Xinping Zhao

Yuki131's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

Paper • 2603.13398 • Published 23 days ago • 152

upvoted a paper 10 days ago

OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory Synthesis

Paper • 2603.20278 • Published 16 days ago • 91

upvoted a paper 13 days ago

F2LLM-v2: Inclusive, Performant, and Efficient Embeddings for a Multilingual World

Paper • 2603.19223 • Published 14 days ago • 30

upvoted a paper 15 days ago

Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking

Paper • 2510.14824 • Published Oct 16, 2025 • 2

upvoted a collection 16 days ago

Encoders vs Decoders: the Ettin Suite

Collection

A collection of SOTA, open-data, paired encoder-only and decoder only models ranging from 17M params to 1B. See the paper at https://arxiv.org/abs/250 • 30 items • Updated Mar 2 • 28

upvoted a paper 17 days ago

Scaling Language-Centric Omnimodal Representation Learning

Paper • 2510.11693 • Published Oct 13, 2025 • 107

upvoted a paper 18 days ago

MM-CondChain: A Programmatically Verified Benchmark for Visually Grounded Deep Compositional Reasoning

Paper • 2603.12266 • Published 21 days ago • 19

upvoted 2 collections 18 days ago

Lychee-KaLM-LMEB

Collection

2 items • Updated 18 days ago • 1

🔥Hot Benchmarks

Collection

13 items • Updated 14 days ago • 2

upvoted a paper 18 days ago

LMEB: Long-horizon Memory Embedding Benchmark

Paper • 2603.12572 • Published 21 days ago • 73

upvoted 2 collections about 1 month ago

The Big Benchmarks Collection

Collection

Gathering benchmark spaces on the hub (beyond the Open LLM Leaderboard) • 13 items • Updated Nov 18, 2024 • 264

jina-embeddings-v5-text

Collection

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 paper 2 months ago

On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey

Paper • 2507.20783 • Published Jul 28, 2025 • 1

upvoted a collection 2 months ago

Tool-Retrieval

Collection

The first large-scale and diverse tool retrieval benchmark. See our homepage for more details: https://github.com/mangopy/tool-retrieval-benchmark. • 8 items • Updated Jun 26, 2025 • 3

upvoted 3 collections 3 months ago

Qwen3-VL-Reranker

Collection

2 items • Updated Jan 8 • 41

Qwen3-VL-Embedding

Collection

2 items • Updated Jan 8 • 64

ConTEB evaluation datasets

Collection

Evaluation datasets of the ConTEB benchmark. Use "test" split where available, otherwise "validation", otherwise "train". • 8 items • Updated Jun 2, 2025 • 3

upvoted 2 collections 4 months ago

jina-vlm

Collection

Jina-VLM: Small Multilingual Vision Language Model • 3 items • Updated Dec 15, 2025 • 9

Nemotron RAG

Collection

Set of tools to build retrieval-augmented generation (RAG) systems, improve search and ranking accuracy, and extract structured data from complex docs • 9 items • Updated 2 days ago • 84

upvoted a paper 5 months ago

Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data

Paper • 2511.12609 • Published Nov 16, 2025 • 106