SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Paper
β’
2502.14786
β’
Published
β’
118
kotol
company
AI & ML interests
None defined yet.
Recent Activity
gv-hf's activity
ibomohsinΒ
authored
a
paper
7 days ago
mitschΒ
authored
a
paper
7 days ago
Post
5141
Google just released PaliGemma 2 Mix: new versatile instruction vision language models π₯
> Three new models: 3B, 10B, 28B with res 224, 448 π
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything π€―
Read more https://huggingface.co./blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4
> Three new models: 3B, 10B, 28B with res 224, 448 π
> Can do vision language tasks with open-ended prompts, understand documents, and segment or detect anything π€―
Read more https://huggingface.co./blog/paligemma2mix
Try the demo google/paligemma2-10b-mix
All models are here google/paligemma-2-mix-67ac6a251aaf3ee73679dcc4
andsteingΒ
updated
a
Space
10 days ago
Post
4641
Your weekly recap of open AI is here, and it's packed with models!
merve/feb-14-releases-67af876b404cc27c6d837767
π 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
π¬ 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
π£οΈ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings
πΌοΈ 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
π 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
π¬ 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
π£οΈ Audio
> Zonos-v0.1 is a new family of speech recognition models, which contains the model itself and embeddings
πΌοΈ 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
merveΒ
updated
a
Space
18 days ago
Post
3065
Interesting releases in open AI this week, let's recap π€
merve/feb-7-releases-67a5f7d7f172d8bfe0dd66f4
π€ Robotics
> Pi0, first open-source foundation vision-language action model was released in Le Robot (Apache 2.0)
π¬ 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 π€― 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
π 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
πΌοΈ Vision
> BiRefNet_HR is a new higher resolution BiRefNet for background removal
π£οΈ Audio
> kyutai released Hibiki, it's a real-time speech-to-speech translation model π€― 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
πΌοΈ 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
π€ Robotics
> Pi0, first open-source foundation vision-language action model was released in Le Robot (Apache 2.0)
π¬ 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 π€― 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
π 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
πΌοΈ Vision
> BiRefNet_HR is a new higher resolution BiRefNet for background removal
π£οΈ Audio
> kyutai released Hibiki, it's a real-time speech-to-speech translation model π€― 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
πΌοΈ 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
Post
7751
We did it. Kokoro TTS (v1.0) can now run 100% locally in your browser w/ WebGPU acceleration. Real-time text-to-speech without a server. β‘οΈ
Generate 10 seconds of speech in ~1 second for $0.
What will you build? π₯
webml-community/kokoro-webgpu
The most difficult part was getting the model running in the first place, but the next steps are simple:
βοΈ Implement sentence splitting, allowing for streamed responses
π Multilingual support (only phonemization left)
Who wants to help?
Generate 10 seconds of speech in ~1 second for $0.
What will you build? π₯
webml-community/kokoro-webgpu
The most difficult part was getting the model running in the first place, but the next steps are simple:
βοΈ Implement sentence splitting, allowing for streamed responses
π Multilingual support (only phonemization left)
Who wants to help?
- 9 replies
merveΒ
updated
12
models
21 days ago
google/paligemma2-28b-mix-448-jax
Image-Text-to-Text
β’
Updated
β’
1
google/paligemma2-28b-mix-448
Image-Text-to-Text
β’
Updated
β’
471
β’
24
google/paligemma2-28b-mix-224-jax
Image-Text-to-Text
β’
Updated
google/paligemma2-28b-mix-224
Image-Text-to-Text
β’
Updated
β’
77
β’
4
google/paligemma2-10b-mix-224-jax
Image-Text-to-Text
β’
Updated
β’
4
google/paligemma2-10b-mix-448
Image-Text-to-Text
β’
Updated
β’
6.7k
β’
21
google/paligemma2-10b-mix-224
Image-Text-to-Text
β’
Updated
β’
667
β’
7
google/paligemma2-10b-mix-448-jax
Image-Text-to-Text
β’
Updated
β’
4
google/paligemma2-3b-mix-448-jax
Image-Text-to-Text
β’
Updated
β’
5
β’
2
google/paligemma2-3b-mix-448
Image-Text-to-Text
β’
Updated
β’
6.55k
β’
36
google/paligemma2-3b-mix-224-jax
Image-Text-to-Text
β’
Updated
β’
3
β’
1
google/paligemma2-3b-mix-224
Image-Text-to-Text
β’
Updated
β’
3.55k
β’
21