Patrick (Tsung-Han) Wu

tsunghanwu's activity

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

upvoted a paper 26 days ago

VisionArena: 230K Real World User-VLM Conversations with Preference Labels

Paper • 2412.08687 • Published 28 days ago • 13

updated a collection 3 months ago

Visual Haystacks

Collection

3 items • Updated Oct 18, 2024 • 1

updated a model 3 months ago

tsunghanwu/mirage-llama3.1-8.3B

Updated Oct 18, 2024 • 54 • 1

updated 3 datasets 3 months ago

tsunghanwu/MIRAGE-training-set

Updated Oct 17, 2024 • 41

tsunghanwu/visual_haystacks

Viewer • Updated Oct 16, 2024 • 20.1k • 57 • 8

tsunghanwu/visual_haystacks_v0

Viewer • Updated Oct 13, 2024 • 20.7k • 34

upvoted an article 3 months ago

view article

Article

Are We Ready for Multi-Image Reasoning? Launching VHs: The Visual Haystacks Benchmark!

By •

Jul 23, 2024

• 3

upvoted a paper 4 months ago

CLAIR-A: Leveraging Large Language Models to Judge Audio Captions

Paper • 2409.12962 • Published Sep 19, 2024 • 2

liked a dataset 6 months ago

tsunghanwu/visual_haystacks

Viewer • Updated Oct 16, 2024 • 20.1k • 57 • 8

updated a collection 6 months ago

SESAME

Collection

Official checkpoints of the paper -- See, Say, Segment: Teaching LMMs to Overcome False Premises (SESAME), CVPR 2024. • 2 items • Updated Jun 28, 2024 • 1

updated 2 models 7 months ago

tsunghanwu/SESAME_minus

Text Generation • Updated Jun 16, 2024 • 21

tsunghanwu/SESAME

Text Generation • Updated Jun 16, 2024 • 21 • 1

updated a collection 7 months ago

SESAME

Collection

Official checkpoints of the paper -- See, Say, Segment: Teaching LMMs to Overcome False Premises (SESAME), CVPR 2024. • 2 items • Updated Jun 28, 2024 • 1