Talk is done!

Shared our work on Multimodal AI Agents at the #ICCV2025 Workshop on Multi-Modal Reasoning. 🤖

All the slides, key papers, and the research journey are consolidated in this new blog post:

📄https://www.niebles.net/blog/2025/mmagents/

@iccv.bsky.social

Congrats Chaitanya on winning the BEST PAPER AWARD 🥇 🏆

Check out details of our work:

arxiv.org/abs/2504.12513

Our first #cvpr2025 poster is up!

🕐Come check it out right now until 13:00

“AdaVid: Adaptive Video-Language Pretraining”

🪧ExHall D Poster # 203

📝 arxiv.org/abs/2504.12513

Just finished a day at the #CVPR2025 Area Chair workshop. Lots of interesting discussions and ideas, reconnection with colleagues and friends.

Had the chance to present our ViUnit poster to fellow ACs. If you missed it, come to our Sunday poster session.

See details in the 🧵⬇️

Just dropped a new blog post: "Level up your Agents: Teaching Vision-Language Models to Play by the Rules"! We're exploring how to make Vision-Language Models (VLMs) even smarter at interactive tasks.

blog: www.niebles.net/blog/2025/vl...

arxiv: arxiv.org/abs/2505.03181
#multimodalAI #agents #VLM

New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔

Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!

📰 Blog: www.niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859

Work by Artemis P & Honglu Z

New blog post: "Are your Visual Programs Right for the Wrong Reasons?" 🤔

Dive into the motivation behind our @cvprconference.bsky.social #CVPR2025 paper!

📰 Blog: niebles.net/blog/2025/vi...
➡️ Project: artemisp.github.io/viunit/
📄 Paper: arxiv.org/abs/2412.08859

Work by Artemis P & Honglu Z

Workshop days are always the most engaging and rewarding. Here are my two picks for this weekend:

Saturday
Video-language
video-and-language-workshop-2024.webflow.io

Sunday
Multimodal algorithmic reasoning
marworkshop.github.io/neurips24/

Do you have other recommendations?
#NeurIPS #NeurIPS2024

It’s on! Join us
#NeurIPS2024 #NeurIPS

📍 West Ballroom A-D #5106
🗓 4:30 p.m.

📄Arxiv: arxiv.org/abs/2412.03567
💭Blog: www.niebles.net/blog/2024/sdqes/
🌎Website: sdqesdataset.github.io

Join us at our API-Gen poster!
#NeurIPS2024 #NeurIPS

📍West Ballroom A-D #5307
📝 arxiv.org/abs/2406.18518
🌎 apigen-pipeline.github.io

To learn more, please visit our #NeurIPS2024 poster in Vancouver

📍 West Ballroom A-D #5106
🗓Fri 13 Dec 4:30 p.m.

In the meantime, check out the following resources:

📄Arxiv: arxiv.org/abs/2412.03567
💭Blog: www.niebles.net/blog/2024/sdqes/
🌎Website: sdqesdataset.github.io

We found that existing methods struggle to solve this problem. We make the benchmark available to everyone and hope to see some interesting improvements soon.

We also studied the performance of various streaming architectures, including several adapter layers to aggregate temporal information.

For the dataset, we leverage Ego4D videos and annotations, and augment them with an automated pipeline to generate data samples for our task.

For this to work, the smart glass starts capturing video only after receiving a user prompt and it would process the video on-device in a streaming fashion, looking to detect the start of the event indicated by the user.

Our paper introduces a benchmark to study this task.

🤖 “Hey assistant, don't let me forget my card at the ATM!”

🕶 Are you as forgetful as I am? Imagine you could ask your smart glasses to give you a reminder the next time a certain event happens… wouldn’t that be amazing?

As countries across the globe have increasingly prioritized AI, year-over-year rankings in AI leadership have changed.

The tool ranks 36 countries using 42 AI-specific indicators. It is among the most comprehensive indices of its kind. A key finding: the U.S. currently leads in AI, followed by China in a distant second and the United Kingdom in third.