Jeff Willette (@TheOneJeffrey) profile picture
Joined May 2012
Photo by Jeff Willette (@TheOneJeffrey)
Jeff Willette retweeted
Our Agent Distillation paper is accepted at #NeurIPS2025 Spotlight! 🚀 Turn your small LM into a strong agent 💪 Code: github.com/Nardien/agent-dis…
🚨 New preprint! Can small language models (sLMs) solve complex problems like LLMs? We show how to go beyond cloning reasoning—to distill tool-using agent behavior into sLMs as tiny as 0.5B. Meet Agent Distillation: 📄 huggingface.co/papers/2505.1… Here's the details 🧵👇:
3
12
89
8,309
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) arxiv.org/pdf/2505.11254
1
7
1
16
1,325
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...
1
61
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.
47
Jeff Willette retweeted
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. 😊
1
5
69
3,001
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! huggingface.co/papers/2505.1…
3
1
11
661
I just published “Tern: Why it Breaks and How To Fix it” medium.com/p/tern-why-it-bre…
Check out my project docker-alertd, and alert daemon for docker #Docker #dockermonitoring xitter.gq/awesome_docker/status/…
Latest Awesome #Docker List commit - Docker-Alertd: Send Alerts Based on Container Usage/Statistics docker-alertd: - is extremely light