132 29 25

Wenhu Chen

wenhu

https://wenhuchen.github.io

AI & ML interests

NLP

Recent Activity

updated a dataset about 3 hours ago

TIGER-Lab/VisualWebInstruct

updated a model about 15 hours ago

TIGER-Lab/MAmmoTH-VL2

upvoted a paper about 16 hours ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

View all activity

Organizations

wenhu's activity

updated a dataset about 3 hours ago

TIGER-Lab/VisualWebInstruct

Viewer • Updated about 3 hours ago • 1.91M • 13 • 3

updated a model about 15 hours ago

TIGER-Lab/MAmmoTH-VL2

Question Answering • Updated about 15 hours ago • 14

upvoted a paper about 16 hours ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Paper • 2503.10582 • Published 1 day ago • 10

commented a paper about 16 hours ago

VisualWebInstruct: Scaling up Multimodal Instruction Data through Web Search

Paper • 2503.10582 • Published 1 day ago • 10 •

updated 2 datasets about 17 hours ago

TIGER-Lab/VisualWebInstruct-Seed

Viewer • Updated about 17 hours ago • 60.3k • 459 • 16

TIGER-Lab/VisualWebInstruct-Recall

Viewer • Updated about 17 hours ago • 361k • 69 • 2

authored a paper 2 days ago

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Paper • 2503.08638 • Published 3 days ago • 55

updated a dataset 3 days ago

TIGER-Lab/mmlu_pro_leaderboard_submission

Viewer • Updated 2 days ago • 166 • 315

updated a dataset 4 days ago

wenhu/Talk

Updated 4 days ago • 133

liked a dataset 6 days ago

TIGER-Lab/MEGA-Bench

Viewer • Updated Nov 20, 2024 • 12.6k • 1.05k • 20

updated a collection 7 days ago

VLM2Vec

Collection

The VLM2Vec embedding models. • 7 items • Updated about 12 hours ago • 4

authored a paper 8 days ago

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Paper • 2503.00329 • Published 14 days ago • 18

upvoted a paper 9 days ago

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Paper • 2503.00329 • Published 14 days ago • 18

updated a collection 9 days ago

ABC

Collection

A collection of models and datasets from ABC: Achieving Better Control of Multimodal Embeddings using VLMs. • 5 items • Updated 9 days ago • 1

commented a paper 9 days ago

ABC: Achieving Better Control of Multimodal Embeddings using VLMs

Paper • 2503.00329 • Published 14 days ago • 18 •

updated 2 datasets 9 days ago

TIGER-Lab/ABC-Pretraining-Data

Viewer • Updated 3 days ago • 2.25M • 943

TIGER-Lab/ABC-VG-Instruct

Viewer • Updated 3 days ago • 12.5k • 239

updated 2 models 9 days ago

TIGER-Lab/ABC-Qwen2VL-Instruct

Image-Text-to-Text • Updated 3 days ago • 57

TIGER-Lab/ABC-Qwen2VL-Pretrain

Image-Text-to-Text • Updated 3 days ago • 62

New activity in TIGER-Lab/VLM2Vec-Qwen2VL-7B 10 days ago

Adding `safetensors` variant of this model

#1 opened 14 days ago by

SFconvertbot