vlmbook/images
Viewer
•
Updated
•
4
•
103
•
1
Merve Noyan PRO
merve
AI & ML interests
VLMs, vision & co
Recent Activity
updated
a dataset
about 8 hours ago
vlmbook/images
replied to
their
post
about 11 hours ago
Don't sleep on new AI at Meta Vision-Language release! 🔥
https://huggingface.co./collections/facebook/perception-encoder-67f977c9a65ca5895a7f6ba1
https://huggingface.co./collections/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
updated
a dataset
about 11 hours ago
huggingfacejs/tasks
Organizations
merve's activity
updated
a
dataset
about 8 hours ago
replied to
their
post
about 11 hours ago
yess, we are collaborating with the authors to sprint this!
updated
a
dataset
about 11 hours ago
posted
an
update
3 days ago
Post
3621
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
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
upvoted
a
paper
3 days ago
upvoted
2
collections
4 days ago
posted
an
update
5 days ago
Post
3223
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 👏
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 👏
Add license to model metadata
#2 opened 5 days ago
by
merve
License
1
1
#1 opened 5 days ago
by
merve
updated
a
dataset
6 days ago
liked
a
Space
6 days ago
published
a
dataset
6 days ago
published
a
dataset
9 days ago
commented on
Cohere on Hugging Face Inference Providers 🔥
11 days ago
@borgr hello! as of now there's no such option, but we'll consider this, you want this for data labelling right? ☺️ for now you can use the providers programmatically and store them yourself I think
updated
2
collections
12 days ago
liked
a
model
12 days ago
