IPO-Mine
Collection
All the datasets and models used in the paper titled IPO-Mine: A Toolkit and Dataset for Section-Structured Analysis of Long, Multimodal IPO Documents • 3 items • Updated • 4
AI & ML interests
A hub for Finance education, research and industry in the Southeast.
Recent Activity
View all activity
siddharthlohani
updated a
collection about 1 month ago
siddharthlohani
published a
model about 1 month ago
siddharthlohani
updated a
model about 1 month ago
siddharthlohani
updated a
collection about 1 month ago
siddharthlohani
published a
dataset about 1 month ago
siddharthlohani
updated a
collection about 1 month ago
siddharthlohani
updated a
dataset about 1 month ago
Dataset Viewer issue: JobManagerCrashedError
3
#2 opened about 1 month ago
by 
siddharthlohani
Update README.md
#3 opened about 1 month ago
by 
lhoestq
siddharthlohani
updated a
dataset about 1 month ago
siddharthlohani
published a
dataset about 1 month ago
Nikita-A-Tatarinov
updated a
Space 2 months ago
Nikita-A-Tatarinov
updated a
dataset 2 months ago
Akhil-Theerthala
submitted a
paper to Daily Papers 2 months ago
Akhil-Theerthala
authored a
paper 2 months ago
Nikita-A-Tatarinov
published a
Space 2 months ago
Akhil-Theerthala
posted an update 3 months ago
Post
437
Is it better to show a model too many images once (Diversity), or extract as much information from a small set of images?
I have always wanted to do an ablation study on this and recently I got the chance to do exactly that. Why? In applied domains like robotics, manufacturing, or banking, we rarely have the luxury of internet-scale diverse image datasets. We are often "Data Poor" in terms of diversity but "Data Rich" in depth.
The takeaway? Density is efficient for facts but dangerous for reasoning (logical collapse) if you don't have larger scale data.
More details:
https://huggingface.co/blog/Akhil-Theerthala/diversity-density-for-vision-language-models
I have always wanted to do an ablation study on this and recently I got the chance to do exactly that. Why? In applied domains like robotics, manufacturing, or banking, we rarely have the luxury of internet-scale diverse image datasets. We are often "Data Poor" in terms of diversity but "Data Rich" in depth.
The takeaway? Density is efficient for facts but dangerous for reasoning (logical collapse) if you don't have larger scale data.
More details:
https://huggingface.co/blog/Akhil-Theerthala/diversity-density-for-vision-language-models
- 1 reply
Akhil-Theerthala
posted an update 4 months ago
Post
1358
For anyone who likes to get their papers summarized, I've tried to make a bentocard summarizer for research papers, that enables us to get overviews of the papers, with possible deepdives where interested. Of course, this has to be improved a lot, so do check the space and give your feedback!
Akhil-Theerthala/PaperStack
Some sample bentogrids are as follows:
Akhil-Theerthala/PaperStack
Some sample bentogrids are as follows:
Akhil-Theerthala
updated a
Space 5 months ago
huzaifahp7
updated a
dataset 5 months ago