[HN Gopher] AnyGPT: Unified Multimodal LLM with Discrete Sequenc...
       ___________________________________________________________________
        
       AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
        
       Author : tkgally
       Score  : 80 points
       Date   : 2024-02-21 13:45 UTC (9 hours ago)
        
 (HTM) web link (junzhan2000.github.io)
 (TXT) w3m dump (junzhan2000.github.io)
        
       | mdrzn wrote:
       | We're clearly heading towards a "Generalist Multimodal Large
       | Language Model" that autonomously selects the appropriate
       | specialized LLM for any given task, rather than requiring us to
       | switch between multiple LLMs. The combination of a mixture of
       | experts approach and multimodality appears to be the way forward.
       | Very excited for the future.
        
         | ilaksh wrote:
         | I don't think it's accurate to call them language models
         | anymore actually. Large Multimodal Model?
        
           | phh wrote:
           | You're right, that calling them language model is no longer
           | accurate. But "Language Model" has a precise signification
           | (which is that it tries to create a perfect representation of
           | the language). Saying "multimodal model", you're not really
           | saying what does it try to represent. "World Model" or "Human
           | Model" would be more accurate at this point
        
             | t_mann wrote:
             | World model sounds too much of physics than it deserves
             | imho. If you want to name it after what's being modeled
             | (which it doesn't need to be, it could also be named after
             | the methods used eg), why not just call it something like
             | general token model?
        
               | throwanem wrote:
               | What they model is meaning. I'd call them "semantic
               | models".
        
             | Smith42 wrote:
             | "Large Observation Model" has a nice ring to it
        
           | ShamelessC wrote:
           | I'm fond of Large Sequence Model, which I've seen used a bit
           | recently. If your data can be defined as a sequence of unique
           | symbols, actions, letters, tokens, patches, whatever - a
           | transformer is a great way to model it.
        
           | cs702 wrote:
           | I'm partial to Large World Model (LWM).
           | 
           | Large Sequence Model (LSM) is OK too.
        
           | kristjansson wrote:
           | As long as the underlying representation is a sequence of
           | (embeddings of) tokens , and the training depends on next-
           | token prediction, they should still be called language
           | models. The 'language' part of 'language models' is about the
           | architecture, not the modalit(y/ies).
        
             | CuriouslyC wrote:
             | Is it a "language" model though, if you have a multimodal
             | autoencoder that converts input into concept tokens, and
             | you do sequence extension in concept space?
        
               | kristjansson wrote:
               | Unambiguously, yes.
               | 
               | To elaborate a bit, that's effectively what happens in a
               | natural-language-only LLM. Text tokens are immediately
               | mapped to wide embeddings, which are processed by a
               | transformer, producing another embedding, which is
               | decoded back to a discrete token. To a first
               | approximation, unified multimodal models substitute f:
               | text -> [embedding] with g: image -> [embedding,] and act
               | on a sequence like [*f(t), *g(i), ...]. So... the
               | multimodal model maps text/image parts to wide
               | embeddings, which are processed by a transformer
               | producing another embedding, which is decoded back to a
               | discrete text/image part. Which sounds somewhat similar
               | to the former :).
               | 
               | Of course the function g is a bit more complicated, and
               | decoding takes more work, but the underlying machinery is
               | unchanged. The ability to handle multi-modal
               | inputs/outputs uniformly is exactly what's so exciting
               | about work like this!
        
         | jasfi wrote:
         | Apparently used in GPT-4 and coming in Gemini 1.5.
        
         | kristjansson wrote:
         | TFA is the exact opposite of that though? It's a single model
         | that acts on a single representation, which is derived from
         | (and mapped back to) different input (output) modalities.
        
       | ilaksh wrote:
       | I feel like this type of capability or architecture might be the
       | future of interactive agents. The quality of the voices leaves a
       | little to be desired, but otherwise it seems very powerful.
        
         | thfuran wrote:
         | Given how quickly we've been churning through sota
         | architectures in the last decade or so, I'd not bet on anything
         | we currently have being "the future"
        
       | cs702 wrote:
       | The key takeaway for me:
       | 
       | Whether data is continuous or discrete, no matter its modality
       | (text, video, music, etc.), we now have an array of proven
       | methods for representing it with _discrete_ tokens, enabling us
       | to use existing sequence modeling architectures (Transformers,
       | linear RNNs).
       | 
       | We live in interesting times!
        
       | justanotherjoe wrote:
       | What's with the dummy github page? Anyway. This feels like the
       | right step forward. Just like OpenAI, i have near religious faith
       | in the transformers architecture. The question is how these
       | modalities can work together better.
        
       ___________________________________________________________________
       (page generated 2024-02-21 23:01 UTC)