Xin Zhang's picture

Xin Zhang

izhx

·

https://izhx.github.io/

AI & ML interests

NLP, IR, and Multimodal.

Recent Activity

new activity about 1 month ago

Alibaba-NLP/gme-Qwen2-VL-2B-Instruct:error with AutoModel GmeQwen2VLConfig after upgrade

new activity about 1 month ago

Alibaba-NLP/gme-Qwen2-VL-7B-Instruct:Fix remote code

new activity about 1 month ago

Alibaba-NLP/gme-Qwen2-VL-2B-Instruct:Fix mdoel loading

View all activity

Organizations

upvoted a paper about 2 months ago

Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Paper • 2506.05176 • Published Jun 5 • 65

upvoted 2 collections about 2 months ago

Qwen3-Reranker

3 items • Updated about 19 hours ago • 60

Qwen3-Embedding

6 items • Updated about 19 hours ago • 106

upvoted a collection 3 months ago

MTEB Papers

This is a collection of MTEB papers (not exhaustive). • 7 items • Updated Apr 16 • 2

upvoted a paper 3 months ago

MIEB: Massive Image Embedding Benchmark

Paper • 2504.10471 • Published Apr 14 • 18

upvoted a paper 5 months ago

GME: Improving Universal Multimodal Retrieval by Multimodal LLMs

Paper • 2412.16855 • Published Dec 22, 2024 • 5

upvoted a collection 7 months ago

GME Models

General Multimodal Embedding Models Released by Tongyi Lab of Alibaba Group • 3 items • Updated Dec 24, 2024 • 7

upvoted an article 9 months ago

Article

Model2Vec: Distill a Small Fast Model from any Sentence Transformer

By

and 1 other •

Oct 14, 2024

• 95

upvoted an article 11 months ago

Article

Improving Hugging Face Training Efficiency Through Packing with Flash Attention

By

and 5 others •

Aug 21, 2024

• 37

upvoted a paper 12 months ago

mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval

Paper • 2407.19669 • Published Jul 29, 2024 • 25

upvoted 3 collections about 1 year ago

GTE models

General Text Embedding Models Released by Tongyi Lab of Alibaba Group • 21 items • Updated Jan 21 • 30

Qwen2

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated about 19 hours ago • 368

Nomic Embed Vision

Vision Encoders aligned to Nomic Embed Text making Nomic Embed multimodal! • 2 items • Updated Jun 5, 2024 • 9