[HN Gopher] Generative Models: What do they know? Do they know t...
       ___________________________________________________________________
        
       Generative Models: What do they know? Do they know things? Let's
       find out
        
       Author : corysama
       Score  : 348 points
       Date   : 2024-02-23 22:46 UTC (1 days ago)
        
 (HTM) web link (intrinsic-lora.github.io)
 (TXT) w3m dump (intrinsic-lora.github.io)
        
       | goryramsy wrote:
       | SSL error? Just me?
        
         | corysama wrote:
         | Works on my machine. Alternative link:
         | https://github.com/duxiaodan/intrinsic-lora
        
         | 01HNNWZ0MV43FF wrote:
         | Works here. "Verified by DigiCert". SHA-256 fingerprint of 38:2
         | C:D4:2D:33:C0:2B:C6:67:8E:65:7C:E1:7B:84:6D:04:73:A7:E7:91:CD:B
         | 3:5B:8E:AD:90:1A:F1:E1:1A:08
        
       | dkarras wrote:
       | This is pretty remarkable. So these really do learn humanly
       | interpretable representations and not only doing some magic in
       | the billion dimensional hyperplane that we can't hope of
       | deciphering.
        
         | corysama wrote:
         | As an old 3D graphics engineer, the fact that albedo is in
         | there is as just striking as it should be expected.
         | 
         | The core components of physically based rendering are position
         | (derivable from image XY and depth), surface normal, incoming
         | light, and at least albedo + one of a few variations on surface
         | material properties such as specularity and roughness.
         | 
         | That the AI is modeling depth is pretty expected. Modeling
         | surface normal is a nice local convolution of depth. But,
         | modeling albedo separated from incoming light is great. I
         | wonder if specularity is hiding in there too.
        
           | hackerlight wrote:
           | It's a _good_ depth map, too. Better than other tools I 've
           | seen which require fiddling with lots of knobs to get a good
           | result. Might be useful for textures for parallax mapping.
        
           | viraptor wrote:
           | I'm mostly ok with the idea that the text-to-image models do
           | this. What blows me away is that the autoregressive model
           | does it too. We're not even asking it to produce a specific
           | object which has a meaning or context assigned. The network
           | learned to produce those representations as just "this is a
           | useful decomposition if I want to recreate the same thing
           | again". The jump from image compression to figuring out how
           | to represent objects in space is insane. And makes me want to
           | feed some optical illusions through that network - what's the
           | depth map of the infinite staircase?
        
         | int_19h wrote:
         | I find it amazing that, for all the evidence we have of
         | generative models having some fairly complex internal model of
         | the world, people still insist that they are mere "stochastic
         | parrots" who "don't really understand anything".
        
           | mewpmewp2 wrote:
           | From the other side however if you really think about it, our
           | understanding of everything must be stochastic as well. So
           | perhaps this sort of thing yields in many complexities that
           | we are not aware of. How would I know I am not a stochaistic
           | parrot of some sort. I am just neural nets traine on current
           | envrionment while the base model that is dependent on DNA,
           | through evolution and natural selection of the fittest. Same
           | as currently competing LLMs where the best one will win out.
        
             | int_19h wrote:
             | You're not wrong, but the "stochastic parrot" claim always
             | comes with another, implicit one that _we_ are not like
             | that; that there 's some fundamental difference, somehow,
             | even if it is not externally observable. Chinese room etc.
             | 
             | In short, it's the good old religious debate about souls,
             | just wrapped in techno-philosophical trappings.
        
               | cthalupa wrote:
               | You could leverage the exact same accusation against the
               | other side - we know fundamentally how the math works on
               | these things, yet somehow throw enough parameters at them
               | and eventually there's some undefined emergent behavior
               | that results in something more.
               | 
               | What that something more is is even less defined with
               | even fewer theories as to what it is than there are
               | around the woo and mysticism of human intelligence. And
               | as LarsDu88 points out in a separate thread, there are
               | alternative explanations for what we're seeing here
               | besides "We've created some sort of weird internal 3D
               | engine that the diffusion models use for generating
               | stuff," which also meshes closely with the fact that
               | generations routinely have multiple perspectives and
               | other errors that wouldn't exist if they modeled the
               | world some people are suggesting.
               | 
               | If there's something more going on here, we're going to
               | need some real explanations instead of things that can be
               | explained multiple other ways before I'm going to take it
               | seriously, at least.
        
               | int_19h wrote:
               | > somehow throw enough parameters at them and eventually
               | there's some undefined emergent behavior that results in
               | something more.
               | 
               | But the other side doesn't see it that way, specifically
               | not the "something more" part. It's "just math" all the
               | way down, in our brains as well. The "emergent phenomena"
               | are not undefined in this sense - they're (obviously in
               | LLMs) also math, it's just that we don't _understand_ it
               | yet due to the sheer complexity of the resulting system.
               | But that 's not at all unusual - humans build useful
               | things that we don't fully understand all the time (just
               | look at physics of various processes).
               | 
               | > which also meshes closely with the fact that
               | generations routinely have multiple perspectives and
               | other errors that wouldn't exist if they modeled the
               | world some people are suggesting.
               | 
               | This implies that the model of the world those things
               | have either has to be perfect, or else it doesn't exist,
               | which is a premise with no clear logic behind it. The
               | obvious explanation is that, between the limited amount
               | of information that can be extracted from 2D photos that
               | the NN is trained on, and the limit on the complexity of
               | world modeling that NN of a particular size can fit, its
               | model of the world is just not particularly accurate.
               | 
               | > we're going to need some real explanations instead of
               | things that can be explained multiple other ways before
               | I'm going to take it seriously, at least.
               | 
               | If we used this threshold for physics, we'd have to throw
               | out a lot of it, too, since you can always come up with a
               | more complicated alternative explanation; e.g. aether can
               | be viable if you ascribe just enough special properties
               | to it. Pragmatically, at some point, you have to pick the
               | most likely (usually this means the simplest) explanation
               | to move forward.
        
               | peterashford wrote:
               | I dont think that's the core of the objection at all.
               | I've never seen it made by people pushing the idea that
               | AGI is impossible, just that AI approaches like LLM are a
               | lot more limited than they appear - basically that most
               | of the Intelligence they exhibit is that found in the
               | training data.
        
               | mrkstu wrote:
               | Well, the question then becomes, what is the upper limit
               | of a baby human raised by monkeys without human contact?
               | 
               | Will that baby automatically become a complex tool user
               | with a better comprehension of the world around it than
               | the monkeys in its group?
               | 
               | How responsible is the 'training data' in it's
               | environment responsible for human intelligence?
        
               | anon291 wrote:
               | As someone teaching their five year old to read, I think
               | people way underestimate the amount of training data the
               | average human child gets. And perhaps, since we live in a
               | first world country with universal education, and a very
               | rich one at that, many people have not seen what happens
               | when kids don't get that training data.
               | 
               | It's also not just the qualia of sensation, but also that
               | of the will. We all 'feel' we have a will, that can do
               | things. How can a computer possibly feel that? The 'will'
               | in the LLM is forced by the selection function, which is
               | a deterministic, human-coded algorithm, not an intrinsic
               | property.
               | 
               | In my view, this sensation of qualia is so out-there and
               | so inexplicable physically, that I would not be able to
               | invalidate some 'out there' theories. If someone told me
               | they posited a new quantum field with scalar values of
               | 'will' that the brain sensed or modified via some quantum
               | phenomena, I'd believe them, especially if there was an
               | experiment. But even more out there explanations are
               | possible. We have no idea, so all are impossible to
               | validate / invalidate as far as I'm concerned.
        
               | mewpmewp2 wrote:
               | But in which way isn't most of our Intelligence not what
               | is from training data?
               | 
               | 1st evolutionary algorithm and then the constant input we
               | receive from the World being the training data and we
               | having reward mechanisms rewiring our neural networks
               | based on what our senses interpret as good?
        
               | anon291 wrote:
               | The fundamental difference is qualia, which is physically
               | inexplicable, and which LLMs and neural networks show no
               | sign of having. It's not even clear how we would know if
               | it did. As far as I can tell, this is something that
               | escapes all current models of the physical universe,
               | despite what many want to believe.
        
           | wredue wrote:
           | We have zero evidence that these models have any
           | "understanding" of anything.
           | 
           | "Understanding" would mean that they be able to train
           | themselves, which they are as yet unable to do.
           | 
           | We are tuning weights and biases to statistically regurgitate
           | training data. That is all they are.
        
             | huytersd wrote:
             | No, you can have abstract representations of a concept
             | which would fit understanding in a certain sense of the
             | word. You can have "understanding" of a concept without an
             | overarching self aware hypervisor. It's like isolating a
             | set of neurons in your brain that represent an idea.
        
             | visarga wrote:
             | So, in order for a kid to understand multiplication means
             | they must be able to train themselves and not regurgitate
             | the multiplication table?
        
               | ipaddr wrote:
               | Yes I think so. Understanding would involve understanding
               | that it's a short form for adding. Remembering
               | multiplication tables allows you to use math but it
               | doesn't infer understanding.
               | 
               | Training themselves is necessary. All learning is self
               | learning. Teachers can present material in different ways
               | but learning is personal. No one can force you to learn
               | either.
        
               | visarga wrote:
               | You can check if a model (or a kid) understands
               | multiplication by simply probing them with questions, to
               | explain the concept in their own words, or on concrete
               | examples. If their answers are robust they understand, if
               | their answers are fragile and very input dependent, they
               | don't.
               | 
               | "To understand" is one of those poorly defined concepts,
               | like "consciousness", it is thrown a lot in the face when
               | talking about AI. But what does it mean actually? It
               | means to have a working model of the thing you are
               | understanding, a causal model that adapts to any new
               | configuration of the inputs reliably. Or in other words
               | it means to generalize well around that topic.
               | 
               | The opposite would be to "learn to the test" or "overfit
               | the problem" and only be able to solve very limited cases
               | that follow the training pattern closely. That would make
               | for brittle learning, at surface level, based on
               | shortcuts.
        
               | int_19h wrote:
               | > It means to have a working model of the thing you are
               | understanding, a causal model that adapts to any new
               | configuration of the inputs reliably
               | 
               | The weasel word here is "reliably". What does this
               | actually mean? It obviously cannot be reliable in a sense
               | of always giving the correct result, because this would
               | make understanding something a strict binary, and we
               | definitely don't treat it like that for humans - we say
               | things like "they understand it better than me" all the
               | time, which when you boil it down has to mean "their
               | model of it is more predictive than mine".
               | 
               | But then if that is a quantifiable measure, then we're
               | really talking about "reliable enough". And then the
               | questions are: 1) where do you draw that line, exactly,
               | and 2) even more importantly, _why_ do you draw the line
               | there and not somewhere else.
               | 
               | For me, the only sensible answer to this is to refuse to
               | draw the line at all, and just embrace the fact that
               | understanding is a spectrum. But then it doesn't even
               | make sense to ask questions like "does the model _really_
               | understands? " - they are meaningless.
               | 
               | (The same goes for concepts like "consciousness" or
               | "intelligence", by the way.)
               | 
               | The reason why I think this isn't universally accepted is
               | because it makes us not special, and humans really,
               | _really_ like to think of themselves as special (just
               | look at our religions).
        
               | haswell wrote:
               | > _It obviously cannot be reliable in a sense of always
               | giving the correct result, because this would make
               | understanding something a strict binary_
               | 
               | Our capacity to make mistakes does not necessarily equate
               | to a lack of understanding.
               | 
               | If you're doing a difficult math problem and get it
               | wrong, that doesn't necessarily imply that you don't
               | understand the problem.
               | 
               | It speaks to a limitation of our problem solving
               | machinery and the implements we use to carry out tasks.
               | 
               | e.g. if I'm not paying close enough attention and write
               | down the wrong digit in the middle of solving a problem,
               | that could also just be because I got distracted, or made
               | a mistake. If I did the same problem again from scratch,
               | I would probably get it right if I understand the subject
               | matter.
               | 
               | Limitations of our working memory, how distracted we are
               | that day, mis-keying something on a calculator or writing
               | down the wrong digit, etc. can all lead to a wrong
               | answer.
               | 
               | This is distinct from encountering a problem where one's
               | understanding was incomplete leading to consistently
               | wrong answers.
               | 
               | There are clearly people who are better and worse
               | comparatively at solving certain problems. But given the
               | complexity of our brains/biology, there are myriad
               | reasons for these differences.
               | 
               | Clearly there are people who have the capacity to
               | understand certain problems more deeply (e.g. Einstein),
               | but all of this was primarily to say that output doesn't
               | need to be 100% "reliable" to imply a complete
               | understanding.
        
               | int_19h wrote:
               | Indeed, but I wasn't talking about mistakes at all, but
               | specifically about the case when "A understands X better
               | than B does", which _is_ about their mental model of X. I
               | hope you won 't dispute that 1) we do say things like
               | that all the time about people, and 2) most of us
               | understand what this means, and it's not just about
               | making fewer mistakes.
        
               | mardef wrote:
               | I wouldn't call someone reciting a French-English
               | dictionary a French speaker that understands the
               | language.
               | 
               | Other way around. If a kid understood the concepts of
               | multiplation, they could train themselves on the next
               | logical steps like exponents.
               | 
               | The consequences of this in the terms of AI would mean
               | they build on a series of concepts and would quickly
               | dwarf us in intelligence.
        
               | kenjackson wrote:
               | How many people years existed between the time people
               | discovered multiplication and then exponentiation? Did it
               | happen in wall clock time in a single generation?
        
               | wizzwizz4 wrote:
               | > _How many people years existed between the time people
               | discovered multiplication and then exponentiation?_
               | 
               | We don't know, because these concepts were discovered
               | before writing. We _do_ know that far larger jumps have
               | been made by individual mathematicians who never made it
               | past 33 years of age.
        
               | int_19h wrote:
               | Neither would I. But if someone who can translate a
               | French sentence into English preserving the meaning most
               | of the time, I think it would be reasonable to say that
               | this person understands French. And that is what we're
               | talking about here - models _do_ produce correct output
               | much of the time, even when you give them input that was
               | not present in their training data. The  "stochastic
               | parrot" argument is precisely the claim that this still
               | does not prove understanding. The "Chinese room" argument
               | takes it one notch further and claims that even if the
               | translation is 100% correct 100% of the time, that
               | _still_ doesn 't prove understanding.
        
             | esafak wrote:
             | I don't buy that definition of understanding. Yours is
             | closer to learning. If you had an accident and lost the
             | ability to learn new things, you would still be able to
             | understand based on what you have learnt so far. And that's
             | what these models are like. They don't retrain themselves
             | because we haven't told them to.
        
             | chaxor wrote:
             | While I agree with the hidden statement of the utility in
             | online reinforcement learning here, it should be pointed
             | out that for some snapshot of a system, which may have
             | already been trained with a large amount of data - the
             | structure of the learned space and the inferences within it
             | seem like a reasonable definition for 'understanding'.
             | 
             | I don't know many people that would suggest that knowing
             | about ones family structure, such as their mom/dad/uncle,
             | and how their history relates to them, is _required_ to be
             | _completely reconstructed_ every time they interact with
             | their environment somehow from first principles.
             | 
             | Online reinforcement learning can have large merits without
             | resorting to stating it's required for learning. Just as
             | self awareness can occur independently of consciousness can
             | occur independently of intelligence is independent of
             | empathy and so on. They are all different, and having one
             | component doesn't mean anything about the rest.
        
           | asadotzler wrote:
           | Well, when the cherry picked videos from OpenAI have a cat
           | springing a fifth leg for no reason, people are right to be
           | skeptical.
        
             | anon291 wrote:
             | I have several thoughts on the concept of 'hallucination'.
             | Firstly, most people do it regularly. I'm not sure why this
             | alone is indicative of not understanding. Secondly, if we
             | think about our dreams (the closest we can get, in my view,
             | to making the human brain produce images without physical
             | reality interfering), then actually we make very similar
             | hallucinations. When you think about your dreams and think
             | about the details, sometimes there are things that just
             | kind of happen and make sense at the time, but when you
             | look further, you're kind of like 'huh, that was strange'.
             | 
             | The images we get from these neural networks are trained on
             | looking pleasing, for some definition of pleasing. That's
             | why they look good on the whole, but get into that uncanny
             | valley the moment you go inspecting. Similar to dreams.
             | 
             | Whereas obviously real human perception is (usually)
             | grounded in reality.
        
       | bbor wrote:
       | I have no idea what Toyota or adobe are up to and why they're
       | funding research with a name like this, but I fucking love it.
       | It's science, let's get some whimsy back in here!!
       | 
       | More materially:                 Optimized with a small set of
       | labeled images, our model-agnostic approach adapts to various
       | generative architectures, including Diffusion models, GANs, and
       | Autoregressive models.
       | 
       | Am I correct in understanding that this is purely a visuospatial
       | tool, and the examples aren't just visual by coincidence? Like,
       | there's no way to stretch this to text models? Very new to this
       | interpretability approach, very impressive.
        
         | raincole wrote:
         | Bojack Horseman reference that we didn't know we need.
        
           | seattle_spring wrote:
           | What is this, a crossover episode?
        
         | sp332 wrote:
         | There's research into editing facts in language models.
         | https://rome.baulab.info/
        
         | frri wrote:
         | Si hzux
        
         | blovescoffee wrote:
         | You have no idea why Toyota or Adobe are funding computer
         | vision research?
        
           | bbor wrote:
           | lol yeah a little. A) it said something very odd sounding
           | like "Toyota university of Chicago", which wtf why does
           | Toyota have a university, and B) most labs would be hesitant
           | to publish a paper with an extraneous clause in the title
           | just to reference an absurd cartoon
        
       | dougmwne wrote:
       | This is awesome!
       | 
       | So one of the big reasons there was hype about Sora is that it
       | felt very likely from watching a few videos that there was an
       | internal physical simulation of the world happening and the video
       | was more like a camera recording that physical and 3D scene
       | simulation. It was just a sort of naive sense that there HAD to
       | be more going on behind the scenes than gluing bits of other
       | videos together.
       | 
       | This is evidence, and it's appearing even in still image
       | generators. The models essentially learn how to render a 3D scene
       | and take a picture of it. That's incredible considering that we
       | weren't trying to create a 3D engine, we just threw a bunch of
       | images at some linear algebra and optimized. Out popped a world
       | simulator.
        
         | ClumsyPilot wrote:
         | Well we do have game engines for a while now. Maybe a game
         | engine with a chat interface would do a better job
        
           | TheDudeMan wrote:
           | Depends on whether your goal is to render a scene or push the
           | envelope in generative AI.
        
           | 3abiton wrote:
           | I think is the key, most likely it was a big part of their
           | training dataset.
        
         | patcon wrote:
         | > we weren't trying to create a 3D engine, we just threw a
         | bunch of images at some linear algebra and optimized. Out
         | popped a world simulator.
         | 
         | Heh. Sounds like what a personified evolution might say about a
         | mind ;)
        
         | whimsicalism wrote:
         | > just a sort of naive sense that there HAD to be more going on
         | behind the scenes than gluing bits of other videos together
         | 
         | People really still think that's all thats happening?
        
           | 0_____0 wrote:
           | Who is people? Most folks only vaguely know about generative
           | AI if they know about it at all. I'm technical but not in
           | software specifically and usually ignore most AI news, so
           | GP's comment is in fact news to me!
        
           | sigmoid10 wrote:
           | There's a lot of nonsensical babble out there from people who
           | have minimal technical insight - both on the sceptic and on
           | the enthusiast side of AI.
           | 
           | It really wasn't clear for the longest time how these models
           | generate things so well. Articles like this one are still
           | rare and comparatively new. And they certainly haven't been
           | around when less informed enthusiasts where already heralding
           | AGI.
           | 
           | On the other hand, we have accrued quite a bit of evidence by
           | now that these models do far more than glue together training
           | data. But there are still sceptics out there who spread this
           | sort misinformation.
        
             | beepbooptheory wrote:
             | Citations for that last claim?
        
               | taneq wrote:
               | I think the Othello paper is the go-to for proving that
               | transformer networks do actually create internal models
               | of the things they're trained on.
               | 
               | https://thegradient.pub/othello/
        
               | viraptor wrote:
               | This post we're commenting on. Also
               | https://www.neelnanda.io/mechanistic-
               | interpretability/othell...
               | 
               | Also, there's a paper I can't find now which shows you
               | can find the name of the operation in the middle layers
               | if you provide example of what to do. That is, if you
               | prompt: "9 2 5 -> 5 2 9, 0 7 3 ->", you'll find the
               | internals generate "reverse" even though it doesn't
               | appear in the output.
        
               | dartos wrote:
               | So you can programmatically approximate the scene
               | intrinsics in this paper with traditional programs as
               | well given a single image.
               | 
               | All these scene data is already suggested by the data,
               | what the AI model is doing is approximating the data it
               | needs to generate a scene.
               | 
               | It's not just gluing data together, it's discovering
               | interrelationships in a very high dimensional feature
               | space. It's not creating anything it hasn't seen either,
               | which is why many image models (mostly smaller ones) have
               | so much trouble with making fine details make sense, but
               | are good with universal patterns like physics, lighting,
               | the human shape, and composition.
               | 
               | (not sure if you were trying to imply that, but it felt
               | like it)
        
               | DinaCoder99 wrote:
               | If you try it with a longer sequence of numbers it seems
               | to stumble. E.g. here's what gemini spits out when I
               | input "9 2 5 8 4 3 7 1 0 2 9 4 -> 4 9 2 0 1 7 3 4 8 5 2
               | 9, 0 7 3 8 6 2 9 4 1 7 5 2 0 3 4 8 5 1 ->":
               | 
               | > You're correct! The pattern you identified applies to
               | both sets of numbers. Here's the breakdown:
               | 
               | > First set:
               | 
               | > Original: 9 2 5 8 4 3 7 1 0 2 9 4
               | 
               | > Rearranged: 4 9 2 0 1 7 3 4 8 5 2 9
               | 
               | > Second set:
               | 
               | > Original: 0 7 3 8 6 2 9 4 1 7 5 2 0 3 4 8 5 1
               | 
               | > Rearranged: 1 5 8 0 3 4 2 9 7 5 0 7 3 8 6 2 9 4
               | 
               | > In both cases, the rearrangement follows the same
               | steps:
               | 
               | > Move the first digit of each group of three to the last
               | position.
               | 
               | > Keep the middle digit in the same position.
               | 
               | > Repeat steps 1 and 2 for all groups of three.
               | 
               | > Therefore, the pattern holds true for both sets of
               | numbers you provided.
               | 
               | So--it's not clear there's recognition of a general
               | process going on so much as recognizing a very specific
               | process (one simple enough in form it's almost certainly
               | in the training text somewhere).
        
             | whimsicalism wrote:
             | > It really wasn't clear for the longest time how these
             | models generate things so well.
             | 
             | Honestly, I think it was pretty much just as clear in 2021
             | as it is in 2024. Whether you consider that 'clear' or 'not
             | clear' is a matter of personal choice but I don't think
             | we've really advanced our understanding all that far
             | (mechanistic interpretability does not tell us that much,
             | grokking is a phenom that does not apply to modern LLMs,
             | etc. )
             | 
             | > we have accrued quite a bit of evidence by now that these
             | models do far more than glue together training data. But
             | there are still sceptics out there who spread this sort
             | misinformation.
             | 
             | Few people who actually worked in this field and were
             | familiar with the concept of 'implicit regularization'
             | really ever thought the 'glue together training data' or
             | 'stochastic parrot' explanations were very compelling at
             | all.
        
           | stormfather wrote:
           | Making Sora's results by glueing videos together would be far
           | more impressive IMO. That would take ASI
        
         | asadotzler wrote:
         | Like the cat springing a 5th leg and then losing it just as
         | quick, in a cherry-picked video from the software makers? How
         | does that fit your wishful narrative?
        
           | alpaca128 wrote:
           | Look at how anyone who's not an artist (especially children)
           | draws pretty much anything, whether it's people or animals or
           | bicycles. You'll see a lot of asymmetric faces, wrong
           | shading, completely unrealistic hairs etc and yet all those
           | people are intelligent and excellent at understanding how the
           | world works. Intelligence can't be expressed in a directly
           | measurable way.
           | 
           | Those videos may be cherry-picked but they're almost good
           | enough that you have to pick problems to point out, problems
           | that will likely be gone a couple iterations later.
           | 
           | Less than a decade ago we read articles about Google's weird
           | AI model producing super trippy images of dogs, now we're at
           | deepfakes that successfully scam companies out of millions
           | and AI models that can't yet reliably preserve consistency
           | across an entire image. In another ten years every new
           | desktop, laptop and smartphone will have an integrated AI
           | accelerator and most of those issues will be fixed.
        
             | intended wrote:
             | Anthromporphizing models lets assumptions of human behavior
             | slip into discussions. Most people dont even know _how_
             | their brains process information while models are not
             | children.
             | 
             | New models appear to be close and based on arguments here,
             | closing the gap is simply a matter of time. This is based
             | on observing the rate of progress, not the actual
             | underlying actions. A tendency belied by assumptions based
             | on human thinking, not the signficant amounts of processing
             | that happens unconciously by us.
             | 
             | Sure expanding the data set has improved results, yet bad
             | hands, ghost legs, and other weirdness persist. If you have
             | a world model, then this shouldn't happen - there is a
             | logical rule to follow, not simply a pixel level
             | correlation.
             | 
             | Working from the other side, if image/video gen has reached
             | the point that it is faithfully recreating 3D rules, then
             | we should expect 3D wireframes to be generated. We should
             | see an update to https://github.com/openai/point-e.
             | 
             | This isn't splitting hairs - this behavior can be hand
             | waved away when building a PoC, not when you make a
             | production ready product.
             | 
             | As for scams, they target weaknesses, not the strongest
             | parts of a verification processes, making them strawmen
             | arguments for AI capabilty.
        
               | og_kalu wrote:
               | >If you have a world model, then this shouldn't happen -
               | there is a logical rule to follow, not simply a pixel
               | level correlation.
               | 
               | Oh I guess humans don't have world models then. It's so
               | weird seeing this rhetoric said again and again. No a
               | world model doesn't mean a perfect one. A world model
               | doesn't mean a logical one either. Humans clearly don't
               | work by logic.
        
               | intended wrote:
               | IF we are getting into the semantics of what a valid
               | world model is, then we really have different standards
               | for what passess as logic.
        
         | ozgung wrote:
         | We humans live in a 3D world and our training set is a
         | continuous stereo stream of a constant scene from different
         | angles. Sora, on the other hand, learned the world by watching
         | TV. It needs to play more video games, in order to learn 3D
         | scenes (implicit representation of a world) and taking their
         | pictures (rendering). Maybe that was the case I don't know.
        
           | DinaCoder99 wrote:
           | > It needs to play more video games, in order to learn 3D
           | scenes (implicit representation of a world) and taking their
           | pictures (rendering).
           | 
           | This can be extrapolated from TV, too.
        
         | SomeoneFromCA wrote:
         | NNs are _not_linear algebra. The genius of NN is that it is a
         | half-linear algebra (assuming most of them these days use ReLU
         | activation.) And thst half linearity gives power.
        
         | GuB-42 wrote:
         | Turns out that 3D graphics also involves a lot of linear
         | algebra.
         | 
         | That's also why GPU are so effective at neural networks. There
         | is a lot of the same maths.
        
       | ukuina wrote:
       | The name is a reference to a fictional gameshow in Bojack
       | Horseman called "Hollywoo Stars and Celebrities: What Do They
       | Know? Do They Know Things?? Let's Find Out!"
       | 
       | https://bojackhorseman.fandom.com/wiki/Hollywoo_Stars_and_Ce...!
        
         | echelon wrote:
         | I adore that show so much. I have this sticker on my laptop.
         | 
         | If you haven't seen Bojack Horseman, it's funny and heartfelt.
         | Palpably existential. If that kind of thing speaks to you, you
         | owe yourself a watch.
         | 
         | In terms of a complete animation package, I think it easy
         | outdoes Futurama. There's so much relatable depth to it. It
         | hits hard, but it stays lighthearted enough to make you feel
         | good about it.
         | 
         | As it turns out, I'm now working on filmtech, so that
         | "Hollywoo" sticker fits me even better now.
        
           | the_af wrote:
           | I want to like Bojack and I know it has drama and heartfelt
           | moments (watched all of season 1 I think), but _in my
           | opinion_ it 's undone by its moments of "wacky" humor. I
           | don't even mean that there are humanoid animals and humans
           | living together, no explanation -- I can embrace that. I mean
           | the Simpsons/Family Guy kind of humor... I could do without
           | it and I think it would make the show better.
           | 
           | Or maybe it does get better after season 1? Since everyone
           | seems to love it.
        
             | yosame wrote:
             | Season 1 is definitely the weakest season, especially at
             | the start. There's definitely still wacky humour in the
             | rest of the show, but it loses the family guy cutaway gags.
             | 
             | I'd personally recommend giving season 2 a shot, if you
             | still don't like it then the shows probably not for you.
        
             | reducesuffering wrote:
             | Season 1 is definitely weakest; very common in great TV
             | series. Just start from season 2 right now and I'm pretty
             | sure you'll love it. It will always have "wacky" moments
             | with a character like Todd in it though.
        
             | KerrAvon wrote:
             | It's very Los Angeles nihilist in tone. If that doesn't
             | make you happy, maybe skip it.
        
             | karmakurtisaani wrote:
             | I remember reading they had to make season 1 "wacky" to
             | sell the show. What the show becomes later would have been
             | ... hard to describe to studio executives.
        
             | chronofar wrote:
             | I'm at the other end, I think the show suffered due to its
             | insistence on querulous characters as a means to pathos,
             | but was kept afloat by its wit and humor (much of it indeed
             | "wacky"). That is of course very much a personal preference
             | thing, but I couldn't connect with much of the darker side
             | of the show, even while I admired much of its execution.
             | 
             | As others have said though, it definitely gets better as
             | the seasons roll on, along both the humor and drama fronts.
             | The final season has many of the funniest and most poignant
             | moments of the show.
        
             | jncfhnb wrote:
             | A tear shed for Simpsons being called wacky humor.
             | 
             | I think bojack hit its stride over time, but I always liked
             | the juxtaposition of dark reality with cartoon silliness.
             | On some level I think it reflects a theme of everyone
             | else's life seeking to be so simple and stupid and trivial
             | compared to your own. Of course even Todd's problems are
             | shown to be pretty real even if they're also cartoonishly
             | comical.
        
               | the_af wrote:
               | > _A tear shed for Simpsons being called wacky humor_
               | 
               | You know what I meant, hopefully? I predate the Simpsons,
               | and I remember when they and their brand of humor first
               | appeared. I also remember how annoyed I felt towards
               | Family Guy (a cartoon I never liked, unlike the Simpsons)
               | because it felt like a cheap copy. And yes, over the
               | years the Simpsons turned wackier and wackier while
               | retaining nothing of what made them good at first.
               | 
               | I don't claim Bojack and the Simpsons have the _same_
               | kind of humor, it was a shortcut to hopefully explain
               | what I found jarring about the former?
               | 
               | Given the rest of the comments, I'll try giving Bojack
               | season 2 a chance.
        
           | jeffparsons wrote:
           | > It hits hard, but it stays lighthearted enough to make you
           | feel good about it.
           | 
           | That wasn't my experience of it. It's a brilliant show, to be
           | sure, but at some point I felt the bleakness, particularly
           | around Bojack's inability to help himself, became too much
           | for me. Maybe different parts of the show resonate in
           | different people.
        
             | rocketbop wrote:
             | I agree it wasn't light at all in the later parts. Very
             | bleak. If it was ever supposed to be a comedy it didn't end
             | as one but I can't think of other animated series you could
             | class as a drama.
             | 
             | I think it is one of only about three animated shows that
             | are genuinely outstanding as TV and not just animation or
             | comedy. The other two being Simpsons and Futurama.
        
               | saberience wrote:
               | I couldn't finish watching the show, it was just too
               | depressing and dark for me to the extent that it made me
               | personally more anxious and depressed.
        
               | Filligree wrote:
               | > I can't think of other animated series you could class
               | as a drama.
               | 
               | Honestly, there are tons. They're just all Japanese.
        
           | khedoros1 wrote:
           | > but it stays lighthearted enough to make you feel good
           | about it.
           | 
           | There were plenty of parts that were dark enough to make it
           | difficult to watch. There were lighthearted parts, but that's
           | not a description I would've applied to the show as a whole.
        
           | saberience wrote:
           | Just a warning to anyone who read this comment, the show (in
           | later seasons) gets incredibly dark, existential, and
           | depressing, to the point where I couldn't watch it anymore as
           | it made me both anxious and depressed.
           | 
           | Anyone prone to anxiety or depression or sad thoughts in
           | general should probably avoid, it's really that depressing,
           | and I can imagine it making suicidal people even more
           | suicidal.
        
         | reso wrote:
         | Not gonna lie I upvoted this post based only on the title.
        
         | _____-___ wrote:
         | I reference this specific game show title quite a bit, but I
         | don't think that many people get it sadly, so I just seem weird
         | haha
        
           | jncfhnb wrote:
           | It's for the best. We wouldn't want this getting too
           | commercial.
        
         | lysecret wrote:
         | I have found my people. I watched this show like 6 times haha
        
       | mindcrime wrote:
       | Damn, now I'm suddenly finding myself wanting to go back and re-
       | watch Bojack Horseman. Not that that would be a bad thing.
        
       | vslira wrote:
       | Not to be a skeptic or anything, but how do we know normal maps
       | etc weren't enriched into the datasets by the image gen
       | companies?
       | 
       | I understand this paper links to open source model where that can
       | be verified, but maybe this is one secret sauce of these more
       | advanced models?
        
         | dougmwne wrote:
         | You would need to train on pairings of normal map images to
         | source images. To my knowledge, that's not a common training
         | technique and this ability seems to bridge across several open
         | models.
        
           | coffeebeqn wrote:
           | It's also kind of cool if it "understands" a normal map and
           | that it maps to specific 3D geometry. People generally use 3D
           | tools like Zbrush to sculpt the details to normals. Probably
           | some people can draw them too
        
       | auggierose wrote:
       | So how do they get the normals, for example? Are they generated
       | by the AI _before_ the image is generated in order to generate
       | the image, and they are just reading them off some internal
       | state?
        
         | corysama wrote:
         | The training data is just billions of {RGB image, text
         | description} pairs. So, it appears the model figured out how to
         | make the normals as part of the process of making the images.
         | 
         | Or, are you asking how the researchers extracted it?
         | 
         | > I-LoRA modulates key feature maps to extract intrinsic scene
         | properties such as normals, depth, albedo, and shading, using
         | the models' existing decoders without additional layers,
         | revealing their deep understanding of scene intrinsics.
        
           | auggierose wrote:
           | Yes, that sentence "modulates key feature maps" doesn't tell
           | me anything. What do they mean when saying they extract the
           | normals?
        
         | dougmwne wrote:
         | Yes, there's rudimentary evidence that there's essentially a 3D
         | engine within the model that participates in generating the
         | image. If we could inspect and interpret the whole process it
         | would likely be bizarre and byzantine, like a sort of
         | convergent evolution that independently recreates a tangled
         | spaghetti mess of unreal engine, adobe lightroom, and a
         | physical simulation of a Canon D5.
        
           | qingcharles wrote:
           | Essentially similar perhaps to the 3D engine that a human
           | brain runs that generates a single "3D" image from two 2D
           | cameras (eyes) and fills in missing objects in blind spots,
           | etc.
        
             | tsimionescu wrote:
             | Note that while having two eyes helps build a more accurate
             | 3D image, people with one eye still see in 3D. Eye movement
             | is at least as important a part of 3D vision as
             | stereoscopy.
        
               | dougmwne wrote:
               | And apparently 3D renders can be inferred from only 2d
               | images like in these image gen models, so even without
               | video or parallax, brains could probably model the world
               | in 3D.
        
             | daxfohl wrote:
             | I remember a wittgenstein thing asking to think of a tree
             | or something, and then point to the place in your head
             | where that thought exists. It's kind of like that.
        
       | LarsDu88 wrote:
       | Reminds me of when I tried to extract G-buffers from my Unity
       | High Definition Rendering Pipeline test project:
       | https://www.youtube.com/watch?v=Fwtc694qNUM
       | 
       | I'm not sure if this paper is really proving anything though.
       | There's a giant-ass UNET Lora model that's being trained here, so
       | is it really "extracting" something from an existing model, or
       | simply creating a new model that can create channels that look
       | like something you'd get out of a deferred rendering pipeline.
       | 
       | After all, taking normals, albedo, and depth and combining them
       | (deferred rendering) is just one of several techniques to create
       | a 3d scene. Wasn't even used in videogames until the early 2000s
       | (in a Shrek videogame for the Xbox!
       | (https://sites.google.com/site/richgel99/the-early-history-of...)
       | 
       | What would really be awesome is to get a LORA model that can
       | extract the "camera" rotation and translation matrix for these
       | image generation models. That would really demonstrate something
       | (and be quite useful at the same time).
        
         | joefourier wrote:
         | If you look at the supplementary material, they do a test where
         | they train the Lora with a randomly initialised Unet and it is
         | largely incapable of extracting any surface normals as opposed
         | to using the pretrained Stable Diffusion Unet - clearly showing
         | the features of the model are relevant to its performance.
        
         | sfink wrote:
         | I don't really know what I'm talking about, but doesn't this
         | address that?
         | 
         | > with newly learned parameters that make up less than 0.6% of
         | the total parameters in the generative model
         | 
         | 0.6% sounds like a small number. Is it measuring the right
         | thing?
         | 
         | Certainly, I wouldn't expect the model to necessarily be
         | encoding exactly the set of things that they're extracting, but
         | it still seems very significant to me even if it is "just"
         | encoding some set of things that can be cheaply (in terms of
         | model size) and reliably mapped to normals, albedo, and depth.
         | 
         | (I don't care what basis vectors it's using, as long as I know
         | how to map them to mine.)
        
           | LarsDu88 wrote:
           | 0.6 percent of a model with 890 million parameters is still
           | 5.34 million parameters.
           | 
           | That's still pretty big. Maybe big enough to fake normals,
           | learn some albedo smoothing functions, and learn a depth
           | estimator perhaps??
        
       | hn_throwaway_99 wrote:
       | I skimmed the paper, but a lot of it was over my head. As someone
       | not very versed in image generation AI, can anyone help me
       | understand? This sentence (which another commenter highlighted)
       | appears to be the key part:
       | 
       | > I-LoRA modulates key feature maps to extract intrinsic scene
       | properties such as normals, depth, albedo, and shading, using the
       | models' existing decoders without additional layers, revealing
       | their deep understanding of scene intrinsics.
       | 
       | What exactly does "modulates key feature maps to extract
       | intrinsic scene properties" mean? How were these scene property
       | images generated if no additional decoding layers were added?
        
         | visarga wrote:
         | Say you have a neural network with 1B parameters, you add 5M
         | more parameters spread around (LoRA), and continue training for
         | a while but only the newly added parameters, not the base
         | network. The result is a "modulated" network that would predict
         | scene properties.
         | 
         | The interesting thing is that it only takes a few more
         | parameters so it must be that the original network was pretty
         | close already.
        
           | kenjackson wrote:
           | Great explanation! Wish I could upvote more as it took me
           | from head scratching to "that makes total sense".
        
       | educaysean wrote:
       | This is good news for VR (or spatial computing). If the models
       | understand the physical world as well as the paper shows,
       | generating two projections of a scene does not sound like a
       | difficult ask. Really excited for what's to come.
        
       | modeless wrote:
       | Ooh, so this can take real images and predict albedo and
       | lighting! Please, someone use this to make relightable gaussian
       | splatting scenes. Dynamic lighting would really expand the
       | usefulness of 3D scans made from photos, and I haven't seen
       | anyone get anything close to what I would call "good" results in
       | that area yet.
        
         | IshKebab wrote:
         | Can it definitely use real images? I imagine extracting the
         | depth map from real images would be the most useful application
         | if it can.
        
           | modeless wrote:
           | "Fortunately, diffusion models are not only powerful image
           | generators, their structure as image-to-image models makes it
           | straightforward to apply to real images."
           | 
           | It looks like they actually only tried depth/normal maps for
           | real images, not albedo/lighting maps, but it certainly seems
           | possible. Honestly depth maps often look impressive at first
           | glance but typically if you actually try to use them for
           | anything (e.g. reprojection, DoF blur) their hidden flaws
           | instantly become super apparent, and they aren't as useful as
           | you might think. Gaussian splatting reconstructions already
           | do reprojection better anyway. OTOH albedo maps look weird,
           | but relighting is extremely useful and important. I'm not
           | excited about yet another way to generate approximate depth
           | maps, but I am excited about relighting.
        
       | dvh wrote:
       | I asked ai that was posted here yesterday to draw common european
       | chub and virtually every single one had adipose fin.
        
       | nottorp wrote:
       | Hmm. Facebook has had an option to create "3d photos" for a
       | while. I think they're annoying but now I wonder how they're
       | made, and if you really need a neural network to figure out the
       | 3d part in a 2d photo.
        
       | anjc wrote:
       | Would be interesting to see if the perceptive abilities of
       | generative models are superior to human perception, when tested
       | on optical illusions that humans are fooled by. E.g., do they
       | correctly assess depth in a Ponzo illusion scenario
        
       | renonce wrote:
       | So is this GPT for images? They take a generative model and apply
       | finetuning via LoRA on some downstream task such as surface
       | normal and conclude that these models intrinsically learn these
       | representations, and find that they do better than supervised
       | approaches?
       | 
       | I think this is awesome but maybe it's not really that surprising
       | given how this "generate and then finetune" approach has already
       | worked so well?
        
       | leobg wrote:
       | Yet again. Anyone who placed their bets on LiDAR for self driving
       | is proven wrong. Cameras and neural nets will rule the day.
        
       ___________________________________________________________________
       (page generated 2024-02-24 23:02 UTC)