Re:Show HN: I invented a new generative model and got accept...
by VoidWhisperer on Friday October 10, 2025 @06:33AM
(#45537268)
I don't have a super deep understanding of the underlying algorithms involved, but going off the demo and that page, is this mainly a model for image related tasks, or could it also be trained to do things like what GPT/Claude/etc does (chat conversations)?
[ Parent
| on HN ]
Re:Show HN: I invented a new generative model and got accept...
by diyer22 on Friday October 10, 2025 @07:24AM
(#45537623)
Yes, it's absolutely possible—just like how diffusion LLMs work, we can do the same with DDN LLMs.
I made an initial attempt to combine [DDN with GPT](https://github.com/Discrete-Distribution-Networks/Discrete-D...), aiming to remove tokenizers and let LLMs directly model binary strings. In each forward pass, the model adaptively adjusts the byte length of generated content based on generation difficulty (naturally supporting speculative sampling).
Re:Show HN: I invented a new generative model and got accept...
by vintermann on Friday October 10, 2025 @10:33AM
(#45539561)
This is what I find most impressive, that it's a natural hierarchial method which seems so general, yet is actually quite competitive. I feel like the machine learning community has been looking for that for a long time. Non-generative uses (like hierarchial embeddings, maybe? Making Dewey's decimal like embeddings for anything!) are even more exciting.
Re:Show HN: I invented a new generative model and got accept...
by diyer22 on Friday October 10, 2025 @10:43AM
(#45539656)
Exactly! The paragraph on Efficient Data Compression Capability in the original paper also highlights:
> To our knowledge, Taiji-DDN is the first generative model capable of directly transforming data into a semantically meaningful binary string which represents a leaf node on a balanced binary tree.
This property excites me just as much.
[dead]
Re:Show HN: I invented a new generative model and got accept...
by lukan on Saturday October 11, 2025 @08:57AM
(#45548807)
I vouched for this comment. Your account seems to be shadow banned, but your last comments look fine to me, so you maybe want to email dang to revoke that status ..
Re:Show HN: I invented a new generative model and got accept...
by diyer22 on Saturday October 11, 2025 @01:18PM
(#45550877)
It does seem that way — we’re both trying to overcome the limitations imposed by LLM tokenization to achieve a truly end-to-end model.
And, their work is far more polished; I’ve only put together a quick GPT+DDN proof-of-concept.
Thank you for sharing.
Re:Show HN: I invented a new generative model and got accept...
by booli on Friday October 10, 2025 @06:41AM
(#45537309)
The posts mentions that: https://github.com/Discrete-Distribution-Networks/Discrete-D...