Haonan Chen

Haon-Chen's activity

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

upvoted a paper 2 days ago

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Paper • 2608.02583 • Published 3 days ago • 46

New activity in Haon-Chen/e5-omni-3B 3 months ago

Avoid trust_remote_code with transformers v5.6.0

#3 opened 3 months ago by

tomaarsen

New activity in Haon-Chen/e5-omni-7B 3 months ago

Avoid trust_remote_code with transformers v5.6.0

#2 opened 3 months ago by

tomaarsen

New activity in Haon-Chen/e5-omni-7B 4 months ago

Integrate with Sentence Transformers v5.4

#1 opened 4 months ago by

tomaarsen

New activity in Haon-Chen/e5-omni-3B 4 months ago

Integrate with Sentence Transformers v5.4

#2 opened 4 months ago by

tomaarsen

upvoted a paper 6 months ago

DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories

Paper • 2602.10809 • Published Feb 11 • 59

New activity in AdaTooler-V/AdaTooler-V-train-data 7 months ago

Upload json file

#21 opened 7 months ago by

Haon-Chen

upvoted a paper 7 months ago

e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings

Paper • 2601.03666 • Published Jan 7 • 5

updated a collection 7 months ago

e5-omni

Collection

A lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. https://arxiv.org/abs/2601.03666 • 3 items • Updated Jan 13

submitted a paper to Daily Papers 7 months ago

e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings

Paper • 2601.03666 • Published Jan 7 • 5

authored a paper 7 months ago

e5-omni: Explicit Cross-modal Alignment for Omni-modal Embeddings

Paper • 2601.03666 • Published Jan 7 • 5

updated 2 models 7 months ago

Haon-Chen/e5-omni-7B

Visual Document Retrieval • 9B • Updated Apr 24 • 42k • 9

Haon-Chen/e5-omni-3B

Visual Document Retrieval • 5B • Updated Apr 24 • 453 • 6

New activity in TIGER-Lab/MMEB-Leaderboard 7 months ago

Upload 2 files

#98 opened 7 months ago by

Haon-Chen

updated a collection 7 months ago

e5-omni

Collection

A lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. https://arxiv.org/abs/2601.03666 • 3 items • Updated Jan 13

New activity in Haon-Chen/e5-omni-3B 7 months ago

Multi-image / interleaved document embeddings?

1

#1 opened 7 months ago by

vishaal27

updated a collection 7 months ago

e5-omni

Collection

A lightweight explicit alignment recipe that adapts off-the-shelf VLMs into robust omni-modal embedding models. https://arxiv.org/abs/2601.03666 • 3 items • Updated Jan 13

published 2 models 7 months ago

Haon-Chen/e5-omni-3B

Visual Document Retrieval • 5B • Updated Apr 24 • 453 • 6

Haon-Chen/e5-omni-7B

Visual Document Retrieval • 9B • Updated Apr 24 • 42k • 9