dinhanhx's picture

dinhanhx

dinhanhx

·

dinhanhx

AI & ML interests

Vision Language

Recent Activity

upvoted a collection 5 days ago

jina-embeddings-v5-text

upvoted a collection 16 days ago

NVIDIA Nemotron v3

upvoted an article about 2 months ago

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

View all activity

Organizations

upvoted a collection 5 days ago

jina-embeddings-v5-text

Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated Feb 27 • 38

upvoted a collection 16 days ago

NVIDIA Nemotron v3

Open, Production-ready Enterprise Models • 15 items • Updated 1 day ago • 255

upvoted an article about 2 months ago

Article

ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases

Nov 5, 2025

•

63

liked a model about 2 months ago

jinaai/jina-reranker-v2-base-multilingual

Text Ranking • 0.3B • Updated Oct 21, 2025 • 907k • 347

liked a model 2 months ago

hantian/layoutreader

Token Classification • 0.4B • Updated Jun 8, 2025 • 232k • • 42

upvoted a collection 2 months ago

Contextual AI Reranker v2

Family of instruction-following multilingual rerankers on the cost/performance Pareto frontier across public and customer benchmarks • 6 items • Updated Aug 25, 2025 • 10

upvoted a paper 2 months ago

LiLT: A Simple yet Effective Language-Independent Layout Transformer for Structured Document Understanding

Paper • 2202.13669 • Published Feb 28, 2022 • 3

liked a model 2 months ago

nvidia/nemotron-ocr-v1

Image-to-Text • Updated about 10 hours ago • 272 • 117

liked a model 3 months ago

pytorch/gemma-3-12b-it-FP8

Image-Text-to-Text • Updated Oct 16, 2025 • 3.24k • 1

liked a dataset 3 months ago

52100303-TranPhuocSang/hoidap-tvpl-500k

Viewer • Updated Feb 3, 2025 • 502k • 4 • 1

upvoted an article 3 months ago

Article

How We Built a Semantic Highlight Model To Save Token Cost for RAG

Jan 15

•

65

liked a dataset 3 months ago

GreenNode/TVPL-Retrieval-VN

Viewer • Updated Jan 8 • 42.9k • 47 • 1

liked a model 3 months ago

Qwen/Qwen3-VL-Embedding-2B

Feature Extraction • 2B • Updated Jan 19 • 1.2M • • 362

liked a dataset 3 months ago

YuITC/Vietnamese-Legal-Documents

Viewer • Updated 15 days ago • 119k • 114 • 3

upvoted a paper 3 months ago

NV-Retriever: Improving text embedding models with effective hard-negative mining

Paper • 2407.15831 • Published Jul 22, 2024 • 4

upvoted a collection 4 months ago

Pixio

5 items • Updated Dec 19, 2025 • 13

liked a model 4 months ago

nvidia/llama-nemotron-rerank-1b-v2

Text Ranking • 1B • Updated 22 days ago • 77.8k • 42

New activity in frgfm/torch-cam 4 months ago

Issue loading images

#2 opened 4 months ago by

updated a Space 4 months ago

TorchCAM

Class activation maps for your PyTorch models (CAM, Grad-CAM

liked a Space 4 months ago

TorchCAM

Class activation maps for your PyTorch models (CAM, Grad-CAM