[HN Gopher] Genie: Generative Interactive Environments
       ___________________________________________________________________
        
       Genie: Generative Interactive Environments
        
       Author : kuter
       Score  : 72 points
       Date   : 2024-02-26 11:10 UTC (11 hours ago)
        
 (HTM) web link (sites.google.com)
 (TXT) w3m dump (sites.google.com)
        
       | polygamous_bat wrote:
       | Firstly, do these models learn a good physics grounding for
       | nonsense actions? Like keep pressing down even when you are in
       | the ground? Or will they phase you through the ground?
       | 
       | Secondly, why are all videos like half a second long? I thought
       | video generation came much farther than this. My guess would be
       | that the world models unravel at any length longer than that,
       | which is (and has always been) the problem with models such as
       | these. Minus the video generation part, we had pretty good world
       | models for games already, see Dreamer line of work:
       | https://danijar.com/project/dreamerv3/
        
         | jparkerholder wrote:
         | Author here :) Re: 1) typically no, but of course it can
         | hallucinate just like LLMs. 2) Agreed but the key point missing
         | is Dreamer is trained from an RL environment with action
         | labels. Genie is trained exclusively from videos and learns an
         | action space. This is the first version of something that is
         | now possible and will only improve with scale.
        
           | polygamous_bat wrote:
           | Thanks for braving the crowd here, you will unfortunately
           | only find hard questions.
           | 
           | Anyway, about my second question: why are the videos only
           | half second ish long? Does the model unravel after that?
           | 
           | Also
           | 
           | > This is the first version of something that is now possible
           | and will only improve with scale.
           | 
           | 11b params is already pretty large considering the stable
           | diffusion and LLM scale. How much higher do we need to scale
           | until we get something useful beyond simple setups?
        
             | jparkerholder wrote:
             | The bigger issue is lack of generating novel content rather
             | than a total "unravel". We focus on OOD images because our
             | motivation is generating diverse environments, but these
             | are much harder to play for longer vs images closer to the
             | training videos. It is interesting because one of the
             | things you gain when going from 1B->10B is the OOD images
             | working _at all_. Note it is not even trivial to detect the
             | character given our model does not train with any labels or
             | have any inductive biases to do so.
             | 
             | Point of clarification -- we don't expect bigger models to
             | be the only way to improve this and are working on
             | innovations on the modeling side, however we don't want to
             | overlook the significance of scaling either :)
        
       | nycdatasci wrote:
       | The results seem quite bad. Compare the static image and "game"
       | in this one example: Static Image:
       | https://lh3.googleusercontent.com/c0GV4hG0Xg0eqpsUS1z62v6aJ2...
       | "Game":
       | https://lh5.googleusercontent.com/L_WsAa1saPmj29DSKda_fzk15y...
       | 
       | In the video, the character becomes a pixelated mess. In the
       | static image, the character is clearly on rocks in the
       | foreground, but in the "game" we see the character magically
       | jumping from the foreground rocks to the background structure
       | which also contains significant distortions.
       | 
       | The extremely short demo videos make it slightly harder to catch
       | these obvious issues.
        
         | polygamous_bat wrote:
         | What is the video resolution, 64x64? And even then it becomes
         | blurry. Seems like another Google flag-plant-y paper filled
         | with hot air that we will never see the source code or model
         | for because it will expose how poor its capabilities are
         | relative to competitors.
         | 
         | The internal politics at these places must be exhausting.
         | Industry research was supposed to be free from the publish or
         | perish mindset, but it seems like it just got replaced by a
         | different kind of need for posturing.
        
           | jparkerholder wrote:
           | Hey author here :) First, tough crowd, love it, always great
           | to get feedback because we are actively working on improving
           | the model. We are very happy to admit it is not perfect, but
           | given not many people thought this was possible a year ago, I
           | am quite excited to see the next step of improvement. This is
           | like the GPT1 of foundation world models, and we have a fair
           | few ideas in the works to speed up progress.
           | 
           | The resolution is 90p but we use an upsampler to make it 360p
           | for examples on the website.
        
             | nullptr_deref wrote:
             | How can I get started with this kind of research? Is it
             | even possible without a PhD? Thanks.
        
               | jparkerholder wrote:
               | If we did a good job then the paper should be written in
               | a way that is digestible. When you don't understand
               | things, follow the references to learn more (and there's
               | probably videos covering most of the components we use).
               | 
               | In the Appendix we have a case study that should be
               | possible to re-implement and run with a single GPU/TPU.
               | We are hoping the community can build from that and
               | innovate. If you take these steps and get stuck, feel
               | free to get in touch!
        
       | snide wrote:
       | I'm old an immediately assumed this would link to historical
       | retrospective of GEnie
       | 
       | https://en.wikipedia.org/wiki/GEnie
        
       | sqreept wrote:
       | I've read twice the announcement and I can't tell what this is
       | good for. Can you please dumb it down for me?
        
       | jasonjmcghee wrote:
       | > Genie is capable of converting a variety of different prompts
       | into interactive, playable environments that can be easily
       | created, stepped into, and explored
       | 
       | If these are generating a fully interactive environments, why are
       | all the clips ~1 second long?
       | 
       | Based on the first sentence in your paper, I would have expected
       | a playable example as a demo. Or 20.
       | 
       | But reading a bit further into the paper, it sounds like the
       | model needs to be actively running inference and will generate
       | the next frame on the fly as actions are taken- is that correct?
        
         | jparkerholder wrote:
         | That is correct! The model generates each frame on the fly.
        
       | joloooo wrote:
       | Looking forward to following your progress. I've been wanting to
       | see how we might replace polygons for gaming long term, this
       | seems like a step in the right direction.
        
       ___________________________________________________________________
       (page generated 2024-02-26 23:02 UTC)