[2304.08485] Visual Instruction Tuning
6
Public whispers
6
Contributors
2026-07-18 09:42:20
First whispered
Public whispers on this page
Text Highlight2026-07-18 16:06:20
Original Highlight Excerpt
"arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website."
Whisper Note
So basically anyone can just build stuff right on arXiv now, that's pretty cool.
Text Highlight2026-07-18 13:03:20
Original Highlight Excerpt
"NeurIPS 2023 Oral; project page: this https URL"
Whisper Note
I wonder if the project page has the actual code or just a demo.
Text Highlight2026-07-18 12:54:20
Original Highlight Excerpt
"NeurIPS 2023 Oral; project page: this https URL"
Whisper Note
Oral at NeurIPS, that's a big deal for this kind of work.
Text Highlight2026-07-18 10:00:20
Original Highlight Excerpt
"Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks"
Whisper Note
This might finally make vision models follow instructions like a champ.
Text Highlight2026-07-18 09:51:20
Original Highlight Excerpt
"Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks"
Whisper Note
I wonder if the 92% on Science QA actually generalizes or just memorizes.
Text Highlight2026-07-18 09:42:20
Original Highlight Excerpt
"Instruction tuning large language models (LLMs) using machine-generated instruction-following data has improved zero-shot capabilities on new tasks"
Whisper Note
Cool, so they just used GPT-4 to make fake data then trained on it, lol.
Share this page's whispers
Short link
https://domwhisper.com/s/837a7bfad5d9Embed snippet
<iframe src="https://domwhisper.com/embed/837a7bfad5d9" width="100%" height="480" style="border:0;border-radius:16px" loading="lazy"></iframe>See what people are discussing on arxiv.org
Install DomWhisper to view live whispers as you browse, and join the discussion.
Get the extension