Akihito Miyazaki PRO

Akjava

https://github.com/akjava/godot-huggingface-chain

akjava

AI & ML interests

I'm developing a user-friendly, browser-based platform that allows users to connect various AI services like ChatGPT, Gemini, local LLMs, Hugging Face models, and more. Our goal is to empower users to build custom AI tools by seamlessly combining these services, similar to Langchain or ComfyUI.

Recent Activity

liked a Space about 4 hours ago

smolagents/smolagents_leaderboard

liked a Space about 18 hours ago

ariG23498/phi4-multimodal

liked a Space 1 day ago

tencent/Hunyuan3D-2

View all activity

Organizations

None yet

Akjava's activity

liked a Space about 4 hours ago

smolagents LLM leaderboard

🏆

A leaderboard for LLMs powering smolagents

liked a Space about 18 hours ago

Phi4 Multimodal

🦀

Space demoing Phi4 MultiModal

liked a Space 1 day ago

1.84k

Hunyuan3D-2.0

🌍

Text-to-3D and Image-to-3D Generation

posted an update 1 day ago

Post

392

reacted to m-ric's post with 👍 2 days ago

Post

4107

We now have a Deep Research for academia: SurveyX automatically writes academic surveys nearly indistinguishable from human-written ones 🔥

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.

🎯 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 “AttributeTree” object that structures key information from citations. Ablating these AttributeTrees significantly decreased structure and synthesis scores, so they were really useful!

📝 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 🏆

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! 👉 SurveyX: Academic Survey Automation via Large Language Models (2502.14776)
Their website shows examples of generated surveys 👉 http://www.surveyx.cn/

posted an update 12 days ago

Post

2479

I shared smolagents examples

Akjava/open_Deep-Research-DuckDuckGo
Akjava/open_Deep-Research-DuckDuckGo-Groq

Replacing img-src to "#" in mdconvert.py help reducing tokens
I added translate final answer to my language