Snippings of recorded talks
Last week’s #AI4Robotics workshop was fab & fabulously full 😊 If you missed out we've good news -
📽️ All 15 talk recordings are now online 🚀! tinyurl.com/4ns5apvd
Catch up on cutting-edge work in #robot perception, action & autonomy - from #SLAM & control to computer vision & large-scale learning!
The AMIAD research division organizes the AI and Robotics conference during ECW 2025 on 19 November in Rennes, France.
Two live demonstrations with the Spot and SummitXL robots and four presentations will be given on stage by outstanding researchers!
www.european-cyber-week.eu/en
Major announcement ✨registration is OPEN✨
AI for Robotics workshop (4th edition): Spatial AI
🗓️Nov 21-22 Grenoble, France!
Details: tinyurl.com/bdtk2nzs
⭐⭐ 14 confirmed speakers ⭐⭐: 🧵2/3
Poster submissions (travel grant possible): 🧵 3/3
Spread the word!
My Vision Transformer lecture snippet
cleanrl is amazing (github.com/vwxyzjn/clea...) and its structure makes sense for teaching but an actual research codebase should not inherit this style! you do not want this amount of code duplication
🚀 Never miss a beat in science again!
📬 Scholar Inbox is your personal assistant for staying up to date with your literature. It includes: visual summaries, collections, search and a conference planner.
Check out our white paper: arxiv.org/abs/2504.08385
#OpenScience #AI #RecommenderSystems
if you cannot attend in person, stay tuned for the video recording (it will be uploaded here:
www.youtube.com/c/MITRobotic...). [2/n]
🔥🔥🔥 CV Folks, I have some news! We're organizing a 1-day meeting in center Paris on June 6th before CVPR called CVPR@Paris (similar as NeurIPS@Paris) 🥐🍾🥖🍷
Registration is open (it's free) with priority given to authors of accepted papers: cvprinparis.github.io/CVPR2025InPa...
Big 🧵👇 with details!
🚨 New preprint!
How far can we go with ImageNet for Text-to-Image generation? w. @arrijitghosh.bsky.social @lucasdegeorge.bsky.social @nicolasdufour.bsky.social @vickykalogeiton.bsky.social
TL;DR: Train a text-to-image model using 1000 less data in 200 GPU hrs!
📜https://arxiv.org/abs/2502.21318
🧵👇
MASt3R-SLAM code release!
github.com/rmurai0610/M...
Try it out on videos or with a live camera
Work with
@ericdexheimer.bsky.social*,
@ajdavison.bsky.social (*Equal Contribution)
ETH starts a series of exciting guest talks on Robotics, Vision, and Controls this week.
Tomorrow at 12:00 Zurich time, @adai.bsky.social from TU Munich will give a talk titled "From Quantity to Quality for 3D Perception."
robotics-talks.com
#robotics
Such a refreshing talk by Michael Jordan at the AI Action Summit outlining a collectivist vision for AI.
He brings economics into discussion and the concept of collective intelligence to augment the human one in an inclusive, equitable, sustainable way. www.youtube.com/live/W0QLq4q...
SIGGRAPH'25 (paper-md5): 5 days + 11h.
RSS'25 (paper): 6 days + 1h.
ICML'25: 12 days.
SGP'25 (abs): 17 days.
SGP'25 (paper): 20 days.
RLC'25 (abs): 27 days.
RLC'25 (paper): 34 days.
IROS'25: 42 days.
ICCV'25: 47 days.
CORL'25: 100 days.
I started to put together a starter pack for research in AI+Ecology, check it out and let me know if you would like to be added!
go.bsky.app/8zugFF6
Link to the talk: youtu.be/1yvBqasHLZs?...
🚀 Meet RAVEN: a bird-inspired robot mastering air & land! With multifunctional legs, RAVEN can jump into flight, walk, and hop, tackling terrain and obstacles like a pro. Bonus? Jump-assisted takeoff boosts energy efficiency for groundbreaking multimodal navigation! 🌍✈
#Robotics #Robot #drone
On the Karpathy-Schmidhuber discussion: here is a slide I sometimes present on the history and origins of attention, which is shared between ML, image-processing (work of Jean-Michel Morel), NLP and computer vision.
I’d like multiple emojis options when pressing the like button instead of just a heart. It would be like linkedin but with fun emojis. @bsky.app
Last pic of Earth taken by Cassini before it crashed into Saturn
Finished teaching my new course on deep learning for computer vision. You can find the lecture notes here:
users.cecs.anu.edu.au/~sgould/pape...
For my first post on Bluesky, this recent talk I did at the recent BMVA one day meeting on World Models is a good summary of my work on Computer Vision, Robotics and SLAM, and my thoughts on a bigger picture of #SpatialAI.
youtu.be/NLnPG95vNhQ?...
Welcome to all the newcomers! Here's a starter pack for the 3D Computer Vision community: go.bsky.app/Cfm9XFe
📢 Relive the #CVPR2024 poster ScaLR w/ Gilles Puy. It's a Lidar pretrained model distilled from vision foundation models w/o any labels.
💪 Our best ScaLR is publicly available & well suited for semantic tasks w/ few or no labels & still SoTA results on linear probing
www.linkedin.com/posts/andrei...
Thanks for the reminder that I want to buy Foundations of Computer Vision!
The illustrated guide to a #PhD
matt.might.net/articles/phd...
While Bluesky looks like other social apps on the surface, it’s actually quite different. It’s an open network.
I blogged about it here:
It would be interesting to add a chapter about SLAM in heterogenous embedded platforms. It could detail the computational complexity of different techniques used in SLAM and the optimization performed to reach real-time processing on COTS (Jetson, Pi-like) and specific HW accelerators (FPGA, ASIC)
After my general computer vision starter pack is now full (150/150 entries reached), here is one specific to 3D Vision: go.bsky.app/Cfm9XFe
New! - Robotics Research Starter Pack
go.bsky.app/KvzCFeu
