Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders
Paper
• 2603.06569 • Published
• 105
Gradio-Blocks-Party
company
AI & ML interests
None defined yet.
Recent Activity
View all activity
lkeab
authored a paper 8 days ago
AlekseyKorshuk
authored a paper 27 days ago
1aurent
authored a paper about 1 month ago
AlekseyKorshuk
authored a paper 2 months ago
lkeab
submitted a paper to Daily Papers 3 months ago
lkeab
authored 10 papers 3 months ago
Mask Transfiner for High-Quality Instance Segmentation
Paper
• 2111.13673 • Published
Cascade-DETR: Delving into High-Quality Universal Object Detection
Paper
• 2307.11035 • Published
Gaussian Grouping: Segment and Edit Anything in 3D Scenes
Paper
• 2312.00732 • Published
• 3
Mask-Free Video Instance Segmentation
Paper
• 2303.15904 • Published
Matching Anything by Segmenting Anything
Paper
• 2406.04221 • Published
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
Paper
• 2405.02280 • Published
SLAck: Semantic, Location, and Appearance Aware Open-Vocabulary Tracking
Paper
• 2409.11235 • Published
Multi-View 3D Point Tracking
Paper
• 2508.21060 • Published
• 23
RobotArena $\infty$: Scalable Robot Benchmarking via Real-to-Sim Translation
Paper
• 2510.23571 • Published
• 9
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing
Paper
• 2512.10284 • Published
• 26
Aurelien-Morgan
posted an
update 3 months ago
Post
355
Hey, I went to Hangzhou to talk about
The recording just got released. Go check it out !
https://www.youtube.com/watch?v=nmrMachM5aM
Slides are there :
https://docs.google.com/presentation/d/1hnAzHJ0SbeAOtGJir-iH84RBtXT1OxVT/
retrain-pipelines at the GOSIM Foundation's conference last september.The recording just got released. Go check it out !
https://www.youtube.com/watch?v=nmrMachM5aM
Slides are there :
https://docs.google.com/presentation/d/1hnAzHJ0SbeAOtGJir-iH84RBtXT1OxVT/
-
- 2 replies
runtime error
2
#10 opened 4 months ago
by
liangnanying
hysts
updated a Space 4 months ago
dawood
authored a paper 4 months ago
Post
1823
Multilingual Tokenization Showdown
Analyzing 12 LLM Tokenizers Across 204 Languages.
First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages:
Norod78/WikiCat-Multilingual
For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language).
You can see a slideshow summary of the results here:
https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html
I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo:
https://github.com/Norod/wikicat-tokenizer-eval
Post on X:
https://x.com/Norod78/status/1984366900550266999
Analyzing 12 LLM Tokenizers Across 204 Languages.
First, I've created a dataset with Wikipedia's "Cat" article text in 272 languages:
Norod78/WikiCat-Multilingual
For each language entry with at least 100 words, I tokenized the text using 12 tokenizers and calculated the "Characters per token" ratio and "Word per token" ratio. The higher this ratio is, the more information each token represents on average for that language (and perhaps allowing the llm to potentially learn more per-parameter if trained on a dataset of that language).
You can see a slideshow summary of the results here:
https://norod.github.io/wikicat-tokenizer-eval/tokenizer-slideshow.html
I hope I interpreted the results correctly, I've made the code available on GitHub so you can re-create the raw results jsonl with this repo:
https://github.com/Norod/wikicat-tokenizer-eval
Post on X:
https://x.com/Norod78/status/1984366900550266999