Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
1
1
53
BingHan
BrightXiaoHan
Follow
eliasalbouzidi's profile picture
1 follower
·
11 following
BrightXiaoHan
AI & ML interests
Machine Translation
Recent Activity
updated
a model
7 days ago
BrightXiaoHan/iflytech_heqc_cls
liked
a model
22 days ago
jinaai/reader-lm-1.5b
reacted
to
singhsidhukuldeep
's
post
with 🔥
22 days ago
Exciting breakthrough in large-scale recommendation systems! ByteDance researchers have developed a novel real-time indexing method called "Streaming Vector Quantization" (Streaming VQ) that revolutionizes how recommendations work at scale. >> Key Innovations Real-time Indexing: Unlike traditional methods that require periodic reconstruction of indexes, Streaming VQ attaches items to clusters in real time, enabling immediate capture of emerging trends and user interests. Superior Balance: The system achieves remarkable index balancing through innovative techniques like merge-sort modification and popularity-aware cluster assignment, ensuring all clusters participate effectively in recommendations. Implementation Efficiency: Built on VQ-VAE architecture, Streaming VQ features a lightweight and clear framework that makes it highly implementation-friendly for large-scale deployments. >> Technical Deep Dive The system operates in two key stages: - An indexing step using a two-tower architecture for real-time item-cluster assignment - A ranking step that employs sophisticated attention mechanisms and deep neural networks for precise recommendations. >> Real-world Impact Already deployed in Douyin and Douyin Lite, replacing all major retrievers and delivering significant user engagement improvements. The system handles a billion-scale corpus while maintaining exceptional performance and computational efficiency. This represents a significant leap forward in recommendation system architecture, especially for platforms dealing with dynamic, rapidly-evolving content. The ByteDance team's work demonstrates how rethinking fundamental indexing approaches can lead to substantial real-world improvements.
View all activity
Organizations
BrightXiaoHan
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
Articles
liked
a model
22 days ago
jinaai/reader-lm-1.5b
Text Generation
•
Updated
26 days ago
•
3.27k
•
586
liked
a dataset
25 days ago
Zyphra/Zyda-2
Viewer
•
Updated
Dec 12, 2024
•
1.62B
•
169k
•
71
liked
a model
27 days ago
MiniMaxAI/MiniMax-Text-01
Text Generation
•
Updated
26 days ago
•
6.8k
•
513
liked
a model
about 2 months ago
TencentBAC/Conan-embedding-v1
Updated
Nov 27, 2024
•
35.2k
•
139
liked
3 models
5 months ago
stepfun-ai/GOT-OCR2_0
Image-Text-to-Text
•
Updated
8 days ago
•
373k
•
1.37k
jinaai/reader-lm-0.5b
Text Generation
•
Updated
Jan 6
•
481
•
135
mattshumer/Reflection-Llama-3.1-70B
Text Generation
•
Updated
Sep 24, 2024
•
567
•
1.71k
liked
a dataset
10 months ago
HuggingFaceFW/fineweb
Viewer
•
Updated
12 days ago
•
25B
•
492k
•
1.92k
liked
a model
10 months ago
apple/OpenELM
Updated
May 2, 2024
•
1.43k
liked
2 models
12 months ago
google/gemma-2b
Text Generation
•
Updated
Sep 27, 2024
•
269k
•
966
google/gemma-7b
Text Generation
•
Updated
Jun 27, 2024
•
66.2k
•
•
3.12k
liked
a dataset
12 months ago
CohereForAI/aya_dataset
Viewer
•
Updated
Jun 28, 2024
•
206k
•
2.66k
•
293
liked
3 models
12 months ago
nghuyong/ernie-3.0-base-zh
Fill-Mask
•
Updated
Sep 10, 2022
•
11.5k
•
93
CohereForAI/aya-101
Text2Text Generation
•
Updated
Mar 31, 2024
•
3.62k
•
630
BAAI/bge-m3
Sentence Similarity
•
Updated
Jul 3, 2024
•
2.05M
•
1.7k
liked
5 models
about 1 year ago
IDEA-CCNL/Randeng-T5-784M-MultiTask-Chinese
Text2Text Generation
•
Updated
May 25, 2023
•
83
•
70
transformer3/H1-keywordextractor
Summarization
•
Updated
Apr 21, 2023
•
156
•
14
intfloat/e5-mistral-7b-instruct
Feature Extraction
•
Updated
Apr 23, 2024
•
190k
•
486
InstantX/InstantID
Text-to-Image
•
Updated
Jan 22, 2024
•
68.4k
•
766
pyannote/speaker-diarization-3.1
Automatic Speech Recognition
•
Updated
May 10, 2024
•
10.9M
•
681
Load more