DeepSeek OCR

The paper is more interesting than just another VLM for OCR, they start talking about compression and stuff. E.g. there is this quote

>Our work represents an initial exploration into the boundaries of vision-text compression, investigating how many vision tokens are required to decode text tokens. The preliminary results are encouraging: DeepSeek-OCR achieves near-lossless OCR compression at approximately 10× ratios, while 20× compression still retains 60% accuracy.

(I guess you could say a picture token is worth 10 textual tokens...)

Could someone explain to a noob what the information-theoretic intuition is here? Why does this work, is it that text tokens are still too "granular"/repetitive and don't come close to the ideal entropy coding? Or is switching to vision tokens escaping the limitation of working "one word-ish at a time", allowing you to get closer to entropy (similar to the way that arithmetic encoding does compared to huffman codes)?

And then they start talking about handling long-context by literally(?) downscaling images, forming a correspondence between information loss in the textual domain and the image domain.

Text tokens are quantized and represent subword units, vision tokens only exist in the embedding space.

The way text tokenization works in LLMs is that you have a "lookup table" of (small) token ids to (large) vector embeddings. To pass text to the LLM, you split it at token boundaries, convert strings to token ids, and then construct the "context", a matrix where each row is a vector taken from that lookup table.

Transmitting text token sequences can be relatively efficient, you just transmit the token IDs themselves[1]. They're small integers (~100k possible token ids is typical for large models). Transmitting the actual embeddings matrix would be far less efficient, as embeddings often consist of thousands of floating point numbers.

Images are encoded differently. After some basic preprocessing, image data is passed straight to a neural- network-based image encoder. That encoder encodes the image into vectors, which are then appended to the context. There are no token ids, there's no lookup table, we go straight from image data to token embeddings.

This means transmitting image tokens cannot be done as efficiently, as you'd have to transmit the embeddings themselves. Even though an image is encoded in fewer tokens, the most efficient representation of those tokens takes more bytes.

You can think of a text token as an integer between 0 and n, which we know how to map to a vector. This means you have `n` possible choices of tokens. In contrast, an image token is an array of m floating point numbers (the vector itself), each of which can take on many possible values. This means the "token space" of vision tokens is actually much larger.

There's also the issue of patterns. Text tokens correspond directly to a contiguous span of UTF-8 bytes, and most tokenizers won't create tokens that span word boundaries. This means they can't encode global patterns efficiently. You can't have a "Hamlet's monologue" or "the text that follows is in Spanish" token.

Great explanation, thanks. I was surprised to hear that models still only work with ~100k tokens, but after giving it some thought it makes sense. There's only so many words/subword units that get used in any given language. The entropy comes from all the billions of different ways those subwords can be ordered.

There is also a tradeoff between different vocabulary sizes (how many entries exist in the token -> embedding lookup table) that inform the current shape of tokenizers and LLMs. (Below is my semi-armchair stance, but you can read more in depth here[0][1].)

If you tokenized at the character level ('a' -> embedding) then your vocabulary size would be small, but you'd have more tokens required to represent most content. (And context scales non-linearly, iirc, like n^3) This would also be a bit more 'fuzzy' in terms of teaching the LLM to understand what a specific token should 'mean'. The letter 'a' appears in a _lot_ of different words, and it's more ambiguous for the LLM.

On the flip side: What if you had one entry in the tokenizer's vocabulary for each word that existed? Well, it'd be far more than the ~100k entries used by popular LLMs, and that has some computational tradeoffs like when you calculate the probability of each 'next' token via softmax, you'd have to run that for each token, as well as increasing the size of certain layers within the LLM (more memory + compute required for each token, basically).

Additionally, you run into a new problem: 'Rare Tokens'. Basically, if you have infinite tokens, you'll run into specific tokens that only appear a handful of times in the training data and the model is never able to fully imbue the tokens with enough meaning for them to _help_ the model during inference. (A specific example being somebody's username on the internet.)

Fun fact: These rare tokens, often called 'Glitch Tokens'[2], have been used for all sorts of shenanigans[3] as humans learn to break these models. (This is my interest in this as somebody who works in AI security)

As LLMs have improved, models have pushed towards the largest vocabulary they can get away with without hurting performance. This is about where my knowledge on the subject ends, but there have been many analyses done to try to compute the optimal vocabulary size. (See the links below)

One area that I have been spending a lot of time thinking about is what Tokenization looks like if we start trying to represent 'higher order' concepts without using human vocabulary for them. One example being: Tokenizing on LLVM bytecode (to represent code more 'densely' than UTF-8) or directly against the final layers of state in a small LLM (trying to use a small LLM to 'grok' the meaning and hoist it into a more dense, almost compressed latent space that the large LLM can understand).

It would be cool if Claude Code, when it's talking to the big, non-local model, was able to make an MCP call to a model running on your laptop to say 'hey, go through all of the code and give me the general vibe of each file, then append those tokens to the conversation'. It'd be a lot fewer tokens than just directly uploading all of the code, and it _feels_ like it would be better than uploading chunks of code based on regex like it does today...

This immediately makes the model's inner state (even more) opaque to outside analysis though. e.g., like why using gRPC as the protocol for your JavaScript front-end sucks: Humans can't debug it anymore without other tooling. JSON is verbose as hell, but it's simple and I can debug my REST API with just network inspector. I don't need access to the underlying Protobuf files to understand what each byte means in my gRPC messages. That's a nice property to have when reviewing my ChatGPT logs too :P

Exciting times!

0: https://www.rohan-paul.com/p/tutorial-balancing-vocabulary-s...

1: https://arxiv.org/html/2407.13623v1

2: https://en.wikipedia.org/wiki/Glitch_token

3: https://www.lesswrong.com/posts/aPeJE8bSo6rAFoLqg/solidgoldm...