🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

This should be of interest to folks working on sfm / (point) tracking. You can literally get point trajectories “for free” with your recorded data!

Juggling between CVPR AC workshop and Slovenia:Denmark EU cup game 😅

Best conference networking advice right here

⭐🚨 Tweeprint! 🚨⭐ Very excited to present my & Alana Darcher (she/her)’s PhD research! What happens in your brain when you watch a movie? How is the information underlying the movie’s content distributed across neurons? biorxiv.org/content/10.110…

If you’re at #CVPR2024 #CVPR tomorrow (Tuesday) I will be giving a talk on Dynamic 3D Gaussians + SplaTAM (see 👇) as part of the XRNeRF workshop (sites.google.com/view/xrnerf/). Talk is at 9.30am in room Summit 332. The other talks at the workshop also seem super cool! Def check it out

I'll be giving a lightning talk at the DDADS workshop (agents4ad.github.io) at #CVPR about the work that provided the basis for this tomorrow 9:45 am! Multi-Level Neural Scene Graphs for Dynamic Urban Environments - We'll also present on Friday at 10:30 am Poster Session 5.

Y’all need detectors for objects that can move but don’t want to label the data? Come by our poster today! #cvpr2024

Not the best photo, but fascinating work: your (unimodal) LLM already has visual representations “somewhere in there”. Talk to these folks to see how to get them out! #cvpr2024

Damn I wish i hadn’t missed this (having a whole day demo in parallel)

I once did that for a friend, and as soon as I put it on I had a group of folks around waiting for the presentation and I just tagged along 😅 by the time it was turn for my poster I already lost my voice!

Best CVPR so far! There sure were some organizational hiccups, but its not the organization that makes conferences great, its the people. Good night, Seattle!

This looks impressive!

Exactly my experience. Submitting less than half baked papers puts uneccessary strain on reviewers. We desperately need to do something about this. I was reviewing for neurips every year, wheter I submitted or not- I will change this policy.

Introducing fVDB, a deep learning framework for large-scale, high-performance spatial intelligence. ➡️ nvda.ws/3WIR59J Explore how fVDB builds AI operators on top of OpenVDB to enable reality-scale, AI-ready #digitaltwins. #SIGGRAPH2024

🚀 Introducing 𝐖𝐨𝐥𝐟 🐺: a mixture-of-experts video captioning framework that outperforms GPT-4V and Gemini-Pro-1.5 in general scenes 🖼️, autonomous driving 🚗, and robotics videos 🤖. 👑: wolfv0.github.io/leaderboard.ht…

#AI is a civilizational technology that will have profound implications to everyone. "AI policy must encourage innovation, set appropriate restrictions, and mitigate the implications of those restrictions. Policy that doesn't will at best fall short of its goals, and at worst

Zoe Lofgren's (ranking member Science, Space and Tech) letter to Senator Scott Wiener voicing deep concerns on SB 1047. "I’m very concerned about the effect this legislation could have on the innovation economy of California without any clear benefit for the public." Please amplify.

[📚 SlovenianGPT 🧠] Happy to announce that I'm open sourcing the best 7B LLM for the Slovenian language! (better than LLaMA3, Mistral, etc.) I hope that the Slovenian NLP community finds this one useful! HuggingFace: huggingface.co/gordicaleksa/S… SlovenianGPT is a base model and

Check out our work on fine-tuning of image-conditional diffusion models for depth and normal estimation. Widely used diffusion models can be improved with single-step inference and task-specific fine-tuning, allowing us to gain better accuracy while being 200x faster!⚡ 🧵(1/6)

Great work by my team at RWTH Computer Vision Group. Up to now, the prevailing perception was that diffusion models must be slow or complex for depth estimation. We show that this is not the case. With our training scheme, faster more efficient diffusion-based models are possible.