie
I wanted to contribute to "Starter Pack Season" with one for Stanford NLP+HCI: go.bsky.app/VZBhuJ5
Here are some other great starter packs:
- CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK
- NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk
- HCI: go.bsky.app/p3TLwt
- Women in AI: go.bsky.app/LaGDpqg
Here are some other great starter packs:
- CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK
- NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk
- HCI: go.bsky.app/p3TLwt
- Women in AI: go.bsky.app/LaGDpqg
November 15, 2024 at 7:20 PM
I wanted to contribute to "Starter Pack Season" with one for Stanford NLP+HCI: go.bsky.app/VZBhuJ5
Here are some other great starter packs:
- CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK
- NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk
- HCI: go.bsky.app/p3TLwt
- Women in AI: go.bsky.app/LaGDpqg
Here are some other great starter packs:
- CSS: go.bsky.app/GoEyD7d + go.bsky.app/CYmRvcK
- NLP: go.bsky.app/SngwGeS + go.bsky.app/JgneRQk
- HCI: go.bsky.app/p3TLwt
- Women in AI: go.bsky.app/LaGDpqg
Wow, I guess 🦋 is taking off 😆 If you don't know me or my work, here are some highlights:
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
November 19, 2024 at 4:42 PM
Wow, I guess 🦋 is taking off 😆 If you don't know me or my work, here are some highlights:
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
In-Context RL / LLM Agents
EVOLvE arxiv.org/pdf/2410.06238
Accelerate Distributed System arxiv.org/pdf/2410.15625
RL / Causal Inference + Human
arxiv.org/pdf/2304.04933
arxiv.org/abs/2407.09975
Reposted by Allen Nie
The RL (and some non-RL folks) starter pack is almost full. Pretty clear that the academic move here has succeeded
go.bsky.app/3WPHcHg
go.bsky.app/3WPHcHg
November 18, 2024 at 8:30 PM
The RL (and some non-RL folks) starter pack is almost full. Pretty clear that the academic move here has succeeded
go.bsky.app/3WPHcHg
go.bsky.app/3WPHcHg
This talk is just fascinating — “o1 has an effective way to scale compute at inference time” — but you just can’t tell us what it exactly is 🤣
November 19, 2024 at 12:29 AM
This talk is just fascinating — “o1 has an effective way to scale compute at inference time” — but you just can’t tell us what it exactly is 🤣
Noam Brown giving a talk on o1 at Stanford right now 🔥
November 19, 2024 at 12:06 AM
Noam Brown giving a talk on o1 at Stanford right now 🔥