내가 좋아할 만한 콘텐츠
Lecture slides for my "Introduction to #ComputerVision" and "#DeepLearning in Computer Vision" courses. 🆕 Gaussian Splatting 🆕 Flow Matching The included videos do not contain voiceovers yet, planned for a future revision.
Last day of class of my brand-new course Physical Intelligence (lnkd.in/d9BMFG5d) at #UPenn. We concluded with a drone racing competition in the real world! I am really proud of all the students; I have no doubt that they will do great in the future!
it’s more like CES than any conference I’ve ever attended
The leaderboard Illusion is presented at #NeurIPS2025 today! Come learn why leaderboards mislead — and how we can fix them.
1/ Science is only as strong as the benchmarks it relies on. So how fair—and scientifically rigorous—is today’s most widely used evaluation benchmark? We took a deep dive into Chatbot Arena to find out. 🧵
Impromptu NeurIPS meetup: "representational convergence by the beach." We will meet at ballroom 20c (near lunch) 2pm Fri and walk over to Marina. Will chat about platonic reps, fractured reps, or anything else about where all these models are heading. Anyone is welcome to join!
DARPA Challenge in 2015; Looking back, the field has come a long way.
Reality of robotics: humanoid kung fu is solved before they can open doors with RGB. Here we are. Introducing the frontier of sim2real at NVIDIA GEAR. 100% sim data. RGB input only. Code name: 𝗗𝗼𝗼𝗿𝗠𝗮𝗻. We are opening the sim-to-real door. doorman-humanoid.github.io 🧵
Hu, Cheng, Yu et al., "VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction" Easi3r-style attention analysis and masking with mask refinement with VGGT. Also discards tokens related to dynamic points.
I now run Meta's interpretability community-- 150+ researchers across FAIR, GenAI, & Reality Labs. Building our 2026 interp speaker series (w/ sessions on video models, world models, & causal discovery). At NeurIPS this week. If you're working on these areas, let's talk.
Lecture slides for my "Introduction to #ComputerVision" and "#DeepLearning in Computer Vision" courses. 🆕 Gaussian Splatting 🆕 Flow Matching The included videos do not contain voiceovers yet, planned for a future revision.
A NeurIPS/ICML tradition older than ChatGPT: the diffusion circle! Join us on the bayside terrace outside room 11 tomorrow (Friday) at 3:30PM in San Diego to talk about diffusion until the sun sets 🌄! The more the merrier, tell/tag your friends!
📢 Another #NeurIPS, another diffusion circle! Join us to talk about diffusion models on Friday Dec 5 at 3:30PM in San Diego! Bayside terrace outside room 11 (upstairs) ☀️🚢🌊 Please help spread the word, tell your friends! No slides, no talks, we just sit down and chat 🗣️
📢I'm at #NeurIPS2025 this week. What to chat? 😀 🔸Today: I'll be at the NVIDIA booth from 3-4:15pm - drop by! 🔸Today: I'll present "Align Your Flow" at 4:30pm in Poster Session 4. Poster #4406. 🔸Friday: GenAIR team meetup at 1pm-3pm ( x.com/ArashVahdat/st…). (continued)
🔥 Want to meet the GenAIR team at #NeurIPS2025? Join me, @karsten_kreis & @MardaniMorteza for a casual meetup this Friday (Dec 5), 1–3 PM at the Omni Hotel, right across from the convention center. 📍 Omni Hotel Skybox, 19th floor 675 L St, San Diego, CA
Yes I remember this from 10 years ago. My answers were not that great because I didn't get any sleep from the excitement. But it's interesting there was a question about scaling attention in a sub-linear way, which still is an important question and not fully answered.
The last thing you ever want to hear at the end of your talk
Ten years ago in 2015 we published a paper called End-to-End Memory Networks (arxiv.org/abs/1503.08895). Looking back, this paper had many of the ingredients of current LLMs. Our model was the first language model that completely replaced RNN with attention. It had dot-product…
Introducing the new fastest and most flexible view synthesis method: Radiance Meshes. RMs are volumetric triangle meshes that can be thrown into any game engine, rendered at ~200 FPS@1440p on a RTX4090, and edited using conventional tools. Here's a demo running on my desktop:
These are from 2024. What are some standout posters from 2025 Neurips/ICLR/ICML/ACL?
At NeurIPS? Come see our poster on learning a normalized energy model for photographic images - Friday 11am, poster 3700
What is the probability of an image? What do the highest and lowest probability images look like? Do natural images lie on a low-dimensional manifold? In a new preprint with @ZKadkhodaie @EeroSimoncelli, we develop a novel energy-based model in order to answer these questions: 🧵
🚨Google and UCSD just introduced Radiance Meshes, a new radiance field representation that produces watertight meshes and renders faster than 3DGS. Code and demos are available now. Code: github.com/half-potato/ra… Demos: half-potato.gitlab.io/rm/#demos
United States 트렌드
- 1. Cloudflare 32.4K posts
- 2. Cowboys 74.2K posts
- 3. #heatedrivalry 30.7K posts
- 4. Happy Farmers 2,104 posts
- 5. LeBron 115K posts
- 6. Warner Bros 34.2K posts
- 7. Wizkid 182K posts
- 8. Pickens 15.3K posts
- 9. Lions 93.8K posts
- 10. fnaf 2 28.1K posts
- 11. rUSD N/A
- 12. Jake Tapper 44.8K posts
- 13. Shang Tsung 36.5K posts
- 14. Paramount 22.2K posts
- 15. Gibbs 21.2K posts
- 16. #PowerForce N/A
- 17. scott hunter 6,997 posts
- 18. Davido 101K posts
- 19. Hiroyuki Tagawa 32.3K posts
- 20. The Gong Show N/A
내가 좋아할 만한 콘텐츠
-
Michael Black
@Michael_J_Black -
Matthias Niessner
@MattNiessner -
Jürgen Schmidhuber
@SchmidhuberAI -
Peyman Milanfar
@docmilanfar -
Soumith Chintala
@soumithchintala -
Yi Ma
@YiMaTweets -
Aran Komatsuzaki
@arankomatsuzaki -
Jia-Bin Huang
@jbhuang0604 -
AK
@_akhaliq -
Lucas Beyer (bl16)
@giffmana -
#CVPR2026
@CVPR -
Vincent Sitzmann
@vincesitzmann -
Percy Liang
@percyliang -
Alfredo Canziani @ NeurIPS
@alfcnz -
Angjoo Kanazawa
@akanazawa
Something went wrong.
Something went wrong.