Jeff Willette

[Minki Kang @mkkang_1133]

Our Agent Distillation paper is accepted at #NeurIPS2025 Spotlight! 🚀

Turn your small LM into a strong agent 💪
Code: https://t.co/ost8pKZRwo

[Jeff Willette @TheOneJeffrey]

We propose to first perform query-sparse attention and combine the output with a generic key-sparse attn. method. This drastically boosts the performance of sparse attention while adding minimal overhead, and its dead simple to implement on pretrained models.

[Jeff Willette @TheOneJeffrey]

Noice! Our paper "Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction" has been accepted to NeurIPS 2025! See you in San Diego (See part 2 of post for breakdown of our work)
https://t.co/Xjv8Uqvpsk

[Jeff Willette @TheOneJeffrey]

Most sparse attention methods focus on key-sparse attention. We found that key-sparse attention causes a distributional shift in outputs. Therefore, even if you switch to dense attention during decode, the queries and the keys might no longer match...

[Jinheon Baek @jinheonbaek]

So excited to share that five papers have been accepted to #ACL2025 🎉

Huge thanks to all my amazing collaborators. I am especially grateful that all the internship projects (which I have worked on during my PhD journey) have all found their way to publication. Its rewarding. 😊

[Jeff Willette @TheOneJeffrey]

There is a HUGE problem with sparse attention! We found it causes a misalignment of queries and keys, so even if you add a dense decode/generation phase, the sparsely encoded context can be forgotten. But wait... We can fix it with a simple correction! https://t.co/T7KjLd0lDb

[Jeff Willette @TheOneJeffrey]

@netflix I applied for an internship and got an email asking me to fill out a form on https://t.co/A0YR8fvKRl. the link in the email is broken. Your support and https://t.co/A0YR8fvKRl support both said they can't help. What else can I do? There is no one else to contact.

[Jeff Willette @TheOneJeffrey]

@mhartington Ok Thanks! I've got a hard deadline of March 1st to submit my materials, so if you have some time before then I would be forever grateful.

[Jeff Willette @TheOneJeffrey]

@mhartington can you check your DM's? I sent an inquiry related to nvim typescript last week.

[Jeff Willette @TheOneJeffrey]

@gatsbyjs @kylemathews @kylemathews can you check your dm's?

[Jeff Willette @TheOneJeffrey]

@gatsbyjs I have a bit of an unusual (but simple) request related to my contributions to the project, any chance I can speak to someone about it via DM or email?

[Jeff Willette @TheOneJeffrey]

@gatsbyjs @kylemathews I sent him a dm about a week ago and haven't heard back yet.

[Jeff Willette @TheOneJeffrey]

@mhartington Cool. Yeah I see all the files in question being watched but still no fixes. Ever seen anything like that before?

[Jeff Willette @TheOneJeffrey]

@mhartington I am debugging nvim_typescript and why :TSImport is giving me no candidates. I'm down to sending raw requests to the TSServer. Is there a better way to debug this? TSServer isn't doc'd well...

[Jeff Willette @TheOneJeffrey]

@mhartington Cool. Yeah I see the files in question are being watched but still no imports. Ever seen anything like that before?

[Jeff Willette @TheOneJeffrey]

@mhartington Yeah im already logging it all from that wiki. Dobyou know if any of the commands to the server can dump all exported symbols?

[Jeff Willette @TheOneJeffrey]

I just published “Tern: Why it Breaks and How To Fix it” https://t.co/HdyBEPKdaC

[Jeff Willette @TheOneJeffrey]

@flowtype can the autocomplete CLI complete methods and identifiers from non flowtyped files? (without type information of course) https://t.co/UV8sGhn0ix

[Jeff Willette @TheOneJeffrey]

Monitor and get simple alerts on docker container metrics, now from within docker as well! https://t.co/QGJ5xyPfvA #Docker #dockercon

[Jeff Willette @TheOneJeffrey]

@mwitkow does grpc-proxy allow regular gRPC calls as well as grpc-web? or do they have to be on different servers?