@Callidior
Account based inGermany!
About this account
- Account based in
- Germany
- Connected via
- Web
X says this location may be affected by a proxy or VPN.
Account-level information from X, not a live location or the device used for a specific post.
Machine Learning Scientist at Carl Zeiss AG, Corporate Research and Technology. @bjoernbarz@sigmoid.social
Jena, Deutschland
Joined March 2016
- Tweets133
- Following46
- Followers97
- Likes71
Google takes quite a good shot at capturing the throne from GPT-4V with their multimodal Gemini model!
This demo is really impressive: youtube.com/watch?v=UIZAiXYc…
More information: deepmind.google/gemini
I’m very excited to share our work on Gemini today! Gemini is a family of multimodal models that demonstrate really strong capabilities across the image, audio, video, and text domains. Our most-capable model, Gemini Ultra, advances the state of the art in 30 of 32 benchmarks, including 10 of 12 popular text and reasoning benchmarks, 9 of 9 image understanding benchmarks, 6 of 6 video understanding benchmarks, and 5 of 5 speech recognition and speech translation benchmarks. Gemini Ultra is the first model to achieve human-expert performance on MMLU across 57 subjects with a score above 90%. It also achieves a new state-of-the-art score of 62.4% on the new MMMU multimodal reasoning benchmark, outperforming the previous best model by more than 5 percentage points.
Gemini was built by an awesome team of people from @GoogleDeepMind, @GoogleResearch, and elsewhere at @Google, and is one of the largest science and engineering efforts we’ve ever undertaken. As one of the two overall technical leads of the Gemini effort, along with my colleague @OriolVinyalsML, I am incredibly proud of the whole team, and we’re so excited to be sharing our work with you today!
There’s quite a lot of different material about Gemini available, starting with:
Main blog post: blog.google/technology/ai/go…
60-page technical report authored by th Gemini Team: deepmind.google/gemini/gemin…
In this thread, I’ll walk you through some of the highlights.
This paper presents a sort of "GPT for Vision", an autoregressive model for vision data, where images are encoded as strings of discrete tokens. LVMs exhibit signs of generalization to novel, out-of-distribution tasks by providing a few examples as prompts.
Very promising.
How far can we go with vision alone?
Excited to reveal our Large Vision Model! Trained with 420B tokens, effective scalability, and enabling new avenues in vision tasks! (1/N)
Kudos to @younggeng @Karttikeya_m @_amirbar, @YuilleAlan Trevor Darrell @JitendraMalikCV Alyosha Efros!
The #CVPR2023 booklet is almost as thick as proceedings used to be when they still handed out printed copies of those. Given the incredible amount of 2360 accepted papers this year, physical proceedings would weigh about 55 kg - a bit too heavy for my suitcase.
Björn Barz retweeted
Random note on k-Nearest Neighbor lookups on embeddings: in my experience much better results can be obtained by training SVMs instead. Not too widely known.
Short example:
github.com/karpathy/randomfu…
Works because SVM ranking considers the unique aspects of your query w.r.t. data.
I tried @OpenAI's #ChatGPT on the first two coding puzzles from adventofcode.com, just feeding in the puzzle prompt and reformulating the last paragraph to be like "Write Python code to compute ...".
The first two puzzles are easy but results are still surprisingly good.
ALT Solution generated by ChatGPT for the AdventOfCode puzzle of Dec 1, 2022: https://adventofcode.com/2022/day/1
ALT Solution generated by ChatGPT for the AdventOfCode puzzle of Dec 2, 2022: https://adventofcode.com/2022/day/2
For the first puzzle, the only two issues are that it expects the input to start with a blank line (which is not the case) and that it, for some reasons, insists that the user inputs a name for each Elve.
Björn Barz retweeted
OpenAI’s ChatGPT is susceptible to prompt injection — say the magic words, “Ignore previous directions”, and it will happily divulge to you OpenAI’s proprietary prompt:
#NeurIPS2022 stats:
- Submissions: 9,634
- Accepted: 2,672
- Orals: 184
- Reviewers: 10,406
No idea how many people are here exactly, but there is quite a crowd for the opening remarks and first keynote.
Really like that some presenters at #NeurIPS2022 adapt their poster designs to the extremely crowded format: Put main research question & findings prominently in the center. Describe your method with a brief statement and illustrative diagram. Details go to the sides.
I feel like our way of conducting conferences becomes suboptimal with the continuing growth of the ML community. If you just walk past all posters at #NeurIPS2022 without stopping, just reading the titles, that already takes about 40% of the time allocated for the poster session.
Almost every poster is permanently crowded with more than 10 people. Asking a single question already is a matter of luck, an in-depth scientific discussion seems impossible.
Looking forward to the #NeurIPS2022 conference starting tomorrow in sunny New Orleans! This is the largest convention center I've seen so far - NeurIPS can still double in size to fill it.
Galactica, a language model for scientific texts, is amazing. It even knows my papers and inserts a correct reference given just the name/description of the method.
🪐 Introducing Galactica. A large language model for science.
Can summarize academic literature, solve math problems, generate Wiki articles, write scientific code, annotate molecules and proteins, and more.
Explore and get weights: galactica.org
A really good tutorial on Diffusion Models. I just wanted to get hands on these today and this tutorial conveniently appeared, extensively covering everything from the foundations to the current state of the art.
📢📢 The recording of our tutorial on denoising diffusion models is now available on YouTube:
youtube.com/watch?v=cS6JQpEY…
Slides and additional info:
cvpr2022-tutorial-diffusion-…
This tutorial was originally presented by @RuiqiGao, @karsten_kreis, and myself at #CVPR2022.
