Vik Korupati

Co-founder & CTO, Moondream · 1 appearance on the record.

computed by AI from the episodes · how this works → · full disclaimer →

founderexecutiveengineerscientist@vikhyatk ↗vikhyat.net ↗

Vik Korrapati is the creator and CTO of Moondream, an open-source vision-language model built for resource-constrained devices. Prior to Moondream, he worked on distributed computing systems at AWS for nine years and founded the platform Hummingbird.

5statements → 1claims → 0claims resolved → 3.4/5average certainty → 2/5average debate potential →

1 not checkable as stated how the 1 claim stands · each chip opens the sources

1 prediction · 1 opinion · 2 insights · 1 disclosure · every statement was checked. The prediction and assertions are the 1 claim: statements the public record can support or contradict. 0 are resolved, and 1 names no date, number or outcome precise enough to check. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

What they said5 Episodes1

Everything Vik Korupati said on Latent Space that made the record, most notable first. Filter by type, assessment or year in the ledger →

Opinion

Korupati: Vision-Language Models Are Lagging Behind LLMs in Reasoning

“LLMs are showing enormous progress in reasoning, especially with the latest set of models that we've seen, but we're not really seeing, I have a feeling that VLMs are lagging behind, as we can see with these tasks that should be very simple for a human to do t…”

Vik Korupati Dec 22, 2024 ▶ 53:01 Best of 2024 in Vision [LS Live @ NeurIPS]

Insight

Korupati: Developers Can Prototype on 2B Models and Prune for Deployment

“I think the thing that's really exciting about this is it makes it possible for developers to build using the two B per model and Just explore, build their application, and then once they're ready to deploy, figure out what exactly they need out of the model a…”

Vik Korupati Dec 22, 2024 ▶ 46:36 Best of 2024 in Vision [LS Live @ NeurIPS]

Insight

Korupati: VLMs Fail at Gauges Due to E-Commerce Training Biases

“In the case of gauges, most gauges images aren't gauges in the wild. They're product Detail images like these where it's always set to zero. It's paired with an alt text that says something like GIVTO pressure sensor PSI zero to 30 or something. And so, the mo…”

Vik Korupati Dec 22, 2024 ▶ 48:05 Best of 2024 in Vision [LS Live @ NeurIPS]

Prediction Not checkable as stated

Korupati: Visual Chain-of-Thought Will Probably Generalize Across Tasks

“The real question is, is it going to generalize? Probably, like, there's some signs from text models that when you train on a broad number of tasks, it does generalize, and I'm seeing some signs with our model as well.”

Vik Korupati Dec 22, 2024 ▶ 52:10 Best of 2024 in Vision [LS Live @ NeurIPS]

Disclosure

Korupati: Moondream built a 0.5B model by pruning its 2B model

“The way we built our model was to start with the two billion parameter model and Prune it while doing continual training to retain performance.”

Vik Korupati Dec 22, 2024 ▶ 45:46 Best of 2024 in Vision [LS Live @ NeurIPS]

Appearances (1)

Episode	Date	Speaking time
Best of 2024 in Vision [LS Live @ NeurIPS]	Dec 22, 2024	9m

Vik Korupati

Appearances (1)

Turn any episode into a week of clips.