To Be Tested
Collection
3 items
β’
Updated
UICO H
UICO
AI & ML interests
None yet
Recent Activity
updated
a collection
about 1 month ago
To Be Tested
updated
a collection
about 1 month ago
To Be Tested
liked
a model
about 1 month ago
google/gemma-3-27b-pt
Organizations
None yet
UICO's activity
updated
a
collection
about 1 month ago
liked
2
models
about 1 month ago
updated
a
collection
about 1 month ago
liked
a
model
about 1 month ago
Well done! Your technique is very impressiove! BTWοΌCould you provide quantization for QWQ-32B?
liked
3
models
about 1 month ago
liked
3
models
about 2 months ago
updated
a
collection
about 2 months ago
liked
a
model
about 2 months ago
reacted to
m-ric's
post with π€―
about 2 months ago
Post
4823
We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones π₯
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
π― For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an βAttributeTreeβ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
π For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 π
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! π SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys π http://www.surveyx.cn/
Researchers from Beijing and Shanghai just published the first application of a deep research system to academia: their algorithm, given a question, can give you a survey of all papers on the subject.
To make a research survey, you generally follow two steps, preparation (collect and organize papers) and writing (outline creation, writing, polishing). Researchers followed the same two steps and automated them.
π― For the preparation part, a key part is find all the important references on the given subject.
Researchers first cast a wide net of all relevant papers. But then finding the really important ones is like distilling knowledge from a haystack of information. To solve this challenge, they built an βAttributeTreeβ object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!
π For the writing part, key was to get a synthesis that's both short and true. This is not easy to get with LLMs! So they used methods like LLM-based deduplication to shorten the too verbose listings made by LLMs, and RAG to grab original quotes instead of made-up ones.
As a result, their system outperforms previous approaches by far!
As assessed by LLM-judges, the quality score os SurveyX even approaches this of human experts, with 4.59/5 vs 4.75/5 π
I advise you to read the paper, it's a great overview of the kind of assistants that we'll get in the short future! π SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys π http://www.surveyx.cn/
reacted to
ovi054's
post with π
about 2 months ago
Post
2621
Image-to-Vector β‘
ovi054/image-to-vector
Transform Images into Professional Vector Graphics
Convert your raster images (JPG, PNG, WEBP) into high-quality vector graphics (SVG) with our easy-to-use tool! Perfect for designers, artists, and anyone needing vector conversions.
π― Key Features:
Convert to scalable SVG vector graphics
Real-time preview of your SVG output
Advanced customization options
Clean, user-friendly interface
Batch processing ready
π οΈ Advanced Controls:
Color/B&W mode selection
Speckle filtering
Color precision adjustment
Layer management
Curve fitting options
π« Why Image-to-Vector?
No installation needed
Free to use
Professional-grade output
Simple yet powerful
π§ Technical Details:
Built with Gradio
Powered by VTracer
Optimized SVG generation
π Try it now: ovi054/image-to-vector
#computervision #vectorgraphics #imageprocessing #svg #design #ai
ovi054/image-to-vector
Transform Images into Professional Vector Graphics
Convert your raster images (JPG, PNG, WEBP) into high-quality vector graphics (SVG) with our easy-to-use tool! Perfect for designers, artists, and anyone needing vector conversions.
π― Key Features:
Convert to scalable SVG vector graphics
Real-time preview of your SVG output
Advanced customization options
Clean, user-friendly interface
Batch processing ready
π οΈ Advanced Controls:
Color/B&W mode selection
Speckle filtering
Color precision adjustment
Layer management
Curve fitting options
π« Why Image-to-Vector?
No installation needed
Free to use
Professional-grade output
Simple yet powerful
π§ Technical Details:
Built with Gradio
Powered by VTracer
Optimized SVG generation
π Try it now: ovi054/image-to-vector
#computervision #vectorgraphics #imageprocessing #svg #design #ai
upvoted
a
collection
about 2 months ago
reacted to
jjokah's
post with π
about 2 months ago
Post
4640
The past few years have been a blast for artificial intelligence, with large language models (LLMs) stunning everyone with their capabilities and powering everything from chatbots to code assistants. However, not all applications demand the massive size and complexity of LLMs, the computational power required makes them impractical for many use cases. This is why Small Language Models (SLMs) entered the scene to make powerful AI models more accessible by shrinking in size.
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
In this article we went through what SLMs are, how they are made small, their benefits and limitations, real-world use cases, and how they can be used on mobile and desktop devices.
https://huggingface.co/blog/jjokah/small-language-model
- 2 replies