Sign in

Kuzman Ganchev

@ganchev.bsky.social
1.5K followers 33 following 3 posts

Research Scientist at GoogleDeepMind (formerly at Google Research). UPenn graduate.

PostsRepliesMedia
Reposted by Kuzman Ganchev
Ethan Mollick @emollick.bsky.social · 04/05/2025
Study in Nature: “Across 30 out of 32 evaluation axes from the specialist physician perspective & 25 out of 26 evaluation axes from the patient-actor perspective, AMIE [Google Medical LLM] was rated superior to PCPs [primary care docs] while being non-inferior on the rest.” (& AIME is an older LLM)
47015
Reposted by Kuzman Ganchev
Gus @gusthema.bsky.social · 30/04/2025
Gemma 3 explained: Longer context, image support, and a new 1B model. → goo.gle/4lV8iaw Other key enhancements: 🔸 Best model that fits in a single consumer GPU or TPU host 🔸 KV-cache memory reduction with 5-to-1 interleaved attention 🔸 And more! Read the blog for the full details on Gemma 3.
goo.gle
Gemma explained: What’s new in Gemma 3- Google Developers Blog
Google's Gemma 3 model includes vision-language support and architectural changes for resource-friendly multimodal language models.
1228
Kuzman Ganchev @ganchev.bsky.social · 17/12/2024
There's a link to a really nice interactive viewer for a sample of the data (will only make sense after you read the post). There's some examples that I would have expected (where something is implied but not directly stated) but also a surprising number of kind of topical things.
031
Reposted by Kuzman Ganchev
Andreas Steiner @andreaspsteiner.bsky.social · 05/12/2024
Want to get started using PaliGemma 2? 🎤 developers.googleblog.com/en/introduci... 🤗 huggingface.co/blog/paligem... 💾 kaggle.com/models/googl... 🔧 github.com/google-resea... 7/7
071
Kuzman Ganchev @ganchev.bsky.social · 11/11/2024
Wanted to share that Varun Godbole recently released a prompting playbook. The title says prompt tuning, but this is text prompts, not soft prompts. github.com/varungodbole...
github.com
GitHub - varungodbole/prompt-tuning-playbook: A playbook for effectively prompting post-trained LLMs
A playbook for effectively prompting post-trained LLMs - varungodbole/prompt-tuning-playbook
0147
Reposted by Kuzman Ganchev
Jacob Eisenstein @jacobeisenstein.bsky.social · 24/10/2024
I’m pretty excited about this one! ALTA is A Language for Transformer Analysis. Because ALTA programs can be compiled to transformer weights, it provides constructive proofs of transformer expressivity. It also offers new analytic tools for *learnability*. arxiv.org/abs/2410.18077
arxiv.org
ALTA: Compiler-Based Analysis of Transformers
We propose a new programming language called ALTA and a compiler that can map ALTA programs to Transformer weights. ALTA is inspired by RASP, a language proposed by Weiss et al. (2021), and Tracr (Lin...
25316
Kuzman Ganchev @ganchev.bsky.social · 25/10/2024
Not news, but I recently saw the zed.dev demo and it looks amazing. Has anyone used it or something similar?
zed.dev
Zed - The editor for what's next
Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.
030