hf-vision (Hugging Face for Computer Vision)

merve

posted an update 2 days ago

Post

4140

A ton of impactful models and datasets in open AI past week, let's summarize the best 🤩 merve/releases-apr-21-and-may-2-6819dcc84da4190620f448a3

💬 Qwen made it rain! They released Qwen3: new dense and MoE models ranging from 0.6B to 235B 🤯 as well as Qwen2.5-Omni, any-to-any model in 3B and 7B!
> Microsoft AI released Phi4 reasoning models (that also come in mini and plus sizes)
> NVIDIA released new CoT reasoning datasets
🖼️ > ByteDance released UI-TARS-1.5, native multimodal UI parsing agentic model
> Meta released EdgeTAM, an on-device object tracking model (SAM2 variant)
🗣️ NVIDIA released parakeet-tdt-0.6b-v2, a smol 600M automatic speech recognition model
> Nari released Dia, a 1.6B text-to-speech model
> Moonshot AI released Kimi Audio, a new audio understanding, generation, conversation model
👩🏻‍💻 JetBrains released Melium models in base and SFT for coding
> Tesslate released UIGEN-T2-7B, a new text-to-frontend-code model 🤩

merve

posted an update 3 days ago

Post

5899

A real-time object detector much faster and accurate than YOLO with Apache 2.0 license just landed to Hugging Face transformers 🔥

D-FINE is the sota real-time object detector that runs on T4 (free Colab) 🤩

> Collection with all checkpoints and demo ustc-community/d-fine-68109b427cbe6ee36b4e7352

Notebooks:
> Tracking https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_tracking.ipynb
> Inference https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_inference.ipynb
> Fine-tuning https://github.com/qubvel/transformers-notebooks/blob/main/notebooks/DFine_finetune_on_a_custom_dataset.ipynb
h/t @vladislavbro @qubvel-hf @ariG23498 and the authors of the paper 🎩

Regular object detectors attempt to predict bounding boxes in (x, y, w, h) pixel perfect coordinates, which is very rigid and hard to solve 🥲☹️

D-FINE formulates object detection as a distribution for bounding box coordinates, refines them iteratively, and it's more accurate 🤩

Another core idea behind this model is Global Optimal Localization Self-Distillation ⤵️

this model uses final layer's distribution output (sort of like a teacher) to distill to earlier layers to make early layers more performant.

2 replies

·

merve

posted an update 6 days ago

Post

2035

you can easily fine-tune, quantize, play with sota vision LM InternVL3 now 🔥
we have recently merged InternVL3 to Hugging Face transformers and released converted checkpoints 🤗

collection for converted checkpoints: merve/internvl3-hf-6814be2943b2ae0e711c92a5
notebook: https://colab.research.google.com/drive/1wAQ7cyjyaCwLXbMA_OjXZe7aCxCFm6sI?usp=sharing 📖

merve

posted an update 8 days ago

Post

2552

Meta released Llama Guard 4 and new Prompt Guard 2 models 🔥

Llama Guard 4 is a new model to filter model inputs/outputs both text-only and image 🛡️ use it before and after LLMs/VLMs! meta-llama/Llama-Guard-4-12B

Prompt Guard 2 22M & 86M are smol models to prevent model jailbreaks and prompt injections ⚔ meta-llama/Llama-Prompt-Guard-2-22M meta-llama/Llama-Guard-4-12B
Both come with new release of transformers 🤗

Try the model right away 👉🏻https://github.com/huggingface/huggingface-llama-recipes/blob/main/llama_guard_4.ipynb

Read our blog to learn more and easily get started 👉🏻 https://huggingface.co/blog/llama-guard-4 🦙

1 reply

·

merve

posted an update 13 days ago

Post

3942

Don't sleep on new AI at Meta Vision-Language release! 🔥

facebook/perception-encoder-67f977c9a65ca5895a7f6ba1
facebook/perception-lm-67f9783f171948c383ee7498

Meta dropped swiss army knives for vision with A2.0 license 👏
> image/video encoders for vision language modelling and spatial understanding (object detection etc) 👏
> The vision LM outperforms InternVL3 and Qwen2.5VL 👏
> They also release gigantic video and image datasets

The authors attempt to come up with single versatile vision encoder to align on diverse set of tasks.

They trained Perception Encoder (PE) Core: a new state-of-the-art family of vision encoders that can be aligned for both vision-language and spatial tasks. For zero-shot image tasks, it outperforms latest sota SigLIP2 👏

> Among fine-tuned ones, first one is PE-Spatial. It's a model to detect bounding boxes, segmentation, depth estimation and it outperforms all other models 😮

> Second one is PLM, Perception Language Model, where they combine PE-Core with Qwen2.5 LM 7B. it outperforms all other models (including InternVL3 which was trained with Qwen2.5LM too!)

The authors release the following checkpoints in sizes base, large and giant:

> 3 PE-Core checkpoints (224, 336, 448)
> 2 PE-Lang checkpoints (L, G)
> One PE-Spatial (G, 448)
> 3 PLM (1B, 3B, 8B)
> Datasets

Authors release following datasets 📑
> PE Video: Gigantic video datasete of 1M videos with 120k expert annotations ⏯️
> PLM-Video and PLM-Image: Human and auto-annotated image and video datasets on region-based tasks
> PLM-VideoBench: New video benchmark on MCQA

2 replies

·

merve

posted an update 15 days ago

Post

3370

New foundation model on image and video captioning just dropped by NVIDIA AI 🔥

Describe Anything Model (DAM) is a 3B vision language model to generate detailed captions with localized references 😮

The team released the models, the dataset, a new benchmark and a demo 🤩 nvidia/describe-anything-680825bb8f5e41ff0785834c

Most of the vision LMs focus on image as a whole, lacking localized references in captions, and not taking in visual prompts (points, boxes, drawings around objects)

DAM addresses this on two levels: new vision backbone that takes in focal crops and the image itself, and a large scale dataset 👀

They generate a dataset by extending existing segmentation and referring expression generation datasets like REFCOCO, by passing in the images and classes to VLMs and generating captions.

Lastly, they also release a new benchmark again with self-supervision, they use an LLM to evaluate the detailed captions focusing on localization 👏

merve

posted an update 24 days ago

Post

4438

sooo many open AI releases past week, let's summarize! 🤗
merve/april-11-releases-67fcd78be33d241c0977b9d2

multimodal
> Moonshot AI released Kimi VL Thinking, first working open-source multimodal reasoning model and Kimi VL Instruct, both 16B MoEs with 3B active params (OS)
> InternVL3 released based on Qwen2.5VL, 7 ckpts with various sizes (1B to 78B)

LLMs
> NVIDIA released Llama-3_1-Nemotron-Ultra-253B-v1 an LLM built on Llama 405B for reasoning, chat and tool use
> Agentica released DeepCoder-14B-Preview, fine-tuned version of DeepSeek-R1-Distilled-Qwen-14B on problem-test pairs, along with the compiled dataset
> Zyphra/ZR1-1.5B is a new small reasoning LLM built on R1-Distill-1.5B (OS)
> Skywork-OR1-32B-Preview is a new reasoning model by Skywork

Image Generation
> HiDream releases three new models, HiDream I1 Dev, I1 Full, and I1 fast for image generation (OS)

*OS ones have Apache 2.0 or MIT licenses

4 replies

·

mmhamdy

posted an update about 1 month ago

Post

1611

What inspired the Transformer architecture in the "Attention Is All You Need" paper? And how were various ideas combined to create this groundbreaking model?

In this lengthy article, I explore the story and the origins of some of the ideas introduced in the paper. We'll explore everything from the fundamental attention mechanism that lies at its heart to the surprisingly simple explanation for its name, Transformer.

💡 Examples of ideas explored in the article:

✅ What was the inspiration for the attention mechanism?
✅ How did we go from attention to self-attention?
✅ Did the team have any other names in mind for the model?

and more...

I aim to tell the story of Transformers as I would have wanted to read it, and hopefully, one that appeals to others interested in the details of this fascinating idea. This narrative draws from video interviews, lectures, articles, tweets/Xs, and some digging into the literature. I have done my best to be accurate, but errors are possible. If you find inaccuracies or have any additions, please do reach out, and I will gladly make the necessary updates.

Read the article: https://huggingface.co/blog/mmhamdy/pandemonium-the-transformers-story

merve

posted an update about 2 months ago

Post

4144

So many open releases at Hugging Face past week 🤯 recapping all here ⤵️ merve/march-21-releases-67dbe10e185f199e656140ae

👀 Multimodal
> Mistral AI released a 24B vision LM, both base and instruction FT versions, sota 🔥 (OS)
> with IBM we released SmolDocling, a sota 256M document parser with Apache 2.0 license (OS)
> SpatialLM is a new vision LM that outputs 3D bounding boxes, comes with 0.5B (QwenVL based) and 1B (Llama based) variants
> SkyWork released SkyWork-R1V-38B, new vision reasoning model (OS)

💬 LLMs
> NVIDIA released new Nemotron models in 49B and 8B with their post-training dataset
> LG released EXAONE, new reasoning models in 2.4B, 7.8B and 32B
> Dataset: Glaive AI released a new reasoning dataset of 22M+ examples
> Dataset: NVIDIA released new helpfulness dataset HelpSteer3
> Dataset: OpenManusRL is a new agent dataset based on ReAct framework (OS)
> Open-R1 team released OlympicCoder, new competitive coder model in 7B and 32B
> Dataset: GeneralThought-430K is a new reasoning dataset (OS)

🖼️ Image Generation/Computer Vision
> Roboflow released RF-DETR, new real-time sota object detector (OS) 🔥
> YOLOE is a new real-time zero-shot object detector with text and visual prompts 🥹
> Stability AI released Stable Virtual Camera, a new novel view synthesis model
> Tencent released Hunyuan3D-2mini, new small and fast 3D asset generation model
> ByteDance released InfiniteYou, new realistic photo generation model
> StarVector is a new 8B model that generates svg from images
> FlexWorld is a new model that expands 3D views (OS)

🎤 Audio
> Sesame released CSM-1B new speech generation model (OS)

🤖 Robotics
> NVIDIA released GR00T, new robotics model for generalized reasoning and skills, along with the dataset

*OS ones have Apache 2.0 or MIT license

mattmdjaga

posted an update 2 months ago

Post

2600

🚨 Gray Swan AI's Biggest AI Jailbreaking Arena Yet! $130K+ 🚨

🔹 Agent Red-Teaming Challenge – test direct & indirect attacks on anonymous frontier models!
🔹 $130K+ in prizes & giveaways – co-sponsored by OpenAI & supported by UK AI Security Institute 🇬🇧
🔹 March 8 – April 6 – fresh exploits = fresh rewards!

How It Works:
✅ Anonymous models from top providers 🤐
✅ Direct & indirect prompt injection paths 🔄
✅ Weekly challenges for new behaviors 🗓️
✅ Speed & quantity-based rewards ⏩💰

Why Join?
⚖️ Neutral judging – UK AISI & automated judges ensure fairness
🎯 No pre-trained defenses – a true red-teaming battlefield
💻 5 Apple laptops up for grabs – increase chances by inviting friends!

🔗 Arena: app.grayswan.ai/arena/challenge/agent-red-teaming
🔗 Discord: discord.gg/grayswanai

🔥 No illusions, no mercy. Push AI agents to the limit & claim your share of $130K+! 🚀

mmhamdy

posted an update 3 months ago

Post

2758

🎉 We're excited to introduce MemoryCode, a novel synthetic dataset designed to rigorously evaluate LLMs' ability to track and execute coding instructions across multiple sessions. MemoryCode simulates realistic workplace scenarios where a mentee (the LLM) receives coding instructions from a mentor amidst a stream of both relevant and irrelevant information.

💡 But what makes MemoryCode unique?! The combination of the following:

✅ Multi-Session Dialogue Histories: MemoryCode consists of chronological sequences of dialogues between a mentor and a mentee, mirroring real-world interactions between coworkers.

✅ Interspersed Irrelevant Information: Critical instructions are deliberately interspersed with unrelated content, replicating the information overload common in office environments.

✅ Instruction Updates: Coding rules and conventions can be updated multiple times throughout the dialogue history, requiring LLMs to track and apply the most recent information.

✅ Prospective Memory: Unlike previous datasets that cue information retrieval, MemoryCode requires LLMs to spontaneously recall and apply relevant instructions without explicit prompts.

✅ Practical Task Execution: LLMs are evaluated on their ability to use the retrieved information to perform practical coding tasks, bridging the gap between information recall and real-world application.

📌 Our Findings

1️⃣ While even small models can handle isolated coding instructions, the performance of top-tier models like GPT-4o dramatically deteriorates when instructions are spread across multiple sessions.

2️⃣ This performance drop isn't simply due to the length of the context. Our analysis indicates that LLMs struggle to reason compositionally over sequences of instructions and updates. They have difficulty keeping track of which instructions are current and how to apply them.

🔗 Paper: From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions (2502.13791)
📦 Code: https://github.com/for-ai/MemoryCode

mmhamdy

authored 2 papers 3 months ago

MMTEB: Massive Multilingual Text Embedding Benchmark

Paper • 2502.13595 • Published Feb 19 • 34

From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions

Paper • 2502.13791 • Published Feb 19 • 5

merve

posted an update 3 months ago

Post

6494

Google just released PaliGemma 2 Mix: new versatile instruction vision language models 🔥

> Three new models: 3B, 10B, 28B with res 224, 448 💙
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything 🤯

Read more https://huggingface.co/blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4

merve

posted an update 3 months ago

Post

5047

Your weekly recap of open AI is here, and it's packed with models! merve/feb-14-releases-67af876b404cc27c6d837767

👀 Multimodal
> OpenGVLab released InternVideo 2.5 Chat models, new video LMs with long context
> AIDC released Ovis2 model family along with Ovis dataset, new vision LMs in different sizes (1B, 2B, 4B, 8B, 16B, 34B), with video and OCR support
> ColQwenStella-2b is a multilingual visual retrieval model that is sota in it's size
> Hoags-2B-Exp is a new multilingual vision LM with contextual reasoning, long context video understanding

💬 LLMs
A lot of math models!
> Open-R1 team released OpenR1-Math-220k large scale math reasoning dataset, along with Qwen2.5-220K-Math fine-tuned on the dataset, OpenR1-Qwen-7B
> Nomic AI released new Nomic Embed multilingual retrieval model, a MoE with 500 params with 305M active params, outperforming other models
> DeepScaleR-1.5B-Preview is a new DeepSeek-R1-Distill fine-tune using distributed RL on math
> LIMO is a new fine-tune of Qwen2.5-32B-Instruct on Math

🗣️ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings

🖼️ Vision and Image Generation
> We have ported DepthPro of Apple to transformers for your convenience!
> illustrious-xl-v1.0 is a new illustration generation model

3 replies

·

mmhamdy

posted an update 3 months ago

Post

2987

⛓ Evaluating Long Context #2: SCROLLS and ZeroSCROLLS

In this series of posts about tracing the history of long context evaluation, we started with Long Range Arena (LRA). Introduced in 2020, Long Range Arens (LRA) is one of the earliest benchmarks designed to tackle the challenge of long context evaluation. But it wasn't introduced to evaluate LLMs, but rather the transformer architecture in general.

📜 The SCROLLS benchmark, introduced in 2022, addresses this gap in NLP/LLM research. SCROLLS challenges models with tasks that require reasoning over extended sequences (according to 2022 standards). So, what does it offer?

1️⃣ Long Text Focus: SCROLLS (unlike LRA) focus mainly on text and contain inputs with thousands of words, testing models' ability to synthesize information across lengthy documents.
2️⃣ Diverse Tasks: Includes summarization, question answering, and natural language inference across domains like literature, science, and business.
3️⃣ Unified Format: All datasets are available in a text-to-text format, facilitating easy evaluation and comparison of models.

Building on SCROLLS, ZeroSCROLLS takes long text evaluation to the next level by focusing on zero-shot learning. Other features include:

1️⃣ New Tasks: Introduces tasks like sentiment aggregation and sorting book chapter summaries.
2️⃣ Leaderboard: A live leaderboard encourages continuous improvement and competition among researchers.

💡 What are some other landmark benchmarks in the history of long context evaluation? Feel free to share your thoughts and suggestions in the comments.

- SCROLLS Paper: SCROLLS: Standardized CompaRison Over Long Language Sequences (2201.03533)
- ZeroSCROLLS Paper: ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding (2305.14196)

merve

posted an update 3 months ago

Post

3180

Interesting releases in open AI this week, let's recap 🤠 merve/feb-7-releases-67a5f7d7f172d8bfe0dd66f4

🤖 Robotics
> Pi0, first open-source foundation vision-language action model was released in Le Robot (Apache 2.0)

💬 LLMs
> Groundbreaking: s1 is simpler approach to test-time scaling, the release comes with small s1K dataset of 1k question-reasoning trace pairs (from Gemini-Thinking Exp) they fine-tune Qwen2.5-32B-Instruct to get s1-32B, outperforming o1-preview on math 🤯 s1-32B and s1K is out!
> Adyen released DABstep, a new benchmark along with it's leaderboard demo for agents doing data analysis
> Krutrim released Krutrim-2 instruct, new 12B model based on NeMo12B trained and aligned on Indic languages, a new multilingual sentence embedding model (based on STSB-XLM-R), and a translation model for Indic languages

👀 Multimodal
> PKU released Align-DS-V, a model aligned using their new technique called LLF for all modalities (image-text-audio), along with the dataset Align Anything
> OLA-7B is a new any-to-any model by Tencent that can take text, image, video, audio data with context window of 32k tokens and output text and speech in English and Chinese
> Krutrim released Chitrarth, a new vision language model for Indic languages and English

🖼️ Vision
> BiRefNet_HR is a new higher resolution BiRefNet for background removal

🗣️ Audio
> kyutai released Hibiki, it's a real-time speech-to-speech translation model 🤯 it's available for French-English translation
> Krutrim released Dhwani, a new STT model for Indic languages
> They also release a new dataset for STT-TTS

🖼️ Image Generation
> Lumina released Lumina-Image-2.0, a 2B parameter-flow based DiT for text to image generation
> Tencent released Hunyuan3D-2, a 3D asset generation model based on DiT and Hunyuan3D-Paint
> boreal-hl-v1 is a new boring photorealistic image generation LoRA based on Hunyuan

merve

posted an update 3 months ago

Post

2373

IBM released ibm-granite/granite-vision-3.1-2b-preview, a small vision LM with impressive performance on different tasks 😮🔥

it comes with transformers and vLLM support from the get-go 💗
you can run it in Colab T4, so I built a notebook to put it to test, find it here: https://github.com/merveenoyan/smol-vision/blob/main/inference_gists/IBM_Granite_Vision.ipynb

merve

posted an update 3 months ago

Post

4098

This week in open AI was 🔥 Let's recap! 🤗 merve/january-31-releases-679a10669bd4030090c5de4d
LLMs 💬
> Huge: AllenAI released new Tülu models that outperform DeepSeek R1 using Reinforcement Learning with Verifiable Reward (RLVR) based on Llama 3.1 405B 🔥
> Mistral AI is back to open-source with their "small" 24B models (base & SFT), with Apache 2.0 license 😱
> Alibaba Qwen released their 1M context length models Qwen2.5-Instruct-1M, great for agentic use with Apache 2.0 license 🔥
> Arcee AI released Virtuoso-medium, 32.8B LLMs distilled from DeepSeek V3 with dataset of 5B+ tokens
> Velvet-14B is a new family of 14B Italian LLMs trained on 10T tokens in six languages
> OpenThinker-7B is fine-tuned version of Qwen2.5-7B-Instruct on OpenThoughts dataset

VLMs & vision 👀
> Alibaba Qwen is back with Qwen2.5VL, amazing new capabilities ranging from agentic computer use to zero-shot localization 🔥
> NVIDIA released new series of Eagle2 models with 1B and 9B sizes
> DeepSeek released Janus-Pro, new any-to-any model (image-text generation from image-text input) with MIT license
> BEN2 is a new background removal model with MIT license!

Audio 🗣️
> YuE is a new open-source music generation foundation model, lyrics-to-song generation

Codebase 👩🏻‍💻
> We are open-sourcing our SmolVLM training and eval codebase! https://github.com/huggingface/smollm/tree/main/vision
> Open-R1 is open-source reproduction of R1 by @huggingface science team https://huggingface.co/blog/open-r1

1 reply

·

merve

posted an update 3 months ago

Post

5377

Oof, what a week! 🥵 So many things have happened, let's recap! merve/jan-24-releases-6793d610774073328eac67a9

Multimodal 💬
- We have released SmolVLM -- tiniest VLMs that come in 256M and 500M, with it's retrieval models ColSmol for multimodal RAG 💗
- UI-TARS are new models by ByteDance to unlock agentic GUI control 🤯 in 2B, 7B and 72B
- Alibaba DAMO lab released VideoLlama3, new video LMs that come in 2B and 7B
- MiniMaxAI released Minimax-VL-01, where decoder is based on MiniMax-Text-01 456B MoE model with long context
- Dataset: Yale released a new benchmark called MMVU
- Dataset: CAIS released Humanity's Last Exam (HLE) a new challenging MM benchmark

LLMs 📖
- DeepSeek-R1 & DeepSeek-R1-Zero: gigantic 660B reasoning models by DeepSeek, and six distilled dense models, on par with o1 with MIT license! 🤯
- Qwen2.5-Math-PRM: new math models by Qwen in 7B and 72B
- NVIDIA released AceMath and AceInstruct, new family of models and their datasets (SFT and reward ones too!)

Audio 🗣️
- Llasa is a new speech synthesis model based on Llama that comes in 1B,3B, and 8B
- TangoFlux is a new audio generation model trained from scratch and aligned with CRPO

Image/Video/3D Generation ⏯️
- Flex.1-alpha is a new 8B pre-trained diffusion model by ostris similar to Flux
- tencent released Hunyuan3D-2, new 3D asset generation from images

7 replies

·

Hugging Face for Computer Vision

AI & ML interests

hf-vision's activity

MMTEB: Massive Multilingual Text Embedding Benchmark

From Tools to Teammates: Evaluating LLMs in Multi-Session Coding Interactions

AI & ML interests

Team members 53

hf-vision's activity