Seongtae Hong

hongst's activity

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

upvoted a paper about 6 hours ago

Beyond Hard Negatives: The Importance of Score Distribution in Knowledge Distillation for Dense Retrieval

Paper • 2604.04734 • Published 3 days ago • 2

upvoted a paper about 9 hours ago

Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

Paper • 2604.05684 • Published 2 days ago • 2

submitted a paper to Daily Papers about 9 hours ago

Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

Paper • 2604.05684 • Published 2 days ago • 2

authored a paper about 19 hours ago

Improving Semantic Proximity in Information Retrieval through Cross-Lingual Alignment

Paper • 2604.05684 • Published 2 days ago • 2

liked a dataset 21 days ago

Shitao/MLDR

Updated Feb 6, 2024 • 1.75k • 77

upvoted a collection about 2 months ago

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 a paper about 2 months ago

Diffusion-Pretrained Dense and Contextual Embeddings

Paper • 2602.11151 • Published Feb 11 • 23

liked 2 datasets about 2 months ago

nomic-ai/nomic-embed-unsupervised-data

Viewer • Updated Jan 24, 2025 • 239M • 1.6k • 17

uonlp/CulturaX

Viewer • Updated Dec 16, 2024 • 7.18B • 17.2k • 607

liked 2 datasets 2 months ago

jinaai/parallel-sentences

Viewer • Updated Oct 8, 2024 • 1k • 25 • 3

rlhn/rlhn-400K

Viewer • Updated May 27, 2025 • 390k • 49 • 2

liked 2 models 3 months ago

google/metricx-24-hybrid-xxl-v2p6

Updated Dec 12, 2024 • 716 • 16

LGAI-EXAONE/K-EXAONE-236B-A23B

Text Generation • 237B • Updated Feb 24 • 24.2k • 555

upvoted an article 3 months ago

view article

Article

Nano-BEIR: A Multilingual Information Retrieval Benchmark with Quality-Enhanced Queries

• 

Dec 22, 2025

•

9

upvoted a collection 4 months ago

🦢SWIM-IR Dataset [NAACL'24]

Collection

29 million Synthetic Wikipedia-based Multilingual Retrieval Training Pairs. • 4 items • Updated Mar 31, 2025 • 8

liked 2 datasets 4 months ago

Helsinki-NLP/un_pc

Viewer • Updated Apr 3, 2024 • 323M • 4.12k • 26

cfli/bge-e5data

Updated Sep 29, 2024 • 2.93k • 17

updated a model 5 months ago

hongst/test-tokenizer3

Updated Nov 3, 2025

published a model 5 months ago

hongst/test-tokenizer3

Updated Nov 3, 2025

updated a model 5 months ago

hongst/test-tokenizer2

Updated Nov 2, 2025