Preserving the language of black and white photography @Yale. Home to the world’s largest reference collection of photographic paper.

West Haven, CT
Joined January 2024
Lens Media Lab retweeted
In April, I published a longform essay about the use of large language models in humanistic research. In that corner of academia, there are many skeptics, and in fact, many view LLMs as riskier tech than their prelinguistic predecessors (trad ML). I argue the opposite is true
1
2
6
1,083
This talk is now up on YouTube. Check it out! youtu.be/fcqT0dNllB4?si=zQee…
SoCal folks! The lab's lead scientist, Damon Crockett, will be giving at a lecture, hosted by the UCLA/Getty Program in the Conservation of Cultural Heritage, on Tuesday, May 20. Details and RSVP in the link below.
1
2
81
The talk is Tuesday; still time to RSVP!
SoCal folks! The lab's lead scientist, Damon Crockett, will be giving at a lecture, hosted by the UCLA/Getty Program in the Conservation of Cultural Heritage, on Tuesday, May 20. Details and RSVP in the link below.
1
2
46
SoCal folks! The lab's lead scientist, Damon Crockett, will be giving at a lecture, hosted by the UCLA/Getty Program in the Conservation of Cultural Heritage, on Tuesday, May 20. Details and RSVP in the link below.
1
2
1
1
174
Harvard folks! The lab's lead scientist, Damon Crockett, is giving a talk at 11a today at the Center for Astrophysics. He'll demonstrate how to use Paperbase to explore our reference collection of photographic paper. The talk is open to the Harvard community. Details in link ⬇️
1
3
3
265
This (client side!) experiment is now live. Explore 260k public domain objects from @metmuseum across different visual feature spaces and 2D projections. Multimodal queries using @nomic_ai embedders and transformers.js from @xenovacom. Here I search for saturated coats:
14
28
2
171
15,013
"Find visually similar images." Ok but which feature space?
12
21
1
327
19,926
A new feature on Paperbase, our lab’s platform for exploring our massive reference collection of photographic papers. Check it out!
Want to explore the technical history of photography through data visualization? Natalia Kiseleva delves into Paperbase, an interactive platform and its incredible journey to analyze the world's largest collection of gelatin silver photographic papers. nightingaledvs.com/paperbase…
3
30
For those who missed this right before the holiday: if you're using vision-language models, check out our blog post!
New blog post: "Image Captioning in Hostile Conditions". Our lab ranked 10 large VLMs (3 closed, 7 open) by human-judged pairwise contests. GPT-4o won by a large margin. Molmo and Qwen, both open models, shared the next tier with Gemini and Claude. Short 🧵+🔗:
1
2
4
215
New blog post: "Image Captioning in Hostile Conditions". Our lab ranked 10 large VLMs (3 closed, 7 open) by human-judged pairwise contests. GPT-4o won by a large margin. Molmo and Qwen, both open models, shared the next tier with Gemini and Claude. Short 🧵+🔗:
1
4
1
5
618
The Lens Media Lab @IPCH_Yale has unveiled Paperbase, a visual platform for studying its unrivaled collection of photographic papers. Read more: bit.ly/lens-lab
3
3
366
Our "Darkroom To Data" symposium on August 12 was a smashing success! Videos to be released soon. Here are some photos to tide you over (credit to Jon Atherton). The event was also covered by Yale News! Link below ⬇️
1
2
3
98
Come to our August symposium, Darkroom to Data! We will discuss the past 6 years of lab research and launch Paperbase, a web platform for exploring the world’s largest collection of photographic paper. And because it’s funded by a @googlearts grant, it’s free! Link below ⬇️
1
2
1
4
648