David Chan's picture

5 4 2

David Chan

davidchan

·

https://dchan.cc

DavidMChan

AI & ML interests

Vision + Language

Recent Activity

upvoted a paper 2 months ago

Analyzing The Language of Visual Tokens

commented a paper 2 months ago

Analyzing The Language of Visual Tokens

new activity 3 months ago

davidchan/anim400k:The archives are broken

View all activity

Articles

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

Organizations

davidchan's activity

upvoted a paper 2 months ago

Analyzing The Language of Visual Tokens

Paper • 2411.05001 • Published Nov 7, 2024 • 23

commented a paper 2 months ago

Analyzing The Language of Visual Tokens

Paper • 2411.05001 • Published Nov 7, 2024 • 23 •

New activity in davidchan/anim400k 3 months ago

The archives are broken

#2 opened 3 months ago by

lemuriandezapada

upvoted a paper 4 months ago

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

Paper • 2409.12962 • Published Sep 19, 2024 • 2

commented a paper 4 months ago

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

Paper • 2409.12962 • Published Sep 19, 2024 • 2 •

New activity in davidchan/anim400k 5 months ago

Dataset Viewer issue

#1 opened 7 months ago by

commented a paper 6 months ago

Visual Haystacks: Answering Harder Questions About Sets of Images

Paper • 2407.13766 • Published Jul 18, 2024 • 2 •

authored 4 papers 6 months ago

Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition

Paper • 2403.19822 • Published Mar 28, 2024

ALOHa: A New Measure for Hallucination in Captioning Models

Paper • 2404.02904 • Published Apr 3, 2024

Virtual Personas for Language Models via an Anthology of Backstories

Paper • 2407.06576 • Published Jul 9, 2024

Visual Haystacks: Answering Harder Questions About Sets of Images

Paper • 2407.13766 • Published Jul 18, 2024 • 2

posted an update 6 months ago

Post

548

🚨 Launching The Visual Haystacks (VHs) Benchmark: the first "visual-centric" Needle-In-A-Haystack (NIAH) benchmark to assess LMMs' capability in long-context visual retrieval and reasoning.

Check it out!
tsunghanwu/visual_haystacks
https://visual-haystacks.github.io/
https://arxiv.org/abs/2407.13766
https://github.com/visual-haystacks/vhs_benchmark

commented a paper 6 months ago

Visual Haystacks: Answering Harder Questions About Sets of Images

Paper • 2407.13766 • Published Jul 18, 2024 • 2 •

upvoted an article 6 months ago

Article

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

By

•

Jul 23, 2024

• 3

published an article 6 months ago

Article

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

By

•

Jul 23, 2024

• 3

liked a dataset 6 months ago

tsunghanwu/visual_haystacks

Viewer • Updated Oct 16, 2024 • 20.1k • 51 • 8

updated a dataset 7 months ago

davidchan/anim400k

Updated Jun 21, 2024 • 240 • 33

liked a dataset 12 months ago

davidchan/anim400k

Updated Jun 21, 2024 • 240 • 33

authored 2 papers 12 months ago

Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition

Paper • 2401.02417 • Published Jan 4, 2024 • 1

Multimodal Attention Merging for Improved Speech Recognition and Audio Event Classification

Paper • 2312.14378 • Published Dec 22, 2023