After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System
Paper • 2610.37695 • Published • 4
👋 Open to Work
Bo Zou
ZouBo
zongyuhong's profile picture
webbrain-one-18314's profile picture
webbrain-one-703312's profile picture·
AI & ML interests
Natural Language Processing, Text Generation, Creative Writing
Recent Activity
posted an update 5 days ago
After one-click video, ask yourself one question first: am I making work-type content, or service-type content?
Our team has made science videos since 2013. One video used to take a few people three to five days. Now a person who has never made a video can make twenty a day with a top model. So a question that hardly mattered before now matters for creators, tool builders and model researchers.
We wrote a short article about it. Our paper also uses a simple model, and a demo you can play, to show why the recommendation pool on free platforms stops working when content grows too fast.
Article: https://huggingface.co/blog/BreadStudio/after-one-click-video-ask-one-question
Demo: https://huggingface.co/spaces/BreadStudio/recommendation-pool
Paper: https://huggingface.co/papers/2610.37695
published an article 5 days ago
一键出片之后，先问自己一个问题Organizations
authored a
paper 4 days ago
posted an update 5 days ago
Post
56
After one-click video, ask yourself one question first: am I making work-type content, or service-type content?
Our team has made science videos since 2013. One video used to take a few people three to five days. Now a person who has never made a video can make twenty a day with a top model. So a question that hardly mattered before now matters for creators, tool builders and model researchers.
We wrote a short article about it. Our paper also uses a simple model, and a demo you can play, to show why the recommendation pool on free platforms stops working when content grows too fast.
Article: https://huggingface.co/blog/BreadStudio/after-one-click-video-ask-one-question
Demo: BreadStudio/recommendation-pool
Paper: After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System (2610.37695)
Our team has made science videos since 2013. One video used to take a few people three to five days. Now a person who has never made a video can make twenty a day with a top model. So a question that hardly mattered before now matters for creators, tool builders and model researchers.
We wrote a short article about it. Our paper also uses a simple model, and a demo you can play, to show why the recommendation pool on free platforms stops working when content grows too fast.
Article: https://huggingface.co/blog/BreadStudio/after-one-click-video-ask-one-question
Demo: BreadStudio/recommendation-pool
Paper: After One-Click Video: The Inflow of Service-Type Content, the Failure of the Recommendation Pool Mechanism, and the BoLe System (2610.37695)
published an article 5 days ago
Article
一键出片之后，先问自己一个问题
BreadStudio
• published an article 5 days ago
Article
After One-Click Video, Ask Yourself One Question First
BreadStudio
• submitted a
paper to Daily Papers 5 days ago
updated a
Space 5 days ago
published a
Space 5 days ago
posted an update 8 days ago
Post
75
Our paper WORTH Benchmark is on Daily Papers today.
Models read an original mystery story with no clues marked. They have to find the key clue sentences on their own and decide who took part in the homicide. Finding clues and naming the right people turned out to be two different skills.
You can play the Episode 01 task yourself, in English, in your browser:
BreadStudio/worth-ep01-en
Paper: WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot (2610.27597)
Models read an original mystery story with no clues marked. They have to find the key clue sentences on their own and decide who took part in the homicide. Finding clues and naming the right people turned out to be two different skills.
You can play the Episode 01 task yourself, in English, in your browser:
BreadStudio/worth-ep01-en
Paper: WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode Pilot (2610.27597)
submitted a
paper to Daily Papers 8 days ago
updated a
Space 10 days ago
published a
Space 10 days ago
published an article 12 days ago
Article
WORTH Notes #1: Who Decides the Clues?｜WORTH 札记 #1：线索由谁决定？
BreadStudio
• published an article 12 days ago
Article
一条没叫的狗：大模型能找到没人指给它的线索吗？
BreadStudio
• published an article 12 days ago
Article
The Dog That Did Not Bark: Can an LLM Find the Clues Nobody Points Out?
BreadStudio
• authored 2
papers 13 days ago
updated a
Space 13 days ago
updated a
Space 22 days ago
published a
Space 22 days ago
published an article 26 days ago
Article
【观察】Opus 5.5 做视频，强在哪一层？——一个小团队的制作笔记
BreadStudio
•