Robots need touch for human-like hands to reach the goal of general manipulation. However, approaches today don’t use tactile sensing or use specific architectures per tactile task. Can 1 model improve many tactile tasks? 🌟Introducing Sparsh-skin: tinyurl.com/y935wz5c 1/6

Last week I passed my thesis proposal, and I'm now officially a Ph.D. candidate! I'm grateful to my committee, and everyone who supported me. My proposed thesis "Self supervised perception for tactile dexterity" will explore ways to improve dexterous manipulation using tactile reps.

I asked "on the other platform" what were the most important improvements to the original 2017 transformer. That was quite popular and here is a synthesis of the responses:

⏰ Heads up! The deadline for two #CVPR2025 Autonomous Grand Challenge tracks is May 10th, 2025: 1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20... 2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...

I love situations like this: in the pre-deep era (and following classical learning theory), people would have stopped training the white model at the red arrow, as the validation error increases. But, no, the model first seems to learns unwanted short cuts (overfitting wildly) but finds a way out.

Some pictures of the Pittsburgh spring to reduce the spiciness of the bsky feed! a6700 w/ 17-70mm Tamron lens

A new #CosmicDistanceLadder post on why lunar and solar eclipses tend to come in pairs (for instance, the solar eclipse next week is paired with the lunar eclipse from last week). www.instagram.com/p/DHkS3EcA40L

What would you love to know about #robot learning and decision making? Later this season, I'll be chatting to Prof. Lerrel Pinto (@lerrelpinto.com) from NYU about using machine learning to train robots to adapt to new environments. Send me your questions for Lerrel: robottalk.org/ask-a-question/

We are looking for a student researcher to work on video understanding plus 3D, in Google DeepMind London. DM/Email me or pass it to someone if you feel it may be a good fit!

The first measles death in the US in a decade -- the tragic, preventable death of a child whose parents chose not to protect them with vaccination -- should spark an immediate nation-wide campaign to ensure all children are protected against preventable diseases. Anything less is unconscionable.

Gearing up for our workshop on 4D Vision at @CVPR this June! Check out our line up of speakers and submit your work by Mar 28. Spread the word!

Last night I found out that the NSF math postdoctoral fellowship I applied for is being deleted because it does not comply with Trump’s executive orders on DEI in the federal government. I’m going to answer some FAQs and share some thoughts about this ordeal in this thread 1/n

Seeing some of the early results from DexterityGen were definitely a wow moment for me! It doesn't take a lot to realize all the new opportunities a strong teleop system like this enables! 🚀 X thread: x.com/zhaohengyin/... Link: zhaohengyin.github.io/dexteritygen/

Not one VC would ever fund a startup to do the kind of hardcore optimization work that DeepSeek did. Every VC firm should be asking themselves why.

just warms my heart to see how they're citing my stuff -- "some people have done some thing [7]" "most work is inadequate [8]" "unlike prior work [7,8,9], we don't suck" 7. Bigham 8. Bigham 9. Bigham them increasing my hindex is joke on them! 😂

A new dawn, a golden era of boot licking before us. Unheralded, unimaginable forms of boot licking to be discovered

It’s kinda wild how much of ML is tradition. Not always in a bad way, just that there’s so damn much that you’re forced to rely on others’ recommendations for models, hyperparameters, training sets, loss metrics, architectures, and quirky practices.

Brilliant talk by Ilya, but he's wrong on one point. We are NOT running out of data. We are running out of human-written text. We have more videos than we know what to do with. We just haven't solved pre-training in vision. Just go out and sense the world. Data is easy.

This piece of hardware is exciting! @remicadene.bsky.social is the hand able to apply sufficient per joint torques for dexterous tasks such as bottle cap opening?

My anecdote for when entropy clicked for me, was when I understood that the uniform distribution has the highest entropy, and any other distribution is more surprising than that! Prof. Keenan's visualizations are impeccable and a gift!

Excited to present new work on using diffusion priors for video amodal segmentation and content completion! with Deva Ramanan and @tarashakhurana.bsky.social arXiv: arxiv.org/abs/2412.04623 project page: diffusion-vas.github.io

IMO VQGAN is why GANs deserve the NeurIPS test of time award. Suddenly our image representations were an order of magnitude more compact. Absolute game changer for generative modelling at scale, and the basis for latent diffusion models.

Threads banking on Insta's network has turned into baggage. Finding folks I'm interested in, like ML researchers, was incredibly easy on bsky. Starter packs, felt cringe, but were actually useful in discovering accounts. Friction in finding people on Threads, made it very passive for me atleast

The robotics community has built many vision-tactile sensors such as GelSight and DIGIT resulting in significant progress in robot tactile perception. How can one reconcile these sensors to work across many tactile tasks without collecting a lot of labeled data? More on 🎯Sparsh 🧵⬇ 1/6