google/gemma-3n-E4B-it
Image-Text-to-Text
•
8B
•
Updated
•
5.55k
•
182
Dmitry Ryumin
DmitryRyumin
AI & ML interests
Machine Learning and Applications, Multi-Modal Understanding
Recent Activity
liked
a model
1 day ago
google/gemma-3n-E4B-it
liked
a model
5 days ago
MeiGen-AI/MeiGen-MultiTalk
liked
a Space
5 days ago
Ekaterina2002/diabetes-catboost
Organizations
liked
a
model
1 day ago
liked
a
model
5 days ago
liked
a
Space
5 days ago
reacted to
merve's
post with 🔥
9 days ago
Post
2423
#CVPR2025 Paper Picks #1
VisionZip is a compression technique that reduces number of visual tokens to improve performance AND prefill time for vision language models
demo: Senqiao/VisionZip
paper: VisionZip: Longer is Better but Not Necessary in Vision Language Models (2412.04467)
most of the image tokens are redundant for the LLM, so the authors ask "are all visual tokens necessary?"
the method is simple:
find which tokens have the highest attention score, merge rest of the tokens based on similarity, then merge both
their method is both training-free and for fine-tuning
the authors report 5 point improvement on average of vision language tasks + 8x improvement in prefilling time for Llava-Next 7B and 13B 🤯
removing redundant tokens improve image token quality too 🥹
VisionZip is a compression technique that reduces number of visual tokens to improve performance AND prefill time for vision language models
demo: Senqiao/VisionZip
paper: VisionZip: Longer is Better but Not Necessary in Vision Language Models (2412.04467)
most of the image tokens are redundant for the LLM, so the authors ask "are all visual tokens necessary?"
the method is simple:
find which tokens have the highest attention score, merge rest of the tokens based on similarity, then merge both
their method is both training-free and for fine-tuning
the authors report 5 point improvement on average of vision language tasks + 8x improvement in prefilling time for Llava-Next 7B and 13B 🤯
removing redundant tokens improve image token quality too 🥹
liked
a
Space
9 days ago
reacted to
merve's
post with ❤️
9 days ago
Post
3574
Releases of the past week are here
merve/releases-june-13-6852c3c1eaf1e0c24c958860
Here's our picks 🤓
So many interesting models released past week in open AI! 🤖
🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)
Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)
🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model
3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts
Here's our picks 🤓
So many interesting models released past week in open AI! 🤖
🖼️ Computer Vision/VLMs
> nanonets/Nanonets-OCR-s is the new state-of-the-art OCR model that can handle checkboxes, watermarks, tables (OS)
> Meta released facebook/v-jepa-2-6841bad8413014e185b497a6, new sota video embeddings with two new classification models (OS)
> ByteDance-Seed/SeedVR2-3B is a new 3B video restoration model (OS)
Audio
> Stepfun released stepfun-ai/Step-Audio-AQAA, new large (137B 🤯) audio language model that takes in audio and generates audio (OS)
🤖 Robotics
> nvidia released nvidia/GR00T-N1.5-3B, new open foundation vision language action model
3D
> tencent/Hunyuan3D-2.1 is the new version of Hunyuan by Tencent that can generate 3D assets from text and image prompts
liked
a
Space
9 days ago
liked
a
Space
13 days ago
liked
a
Space
20 days ago
upvoted
a
collection
22 days ago
liked
2
Spaces
25 days ago
updated
a
Space
26 days ago
published
a
Space
27 days ago
liked
a
Space
28 days ago
liked
2
models
about 1 month ago
reacted to
AdinaY's
post with 🚀
about 1 month ago
Post
2805
ByteDance is absolutely cooking lately🔥
BAGEL 🥯 7B active parameter open multimodal foundation model by Bytedance Seed team.
ByteDance-Seed/BAGEL-7B-MoT
✨ Apache 2.0
✨ Outperforms top VLMs (Qwen2.5-VL & InternVL-2.5)
✨ Mixture-of-Transformer-Experts + dual encoders
✨ Trained on trillions of interleaved tokens
BAGEL 🥯 7B active parameter open multimodal foundation model by Bytedance Seed team.
ByteDance-Seed/BAGEL-7B-MoT
✨ Apache 2.0
✨ Outperforms top VLMs (Qwen2.5-VL & InternVL-2.5)
✨ Mixture-of-Transformer-Experts + dual encoders
✨ Trained on trillions of interleaved tokens
liked
a
model
about 1 month ago
liked
a
Space
about 1 month ago