🚨 Paper submission alert for BMVC 2024! 📅 Mark your calendars — the final deadline is this Friday, 10 May 2024. Don't miss your chance to showcase your latest research in computer vision.🔍✨
#BMVC2024 #ComputerVision #PaperDeadline

The #CVPR2024 tentative program is now up! Includes the day/time for each poster presentation.

cvpr.thecvf.com/Conferences/20…

Accepted papers are not everything, but I am happy with how lucky our RAI Cluster of Excellence initiative is at #ICLR2024 . You rock! Please check out the posters and talks. hessian.AI TU Darmstadt

Ever wondered how to process distributions with neural networks? Our #ICLR2024 🎻 paper “Uncertainty Quantification via Stable Distribution Propagation” has the answer. SDP is a sampling-free method for efficiently propagating stable distributions through neural networks. A 🧵

✈️✈️✈️Heading to #ICLR2024 with OPTML @MSU ! Excited to present 3 papers:

1. SalUn: Salience-aware unlearning for safe generative modeling. [Project page: optml-group.com/posts/salun_ic…]

2. DeepZero: Scaling up zeroth-order optimization for deep model training. [Project page:…

Having explained how weaponized fear is the 'source code' of fascism--what short-circuits rational self-interest--this proposed solution (make truth prevail) misses the thread's own point.

Ppl scared crazy can't hear truth. They must 1st be calmed, reassured.FDR understood this.

Geo-Regional Asia at Cohere For AI will be having 8 Guest Speaker Sessions in May (Details in the thread).

Join our Open Science Community: share.hsforms.com/10OrjljwpQ52IL…

Are you a researcher in the field of photogrammetry 📷 and remote sensing 🌍? Then, we cordially invite you to submit a paper to our Ph & RS Special Track GCPR 2024. The deadline for submissions is May 29!

🔍Check out our #CVPR2024 challenge on understanding text-rich images (infographics, books, etc)! 📅Phase 1 submissions are due May 15th.

Details: sites.google.com/view/2nd-mmfm-… 🌟

MMFM Workshop

Llama-3 is closing the gap with GPT-4, but multimodal models gotta catch up. Vision capabilities of open models like LlaVA are far, far behind GPT-4V. Video models are even worse. They hallucinate all the time and fail to give detailed descriptions of complex scenes and actions.…

Our team NimbRo@Home participates at the #RoboCup German Open competition in Kassel. After the first competition day, NimbRo is leading with 1271 points, followed by ToBi (Bielefeld University, 445 points) and SCC.
github.com/RoboCupAtHome/…
ais.uni-bonn.de/nimbro/@Home

The story of modern AI

Will be there… 🔥

We have a cool challenge on understanding document images in our 2nd #CVPR2024 workshop on “What is Next in Multimodal Foundation Models?”, (sites.google.com/view/2nd-mmfm-…). This is a great opportunity to showcase your work in front of a large audience (pic below from our 1st workshop)

Short thread on the Atlantic Meridional Overturning Circulation #AMOC , which brings a huge amount of heat to the northern Atlantic.
If it slows, the region west of Britain cools. And the Gulf Stream moves closer to the US coast, causing warming there.
Both are already happening,…

I thought this was funny first… now I’m thinking about writing a thread about how research papers (which should first be out there to communicate new findings and to share knowledge with your community) being used as a pseudo metric for various performance measures where your…