Multi-modal Attribute Prompting for Vision-Language Models
Paper
•
2403.00219
•
Published
•
1
Valeriia Kuka
valeriiakuka
AI & ML interests
Learning AI & ML daily and making it more accessible through clear, concise, and exciting content.
Recent Activity
upvoted
a
paper
3 days ago
Multi-modal Attribute Prompting for Vision-Language Models
upvoted
a
paper
3 days ago
Prompting as Probing: Using Language Models for Knowledge Base
Construction
upvoted
a
paper
3 days ago
The Prompt Report: A Systematic Survey of Prompting Techniques
Organizations
valeriiakuka's activity
upvoted
4
papers
3 days ago
Prompting as Probing: Using Language Models for Knowledge Base Construction
Paper
•
2208.11057
•
Published
•
3
The Prompt Report: A Systematic Survey of Prompting Techniques
Paper
•
2406.06608
•
Published
•
60
Tree Prompting: Efficient Task Adaptation without Fine-Tuning
Paper
•
2310.14034
•
Published
•
3
upvoted
a
paper
9 days ago
upvoted
an
article
2 months ago
Article
Halo: Open Source Health Tracking with Wearables
By
•
•
107
reacted to
clem's
post with 🚀
3 months ago
Post
4676
Six predictions for AI in 2025 (and a review of how my 2024 predictions turned out):
- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.
How my predictions for 2024 turned out:
- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
✅ (Inflexion, AdeptAI,...)
- Open-source LLMs will reach the level of the best closed-source LLMs
✅ with QwQ and dozens of others
- Big breakthroughs in AI for video, time-series, biology and chemistry
✅ for video 🔴for time-series, biology and chemistry
- We will talk much more about the cost (monetary and environmental) of AI
✅Monetary 🔴Environmental (😢)
- A popular media will be mostly AI-generated
✅ with NotebookLM by Google
- 10 millions AI builders on Hugging Face leading to no increase of unemployment
🔜currently 7M of AI builders on Hugging Face
- There will be the first major public protest related to AI
- A big company will see its market cap divided by two or more because of AI
- At least 100,000 personal AI robots will be pre-ordered
- China will start to lead the AI race (as a consequence of leading the open-source AI race).
- There will be big breakthroughs in AI for biology and chemistry.
- We will begin to see the economic and employment growth potential of AI, with 15M AI builders on Hugging Face.
How my predictions for 2024 turned out:
- A hyped AI company will go bankrupt or get acquired for a ridiculously low price
✅ (Inflexion, AdeptAI,...)
- Open-source LLMs will reach the level of the best closed-source LLMs
✅ with QwQ and dozens of others
- Big breakthroughs in AI for video, time-series, biology and chemistry
✅ for video 🔴for time-series, biology and chemistry
- We will talk much more about the cost (monetary and environmental) of AI
✅Monetary 🔴Environmental (😢)
- A popular media will be mostly AI-generated
✅ with NotebookLM by Google
- 10 millions AI builders on Hugging Face leading to no increase of unemployment
🔜currently 7M of AI builders on Hugging Face
- 4 replies
liked
a
Space
3 months ago
upvoted
an
article
10 months ago
Article
Mixture of Experts Explained
•
454
reacted to
chiphuyen's
post with ❤️
12 months ago
Post
It feels awkward having my first post sharing my stuff, but this is a weekend project that I really enjoyed working on. I'd love to meet more people interested in random ideas like this.
A hard part of building AI applications is choosing which model to use. What if we don’t have to? What if we can predict the best model for any prompt?
Predictive human preference aims to predict which model users might prefer for a specific query.
https://huyenchip.com/2024/02/28/predictive-human-preference.html
One use case is model routing. If we know in advance that for a prompt, users will prefer Claude Instant’s response over GPT-4, and Claude Instant is cheaper/faster than GPT-4, we can route this prompt to Claude Instant. Model routing has the potential to increase response quality while reducing costs and latency.
One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are more likely to prefer stronger models. Here’s a visualization of predicted human preference for an easy prompt (“hello, how are you?”) and a challenging prompt (“Explain why Planc length …”).
Preference predictors make it possible to create leaderboards unique to any prompt and domain.
A hard part of building AI applications is choosing which model to use. What if we don’t have to? What if we can predict the best model for any prompt?
Predictive human preference aims to predict which model users might prefer for a specific query.
https://huyenchip.com/2024/02/28/predictive-human-preference.html
One use case is model routing. If we know in advance that for a prompt, users will prefer Claude Instant’s response over GPT-4, and Claude Instant is cheaper/faster than GPT-4, we can route this prompt to Claude Instant. Model routing has the potential to increase response quality while reducing costs and latency.
One pattern is that for simple prompts, weak models can do (nearly) as well as strong models. For more challenging prompts, however, users are more likely to prefer stronger models. Here’s a visualization of predicted human preference for an easy prompt (“hello, how are you?”) and a challenging prompt (“Explain why Planc length …”).
Preference predictors make it possible to create leaderboards unique to any prompt and domain.
- 3 replies