Peter Robicheaux

Roboflow · 1 appearance on the record.

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

7statements → 5claims → 5claims resolved → 100%fully supported → 3.71/5average certainty → 2/5average debate potential →

5 supported 0 partly supported 0 contradicted how the 5 claims stand · each chip opens the sources

5 assertions · 1 opinion · 1 insight · every statement was checked. The predictions and assertions are the 5 claims: statements the public record can support or contradict. 5 are resolved. Everything else (opinions, insights, what ifs, disclosures) can never be settled by the record, so it carries no assessment.

The record, in short

What the tape says about how Peter argues and how the claims held up. Everything they said, and everything said about them, is in the tabs below.

Their most notable supported claim

Assertion Supported

Robicheaux: 2B PaliGemma 2 Beats ChatGPT on MMVP with 47.3%

“The big result, and one of the reasons that I was really excited about this paper, is that they blow everything else away on MMVP. I mean, 47.3, sure, that's nowhere near human accuracy, which again is 94%, but for, you know, two billion language, two billion …”

Peter Robicheaux Dec 22, 2024 ▶ 34:28 Best of 2024 in Vision [LS Live @ NeurIPS]

Expressed certainty vs assessment result

none yet certainty 1

none yet certainty 2

100% certainty 3

100% certainty 4

100% certainty 5

weighted support: a fully supported claim counts one, a partly supported claim counts half. Each filled bar is clickable and opens exactly those claims; "none yet" means nothing said at that certainty level has resolved yet

What they said7 Episodes1

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

Assertion Supported

Robicheaux: 2B PaliGemma 2 Beats ChatGPT on MMVP with 47.3%

Peter Robicheaux Dec 22, 2024 ▶ 34:28 Best of 2024 in Vision [LS Live @ NeurIPS]

Assertion Supported

Robicheaux: AIMv2 Avoids Performance Saturation as Scale Increases

“And we can see that this is finally a model that doesn't saturate. It's even at the highest parameter count, it's, it appears to be Well, at the highest parameter account, it appears to be improving in performance with more and more samples seen”

Peter Robicheaux Dec 22, 2024 ▶ 36:43 Best of 2024 in Vision [LS Live @ NeurIPS]

Opinion

Robicheaux: Convolutional models fail to benefit from pre-training compared to transformers

“Essentially, I think it's kind of been shown now that convolution models, like, just don't benefit from pre-training and just don't, like, have the level of intelligence to transform models.”

Peter Robicheaux Dec 22, 2024 ▶ 42:00 Best of 2024 in Vision [LS Live @ NeurIPS]

Insight

Robicheaux: CLIP encoders lack fine-grained visual features due to caption-matching objective

“Models that have been initialized with Clip as their vision encoder, they don't have fine-grained details and the features extracted using Clip because Clip sort of doesn't need to find these fine grade details to do its job correctly, which is just to match c…”

Peter Robicheaux Dec 22, 2024 ▶ 22:21 Best of 2024 in Vision [LS Live @ NeurIPS]

Assertion Supported

Robicheaux: Adding DINOv2 features degrades multimodal language modeling performance

“As you increase the number of Dynav two features, your model does worse and worse and worse on the actual language modeling task, and that's because Dynav two features were trained completely from a self-supervised manner and completely in image space. It know…”

Peter Robicheaux Dec 22, 2024 ▶ 25:41 Best of 2024 in Vision [LS Live @ NeurIPS]

Assertion Supported

Robicheaux: PaliGemma 1 Pre-Training Saturates at 300M Examples

“One of my critiques, I guess, of polygeoma one, at least, is that you find that performance saturates as a pre-trained model after only three hundred million examples seen.”

Peter Robicheaux Dec 22, 2024 ▶ 32:52 Best of 2024 in Vision [LS Live @ NeurIPS]

Assertion Supported

Robicheaux: Florence-2 Achieves 60% mAP on COCO

“They get 60%, 60% map on Cocoa, which is, like, approaching state of the art, and they train with... You're good. And they train with a much more much more efficiently.”

Peter Robicheaux Dec 22, 2024 ▶ 29:37 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	17m

Peter Robicheaux

The record, in short

Their most notable supported claim

Expressed certainty vs assessment result

Appearances (1)

Turn any episode into a week of clips.