CASA: Cross-Attention via Self-Attention for Efficient Vision-Language Fusion
Paper
•
2512.19535
•
Published
•
10
AI & ML interests
None defined yet.
Recent Activity
View all activity
nielsr
submitted
a
paper
to Daily Papers
9 days ago
Fix dtype for the language model
2
#46 opened 11 days ago
by
qgallouedec
Multiple Image Tokens
2
#60 opened 29 days ago
by
rogergheser
RaushanTurganbay
updated
5
models
about 2 months ago
llava-hf/LLaVA-NeXT-Video-7B-32K-hf
Image-Text-to-Text
•
8B
•
Updated
•
204
•
8
llava-hf/LLaVA-NeXT-Video-7B-DPO-hf
Video-Text-to-Text
•
7B
•
Updated
•
425
•
11
llava-hf/LLaVA-NeXT-Video-34B-DPO-hf
Image-Text-to-Text
•
35B
•
Updated
•
84
•
6
llava-hf/LLaVA-NeXT-Video-34B-hf
Video-Text-to-Text
•
35B
•
Updated
•
790
•
11
llava-hf/LLaVA-NeXT-Video-7B-hf
Video-Text-to-Text
•
7B
•
Updated
•
63.7k
•
121
Post
7454
deepseek-ai/DeepSeek-OCR is out! 🔥 my take ⤵️
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
> pretty insane it can parse and re-render charts in HTML
> it uses CLIP and SAM features concatenated, so better grounding
> very efficient per vision tokens/performance ratio
> covers 100 languages
- 4 replies
Post
6807
large AI labs open-sourced a ton of models last week 🔥
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
here's few picks, find even more here merve/sep-16-releases-68d13ea4c547f02f95842f05 🤝
> IBM released a new Docling model with 258M params based on Granite (A2.0) 📝 ibm-granite/granite-docling-258M
> Xiaomi released 7B audio LM with base and instruct variants (MIT) XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0
> DecartAI released Lucy Edit, open Nano Banana 🍌 (NC) decart-ai/Lucy-Edit-Dev
> OpenGVLab released a family of agentic computer use models (3B/7B/32B) with the dataset 💻 OpenGVLab/scalecua-68c912cf56f7ff4c8e034003
> Meituan Longcat released thinking version of LongCat-Flash 💭 meituan-longcat/LongCat-Flash-Thinking
- 2 replies
Post
3389
IBM just released small swiss army knife for the document models: granite-docling-258M on Hugging Face 🔥
> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
> not only a document converter but also can do document question answering, understand multiple languages 🤯
> best part: released with Apache 2.0 license 👏 use it with your commercial projects!
> it supports transformers, vLLM and MLX from the get-go! 🤗
> built on SigLIP2 & granite-165M
model: ibm-granite/granite-docling-258M
demo: ibm-granite/granite-docling-258m-demo 💗
Post
1198
a ton of image/video generation models and LLMs from big labs 🔥
> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use 💬
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR 📝
> ByteDance released bytedance-research/HuMo, video generation from any input ⏯️
find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
> Meta released facebook/mobilellm-r1-68c4597b104fac45f28f448e, smol LLMs for on-device use 💬
> Tencent released tencent/SRPO, high res image generation model and tencent/POINTS-Reader, cutting edge OCR 📝
> ByteDance released bytedance-research/HuMo, video generation from any input ⏯️
find more models, datasets, demos here merve/sep-11-releases-68c7dbfa26bea8cd921fa0ac
Post
1005
fan-favorite vision LM Florence-2 is now officially supported in transformers 🤗
find all the models in
florence-community
org 🫡
find all the models in
Post
1823
past week was great for open LLMs 🔥
merve/sep-1-releases-68bede0e729c12597eefd050
> Google released google/embeddinggemma-300m, new embedding model with 300M params
> new update to Kimi-K2 just landed moonshotai/Kimi-K2-Instruct-0905 😍
> OpenBMB released a new version to MiniCPM with 8B params openbmb/MiniCPM4.1-8B
also soooo many Qwen-Image & Kontext LoRAs dropped!
> Google released google/embeddinggemma-300m, new embedding model with 300M params
> new update to Kimi-K2 just landed moonshotai/Kimi-K2-Instruct-0905 😍
> OpenBMB released a new version to MiniCPM with 8B params openbmb/MiniCPM4.1-8B
also soooo many Qwen-Image & Kontext LoRAs dropped!
Post
3706
upgrade your transformers 🔥
it comes with insanely capable models like merve/sam2-66ac9deac6fca3bc5482fe30, microsoft/kosmos-2.5, and more 🫡
I built a notebook you can run with free Colab T4 to walk through the API for new models 🙋🏻♀️ merve/smol-vision
fine-tuning will follow-up soon!
it comes with insanely capable models like merve/sam2-66ac9deac6fca3bc5482fe30, microsoft/kosmos-2.5, and more 🫡
I built a notebook you can run with free Colab T4 to walk through the API for new models 🙋🏻♀️ merve/smol-vision
fine-tuning will follow-up soon!
Post
6287
large AI labs have dropped so many open models last week 🔥 don't miss out on them
→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B
find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
→ Apple released on-device vision LMs apple/fastvlm-68ac97b9cd5cacefdd04872e & apple/mobileclip2-68ac947dcb035c54bcd20c47
→ OpenGVLab released InternVL3.5, 32 new vision LMs with one based on gpt-oss! (OS) OpenGVLab/internvl35-68ac87bd52ebe953485927fb
→ MSFT released a killer small TTS model (OS) microsoft/VibeVoice-1.5B
find more herehttps://huggingface.co/collections/merve/august-29-releases-68b5a3754cfb8abf59e2b486
- 1 reply
Post
6072
first vision language model built off
openai/gpt-oss-20b just dropped! 🔥
InternVL3.5 comes with 32 models 🤯 pre-trained, fine-tuned, aligned in various sizes OpenGVLab/internvl35-68ac87bd52ebe953485927fb
comes with gpt-oss or Qwen3 for LLM part ⤵️
InternVL3.5 comes with 32 models 🤯 pre-trained, fine-tuned, aligned in various sizes OpenGVLab/internvl35-68ac87bd52ebe953485927fb
comes with gpt-oss or Qwen3 for LLM part ⤵️
- 1 reply
Post
13802
Okay this is insane... WebGPU-accelerated semantic video tracking, powered by DINOv3 and Transformers.js! 🤯
Demo (+ source code): webml-community/DINOv3-video-tracking
This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍
How does it work? 🤔
1️⃣ Generate and cache image features for each frame
2️⃣ Create a list of embeddings for selected patch(es)
3️⃣ Compute cosine similarity between each patch and the selected patch(es)
4️⃣ Highlight those whose score is above some threshold
... et voilà! 🥳
You can also make selections across frames to improve temporal consistency! This is super useful if the object changes its appearance slightly throughout the video.
Excited to see what the community builds with it!
Demo (+ source code): webml-community/DINOv3-video-tracking
This will revolutionize AI-powered video editors... which can now run 100% locally in your browser, no server inference required (costs $0)! 😍
How does it work? 🤔
1️⃣ Generate and cache image features for each frame
2️⃣ Create a list of embeddings for selected patch(es)
3️⃣ Compute cosine similarity between each patch and the selected patch(es)
4️⃣ Highlight those whose score is above some threshold
... et voilà! 🥳
You can also make selections across frames to improve temporal consistency! This is super useful if the object changes its appearance slightly throughout the video.
Excited to see what the community builds with it!
- 2 replies
Batch inputs (image, prompt)
7
#10 opened over 1 year ago
by
jeeyungk
Post
3321
GPT-4.1-mini level model right in your iPhone 🤯
openbmb/MiniCPM-V-4 is only 4B while surpassing GPT-4.1-mini in vision benchmarks 🔥
allows commercial use as well!
openbmb/MiniCPM-V-4 is only 4B while surpassing GPT-4.1-mini in vision benchmarks 🔥
allows commercial use as well!