Srihari Thyagarajan
Haleshot
AI & ML interests
AI, ML, DL, CV, RecSys
Recent Activity
liked
a Space
12 days ago
franciszzj/Leffa
reacted
to
singhsidhukuldeep's
post
with 🚀
17 days ago
Exciting breakthrough in AI Recommendation Systems! Just read a fascinating paper from Meta AI and UW-Madison researchers on unifying generative and dense retrieval methods for recommendations.
The team introduced LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a novel hybrid approach that combines the best of both worlds:
Key Technical Innovations:
- Integrates semantic ID-based generative retrieval with dense embedding methods
- Uses a T5 encoder-decoder architecture with 6 layers, 6 attention heads, and 128-dim embeddings
- Processes item attributes through sentence-T5-XXL for text representations
- Employs a dual-objective training approach combining cosine similarity and next-token prediction
- Implements beam search with size K for candidate generation
- Features an RQ-VAE with 3-layer MLP for semantic ID generation
Performance Highlights:
- Significantly outperforms traditional methods on cold-start recommendations
- Achieves state-of-the-art results on major benchmark datasets (Amazon Beauty, Sports, Toys, Steam)
- Reduces computational complexity from O(N) to O(tK) where t is semantic ID count
- Maintains minimal storage requirements while improving recommendation quality
The most impressive part? LIGER effectively solves the cold-start problem that has long plagued recommendation systems while maintaining computational efficiency.
This could be a game-changer for e-commerce platforms and content recommendation systems!
What are your thoughts on hybrid recommendation approaches?
reacted
to
singhsidhukuldeep's
post
with 👍
17 days ago
Exciting breakthrough in AI Recommendation Systems! Just read a fascinating paper from Meta AI and UW-Madison researchers on unifying generative and dense retrieval methods for recommendations.
The team introduced LIGER (LeveragIng dense retrieval for GEnerative Retrieval), a novel hybrid approach that combines the best of both worlds:
Key Technical Innovations:
- Integrates semantic ID-based generative retrieval with dense embedding methods
- Uses a T5 encoder-decoder architecture with 6 layers, 6 attention heads, and 128-dim embeddings
- Processes item attributes through sentence-T5-XXL for text representations
- Employs a dual-objective training approach combining cosine similarity and next-token prediction
- Implements beam search with size K for candidate generation
- Features an RQ-VAE with 3-layer MLP for semantic ID generation
Performance Highlights:
- Significantly outperforms traditional methods on cold-start recommendations
- Achieves state-of-the-art results on major benchmark datasets (Amazon Beauty, Sports, Toys, Steam)
- Reduces computational complexity from O(N) to O(tK) where t is semantic ID count
- Maintains minimal storage requirements while improving recommendation quality
The most impressive part? LIGER effectively solves the cold-start problem that has long plagued recommendation systems while maintaining computational efficiency.
This could be a game-changer for e-commerce platforms and content recommendation systems!
What are your thoughts on hybrid recommendation approaches?
Organizations
Haleshot's activity
Thanks a lot for this space!
1
#1 opened 3 months ago
by
Haleshot
Update README.md
#3 opened 5 months ago
by
Haleshot
Regarding quantized .gguf models
2
#1 opened 5 months ago
by
Haleshot
My alternative quantizations.
5
#5 opened 6 months ago
by
ZeroWw
Model doesn't seem to be giving correct outputs.
#1 opened 5 months ago
by
Haleshot
ImportError: cannot import name 'LlavaNextProcessor' from 'transformers'
3
#21 opened 6 months ago
by
Haleshot
ImportError: cannot import name 'LlavaNextProcessor' from 'transformers'
3
#21 opened 6 months ago
by
Haleshot
ImportError: cannot import name 'LlavaNextProcessor' from 'transformers'
3
#21 opened 6 months ago
by
Haleshot