Image created with gemini-2.5-flash-image with claude-sonnet-4-5. Image prompt: Cinematic shot of an ornate chess board mid-game on a dark wooden table with dramatic side lighting, chess pieces casting impossibly long fractal shadows that extend deep into darkness revealing faint computational tree structures and grid patterns, single white king piece in sharp focus foreground, moody study room atmosphere, deep depth of field, photorealistic render
DeepSeek’s new 685B MoE model attends to only to the most relevant tokens, delivering 2–3× faster long-context inference and 6–7× cheaper processing than its V3.1 model. The new v3.2 model has MIT-licensed weights, costs $0.28/$0.028/$0.42 per 1M input/cached/output tokens via https://x.com/DeepLearningAI/status/1980846573681520824
Massively unexpected update from DeepSeek: a powerful, high-compression MoE OCR model. > In production, DeepSeek-OCR can generate 33 million pages of data per day for LLMs/VLMs using 20 nodes (x8 A100-40G). They want ALL the tokens. You’re welcome to have some too. https://x.com/teortaxesTex/status/1980160624140456370
DeepSeek released an OCR model today. Their motivation is really interesting: they want to use visual modality as an efficient compression medium for textual information, and use this to solve long-context challenges in LLMs. Of course, they are using it to get more training https://x.com/iScienceLuvr/status/1980247935700066468
Text or Pixels? It Takes Half: On the Token Efficiency of Visual Text Inputs in Multimodal LLMs Looks like this paper is also exploring the direction DeepSeek is interested in: representing text more efficiently as images, observing almost half reduction in number of tokens https://x.com/iScienceLuvr/status/1980942325573648703
> by storing the data representation natively as image tiles This must be obvious but just to clarify: DeepSeek does not propose to store *screenshots* of your chat logs. Pixel representation can be ephemeral; what is stored is still tokens, just not *language* tokens. https://x.com/teortaxesTex/status/1980453820632297900
Karpathy is undoubtedly vision pilled. And thanks to this casual DeepSeek drop — so will you.”” / X https://x.com/bilawalsidhu/status/1980598830916939880
DeepSeek https://github.com/deepseek-ai/
@mervenoyann The good perf of DeepSeek models matches with what we observe on PrediBench! https://x.com/AymericRoucher/status/1980196484617523445
Again, I will reiterate this: DeepSeek was literally built by chinas top quant firm, and chinas TOP quants.”” / X https://x.com/hamptonism/status/1980182896049811780
After DeepSeek-V3.2-Exp added TileLang & CUDA ops, many asked: what exactly is TileLang? 🤔 In his post “”TileLang: 80 lines of Python kernel code to reach 95% of FlashMLA’s performance””, developer & Zhihu contributor ryume gives a full breakdown of this new AI programming https://x.com/ZhihuFrontier/status/1980170674112188440
GLM-4.6 providers overview: we are benchmarking API endpoints offered by Baseten, GMI, Parasail, Novita, Deepinfra GLM-4.6 (Reasoning) from @Zai_org is one of the most intelligent open weights models, with intelligence close to GPT-OSS-120b (high), DeepSeek V3.2 Exp (Reasoning) https://x.com/ArtificialAnlys/status/1980777360724226282
For people thinking that DeepSeek-OCR is the first model to render text as images, the University of Copenhagen already did this in 2023 Paper is called “”Language Modelling with Pixels””. They trained a Masked AutoEncoder (MAE) by rendering text as images and masking patches https://x.com/NielsRogge/status/1980559120760791125
We’re seeing a lot of usage around DeepSeek’s new OCR model. Alex packaged it so you can deploy and test it yourself – prompts and sample images included.”” / X https://x.com/basetenco/status/1980924381217104338
DeepSeek-OCR looks impressive, but its core idea is not new. Input “Text” as “Image” — already explored by: LANGUAGE MODELING WITH PIXELS (Phillip et al., ICLR 2023) CLIPPO: Image-and-Language Understanding from Pixels Only (Michael et al. CVPR 2023) Pix2Struct: Screenshot https://x.com/awinyimgprocess/status/1980506449706119642
A more serious thread on the DeepSeek-OCR hype / serious misinterpretation going on. 1. On token reduction via representing text in images, researchers from Cambridge have previously shown that 500x prompt token compression is possible (ACL’25, Li, Su, and Collier). Without https://x.com/Kangwook_Lee/status/1980709454522744902
DeepSeek finally released a new model and paper. And because this DeepSeek-OCR release is a bit different from what everyone expected, and DeepSeek releases are generally a big deal, I wanted to do a brief explainer of what it is all about. In short, they explore how vision https://x.com/rasbt/status/1980642191950090585
I quite like the new DeepSeek-OCR paper. It’s a good OCR model (maybe a bit worse than dots), and yes data collection etc., but anyway it doesn’t matter. The more interesting part for me (esp as a computer vision at heart who is temporarily masquerading as a natural language”” / X https://x.com/karpathy/status/1980397031542989305
🚨 DeepSeek just did something wild. They built an OCR system that compresses long text into vision tokens literally turning paragraphs into pixels. Their model, DeepSeek-OCR, achieves 97% decoding precision at 10× compression and still manages 60% accuracy even at 20×. That https://x.com/godofprompt/status/1980233080213590326
Letsss gooo! DeepSeek just released a 3B OCR model on Hugging Face 🔥 Optimised to be token efficient AND scale ~200K+ pages/day on A100-40G Same arch as DeepSeek VL2 Use it with Transformers, vLLM and more 🤗 https://x.com/reach_vb/status/1980170192392270227
a bunch of OCR models released in past few weeks: ~ deepseek-ocr-3b ~ olmo-ocr-2-7b ~ chandra-ocr-8b ~ nanonets-ocr2-3b ~ paddleocr-vl-0.9B ~ qwen3-vl-dense/moe (general vlm) ~ dots.ocr-3b Will be dropping a detailed comparison soon”” / X https://x.com/HarveenChadha/status/1981055277408669934
NEW DeepSeek OCR model that outperforms dots ocr while prefilling 3x less tokens https://x.com/casper_hansen_/status/1980166248878203093
DeepSeek-OCR has some weird architectural choices for the LLM decoder: DeepSeek3B-MoE-A570M -> uses MHA, no MLA (not even GQA?) -> 2 shared experts (like DeepSeek V2, but V3 only has 1) -> quite low sparsity, activation ratio is 12.5%. For V3 it’s 3.52%, for V2 it’s 5% -> not https://x.com/eliebakouch/status/1980193125202083951
I think Glyph coming out on the same day a) corroborates the results of DeepSeek OCR b) confirms the “they had it lying around for a while” suspicion. Charitably, they learned of Zhipu’s project retracing their steps and sped up the release. Other possibilities are obvious too.”” / X https://x.com/teortaxesTex/status/1980642000006451348
deepseek-ai/DeepSeek-OCR: Contexts Optical Compression https://github.com/deepseek-ai/DeepSeek-OCR
what happened this week with OCR and VLMs? * deepseek-ocr * chandra-ocr * nanonets-ocr2 * paddleocr-vl * qwen3-vl (2B, 32B, Instruct and Thinking) * dots.ocr * olmOCR 2 (based on Qwen2.5-VL) * LightOnOCR (smallies) top 5 trending models on @huggingface are still OCR/VLM! https://x.com/MaziyarPanahi/status/1981421331053760775
DeepSeek-OCR Contexts Optical Compression https://x.com/_akhaliq/status/1980260630780162505
DeepSeek OCR dropped … but honestly, Glyph [1], released the same day, showed something more interesting: 3–4× context compression and infilling cost reduction, no performance hit on long-context QA and summarization, which is much less trivial than OCR in many cases. If that https://x.com/arankomatsuzaki/status/1980722682246398069
🚀 DeepSeek-OCR — the new frontier of OCR from @deepseek_ai , exploring optical context compression for LLMs, is running blazingly fast on vLLM ⚡ (~2500 tokens/s on A100-40G) — powered by vllm==0.8.5 for day-0 model support. 🧠 Compresses visual contexts up to 20× while keeping https://x.com/vllm_project/status/1980235518706401405
