Letβs make a generation of amazing image generation models
β’
30
Daniel Vila
dvilasuero
AI & ML interests
RLHF, RLAIF, DPO, data, data, data
Recent Activity
upvoted
an
article
2 days ago
Letβs make a generation of amazing image generation models
liked
a Space
2 days ago
PR-Puppets/PR-Puppet-Sora
liked
a Space
2 days ago
data-is-better-together/image-preferences-leaderboard
Articles
Organizations
dvilasuero's activity
upvoted
an
article
2 days ago
Article
Letβs make a generation of amazing image generation models
By
β’
β’
30
liked
3
Spaces
2 days ago
Reacted to
elliesleightholm's
post with π₯π€
6 days ago
Post
2692
I made a beginners guide to Hugging Face Spaces π€ I hope it's useful to some of you :)
YouTube video: https://www.youtube.com/watch?v=xqdTFyRdtjQ
Blog: https://www.marqo.ai/blog/how-to-create-a-hugging-face-space
YouTube video: https://www.youtube.com/watch?v=xqdTFyRdtjQ
Blog: https://www.marqo.ai/blog/how-to-create-a-hugging-face-space
- 8 replies
upvoted
a
collection
6 days ago
updated
a
collection
6 days ago
upvoted
a
collection
6 days ago
liked
2
Spaces
6 days ago
upvoted
an
article
6 days ago
Article
Halo: Open Source Health Tracking with Wearables
By
β’
β’
83
updated
a
Space
6 days ago
liked
a
dataset
7 days ago
updated
a
dataset
7 days ago
liked
a
dataset
8 days ago
[24/ 11] What are you working on this week! πͺ
15
#2 opened 8 days ago
by
reach-vb
reach-vb
Reacted to
andito's
post with β€οΈ
8 days ago
Post
1077
Hugging face presents FineVideo π₯! Unlocking the next generation of Video understanding π
π€―3400 hours of annotated Creative Common videos with rich character descriptions, scene splits, mood, and content descriptions per scene as well as QA pairs.
π₯
@mfarre processed over 2M videos of Youtube-CC to make this incredibly powerful selection.
Very psyched to fine-tune idefics on this dataset. β‘οΈ
Explore the videos: HuggingFaceFV/FineVideo-Explorer
π€―3400 hours of annotated Creative Common videos with rich character descriptions, scene splits, mood, and content descriptions per scene as well as QA pairs.
π₯
@mfarre processed over 2M videos of Youtube-CC to make this incredibly powerful selection.
Very psyched to fine-tune idefics on this dataset. β‘οΈ
Explore the videos: HuggingFaceFV/FineVideo-Explorer
Reacted to
singhsidhukuldeep's
post with π
8 days ago
Post
1242
Sorry judge, my lawyer hallucinated? π If you get an AI lawyer, you would want it to be hallucination-free!
New @Stanford -@Yale research reveals surprising findings about leading AI legal research tools. Here's what you need to know:
>> Key Findings
The study tested LexisNexis (Lexis+ AI), Thomson Reuters (Westlaw AI & Ask Practical Law AI), and GPT-4, finding hallucination rates between 17-33% despite claims of being "hallucination-free".
>> Technical Deep Dive
The research evaluated these tools using Retrieval-Augmented Generation (RAG) architecture, which operates in two crucial steps:
1. Retrieval System:
- Uses neural text embeddings to capture semantic meaning
- Employs both lexical and semantic search mechanisms
- Implements document filtering and extraction
- Retrieves relevant legal documents from vast databases
2. Generation Pipeline:
- Processes retrieved documents alongside original queries
- Synthesizes information from multiple legal sources
- Generates responses based on retrieved context
- Includes citation verification mechanisms
>> Performance Breakdown:
- Lexis+ AI: 65% accuracy rate
- Westlaw AI: 42% accuracy rate
- Ask Practical Law AI: Over 60% incomplete answers
>> Why This Matters
This research exposes critical vulnerabilities in AI legal tools that lawyers increasingly rely on. It's essential for legal professionals to understand these limitations when incorporating AI into their practice.
New @Stanford -@Yale research reveals surprising findings about leading AI legal research tools. Here's what you need to know:
>> Key Findings
The study tested LexisNexis (Lexis+ AI), Thomson Reuters (Westlaw AI & Ask Practical Law AI), and GPT-4, finding hallucination rates between 17-33% despite claims of being "hallucination-free".
>> Technical Deep Dive
The research evaluated these tools using Retrieval-Augmented Generation (RAG) architecture, which operates in two crucial steps:
1. Retrieval System:
- Uses neural text embeddings to capture semantic meaning
- Employs both lexical and semantic search mechanisms
- Implements document filtering and extraction
- Retrieves relevant legal documents from vast databases
2. Generation Pipeline:
- Processes retrieved documents alongside original queries
- Synthesizes information from multiple legal sources
- Generates responses based on retrieved context
- Includes citation verification mechanisms
>> Performance Breakdown:
- Lexis+ AI: 65% accuracy rate
- Westlaw AI: 42% accuracy rate
- Ask Practical Law AI: Over 60% incomplete answers
>> Why This Matters
This research exposes critical vulnerabilities in AI legal tools that lawyers increasingly rely on. It's essential for legal professionals to understand these limitations when incorporating AI into their practice.