Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

ai.googleblog.com

Post reply on HN
Print view View original

11–20 of 36 posts

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#11

Post by esafak »

fpgaminer wrote: post #9
gs17 wrote: post #4

Earlier quoted context omitted.

I don't even bother with the "astounding" things unless there's code. MusicLM was cool, but without code/weights it might as well be a hoax.

Yeah, these days I'm "over" Google's AI research. All their papers sound cool, and they've got nice pictures/audio/etc. But nothing meaningful has ever materialized from Google. OpenAI is killing it with ChatGPT, a publicly accessible product with research papers that have been reproduced. Facebook released huge LLMs for free. Stability released successful image models for free. etc. Meanwhile Google has ... Tensorfl…

> Remember when Google said they were going to have an AI call your hair salon and make appointments for you?

I think that ran into social problems, not technical ones.

https://www.theverge.com/2019/5/9/18538194/google-duplex-ai-...

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#12

Post by alsodumb »

fpgaminer wrote: post #10
alsodumb wrote: post #8

Earlier quoted context omitted.

Researchers always have a lot to take away from Google papers that don’t release code or dataset - people understand that sometimes folks at companies sometimes cannot release the code or dataset. Doesn’t make any key contributions less meaningful - if that was the case, all conferences would have banned papers that don’t release code and dataset by now.

Conferences _should_ ban papers that don't release code or other means of reliable reproduction. The only reason they don't is because "research" in ML has more or less been a joke compared to any other established scientific field. And I'm not going to give Google the benefit of the doubt. At the very least I'll treat them like any random stranger publishing a paper. But in reality I treat their papers with a heavy…

Funny you compare ML with other fields - in my experience ML is the most open and reproducible area of scientific research, by far. Talk to researchers in other areas, many write “dataset and code available by request” but never share it, have custom CFS solvers and write papers with it but never release the code, and do experiments and leave out all details in the paper making it impossible to reproduce.

You are free to treat a paper from Google like a paper from any random stranger, sure. But it doesn’t change the fact that many ML researchers I know in my R1 University (and many other top universities) always mention how much insights they get from these papers even when they couldn’t always release the code/models.

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#14

Post by reaperman »

fpgaminer wrote: post #7
skybrian wrote: post #5

Earlier quoted context omitted.

I wish people would stop with these shallow, boring dismissals. It's a research paper, not a product. While it's disappointing that they don't release more, it's good that they share their ideas.

A research paper by itself isn't worth nothing, sure, but without the ability to reproduce the paper or even check their results it's ... not worth much.

The architecture is described enough to re-implement it and train it on known datasets/benchmarks such as VQA2. A single man with a medical degree named Phil Wang ('lucidrains')[0] has the ability to reproduce most of these papers by himself. He has 246 GitHub repos[1], most of which appear to be reproductions of models which are only described in papers that had no associated code or models released, such as [2]. Often it appears he releases code within 2 weeks of a paper's publication on ArXiv.

0: https://lucidrains.github.io

1: https://github.com/lucidrains

2: https://paperswithcode.com/paper/coca-contrastive-captioners...

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#15

Post by gremlinsinc »

gs17 wrote: post #4
light_hue_1 wrote: post #3

Earlier quoted context omitted.

That's Google. I don't bother to read most Google papers unless someone tells me that they're doing something astounding. Just because I know I don't have access to their models, their code or their data. So what's the point? As a community we need to stop accepting and stop citing papers like these. There is no science without replicability, and it is literally impossible to replicate this work. It's not worth the p…

I don't even bother with the "astounding" things unless there's code. MusicLM was cool, but without code/weights it might as well be a hoax.

yeah they were supposed to have the next big image thing, OMG it can do text, and stable diffusion beat them to releasing something that actually can render text on images, so yeah - there's a lot of young companies iterating way faster than an old guard can muster up the troops and honestly I don't think anyone at Google feels inspired much these days, hard to build some passionate endeavors when your soul is being sucked right out of you.

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#16

Post by rvcdbn »

skybrian wrote: post #5
frisco wrote: post #2

Is there anything actually released here? Just a paper? No weights, not even code ?! No interactive product of any kind? The degree of Google’s inability to actually ship anything even now is totally mindblowing

I wish people would stop with these shallow, boring dismissals. It's a research paper, not a product. While it's disappointing that they don't release more, it's good that they share their ideas.

I think these are both important perspectives. There’s a real societal cost to having some of the best AI researchers with a golden gag only able to share limited details about their work the main bulk of which remains behind closed doors. If we don’t impose social costs to this behavior it will become even more common.

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#17

Post by ukuina »

skybrian wrote: post #5
frisco wrote: post #2

Is there anything actually released here? Just a paper? No weights, not even code ?! No interactive product of any kind? The degree of Google’s inability to actually ship anything even now is totally mindblowing

I wish people would stop with these shallow, boring dismissals. It's a research paper, not a product. While it's disappointing that they don't release more, it's good that they share their ideas.

I'm not against them publishing papers without code, but if they tout the paper on their blog, the onus is on them to publish things of consequence.

Re: MaMMUT: A simple vision-encoder text-decoder architecture for multimodal tasks

#20

Post by nl »

frisco wrote: post #2

Is there anything actually released here? Just a paper? No weights, not even code ?! No interactive product of any kind? The degree of Google’s inability to actually ship anything even now is totally mindblowing

This is absolutly wrong.

Google (and other large industry labs) have the budget and resources to experiment.

They should be encouraged and thanked for publishing what works.

It's not super hard to reimplement a published paper. But running multiple experiments is hard for individuals or smaller companies.

Post reply on HN