🔥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

Introducing Sora, our text-to-video model. Sora can create videos of up to 60 seconds featuring highly detailed scenes, complex camera motion, and multiple characters with vibrant emotions. openai.com/sora Prompt: “Beautiful, snowy

🚀 Fresh from #HotMobile2024 & excited! Our recent work tackles depth estimation in Mobile AR, highlighting challenges, proposing possible solutions, & reviewing recent works. 🔍 Curious? Check our paper: [rb.gy/lr9r0a]. Stay tuned for more! #DepthEstimation #AR.

👇👇👇check out the challenges of metric depth for mobile #AR and some ideas of how to make it better! Great efforts by Ashkan to lead this project and Yiqin Zhao | 赵一勤 This Cake Lab (WPI) paper is in collaboration with Hang Su NVIDIA research.

We've open-sourced our work on depth estimation in Mobile AR! 🎉 Check out our comprehensive codebase for training, evaluation, and analysis here: [github.com/cake-lab/Mobil…]. Feel free to share your thoughts with us! #DepthEstimation #AR

At this time of year, I remember getting ready for school—buying new things with my family, the smell of fresh paper, and that simple excitement I had. I miss those times tonight.

It seems that the new ChatGPT can reason very well. Not sure whether to feel happy or sad about it.

I saw some people didn’t believe my previous post.

With the ICLR deadline coming up, a few people asked me for tips on cutting down papers to fit the page limit. Figured it might help others too, so here are my tips, which I apply by the order they are written >>>

Managed to spend some time updating my personal website! Now I'm thinking about sticking with Bootstrap or making the switch to Tailwind CSS 🤔 ashkanganj.me

I guess we need a lot of things

The new Joker movie is a complete waste of time. Don’t bother.

Looks like the sun decided to take a seat on the clouds today!

Introducing MASt3R-SLAM, the first real-time monocular dense SLAM with MASt3R as a foundation. Easy to use like DUSt3R/MASt3R, from an uncalibrated RGB video it recovers accurate, globally consistent poses & a dense map. With Eric Dexheimer*, Andrew Davison (*Equal Contribution)

Dear @google, why put my applications on a diet? Let me feast on these opportunities!

github.com/ading2210/linu… Running Linux on a PDF? Now that's crazy!

Please stop asking me about my dream job I would never dream about working!

Feels like LLMs have hit a wall when it comes to making truly meaningful improvements.