Y-Research-SBU/CSR
Official Repository for CSR - ICML 2025 Oral
This project helps machine learning practitioners efficiently process and retrieve information from large datasets containing images, text, or a combination of both. It takes existing data embeddings and transforms them into a 'sparse' representation, allowing for faster and more cost-effective searches while maintaining accuracy. This is ideal for researchers and engineers building and deploying AI models.
Use this if you need to perform accurate content retrieval or classification on large image, text, or multimodal datasets with significantly reduced computational cost and faster inference.
Not ideal if your primary goal is to train a model from scratch without leveraging pre-trained embeddings or if your datasets are very small and efficiency is not a critical concern.
Stars
21
Forks
1
Language
Python
License
—
Category
Last pushed
Feb 28, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Y-Research-SBU/CSR"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
jncraton/languagemodels
Explore large language models in 512MB of RAM
microsoft/unilm
Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities
haizelabs/verdict
Inference-time scaling for LLMs-as-a-judge.
albertan017/LLM4Decompile
Reverse Engineering: Decompiling Binary Code with Large Language Models
bytedance/Sa2VA
Official Repo For Pixel-LLM Codebase