Vignesh Prasad

@aks1812 Heroes!!!

@FatAndFurious42 Did you get the two TV shows referenced in my tweet?

Ohh...he is not available. He is busy making a miracle drug that gives you super hero abilities. Also he is in a constant fear that he is cursed because all his girlfriends keep getting attacked.

Want to know how to learn effective multisensory representations that make your robot robust to partying? Check out our latest RAL paper by @RKrohn_ : msdp-pearl.github.io

This is what happens when novelty, not results, becomes the North Star. The real work is often in the system details, but those rarely make it into the spotlight. Instead, we get unnecessary “novelty” that’s easier to package, pitch, and hype. Will there ever be a time when system details are treated as first-class citizens in papers?

🚀 Hiring PhDs & Postdocs in Structured Robot Learning & Embodied AI @TUDarmstadt (PEARL Lab) 🤖 We study how structure in the robot–environment system can be exploited to learn robust, adaptive, and generalizable behaviors, beyond black-box policies 🔬 Topics: • Grounding (language → perception → action) • Structured world models • VLA + control + memory • RL (credit assignment, offline→online) • Whole-body & bimanual mobile manipulation 🇪🇺 New EU Lighthouse Project on Generative AI for Robotics + ERC StG SIREN 👉 Full call: tinyurl.com/pearlgenai Please repost 🙏 #RobotLearning #EmbodiedAI #Robotics #MachineLearning #PhDPositions #Postdoc

Simplicity should be valued more. When a task can be solved equally with a simpler framework, one should not be blamed having “nothing new”. Many unnecessary novelties are invented for the sake of novelty, while the effort of making simpler methods general is not appreciated.

🚀 New work accepted to ICRA 2026! We introduce a flow-matching framework on the SE(3) manifold. Instead of just a single guess, our model captures the full pose distribution—perfect for handling tricky occlusions, symmetries, and partial views in real-world robotics. Huge thanks to my amazing collaborators! @n_w_funk @softraeh @FatAndFurious42 @Jan_R_Peters @GeorgiaChal 📄 Paper: arxiv.org/abs/2511.01501 🌐 Website: yufengjin.github.io/projects/se3-p…

Alma mater researching things that matter 🔥🔥🔥

Repeat after me: This is NOT a paper contribution, it’s an expected component!

Anyone with basic brains can figure out what Indigo did was very intentional. This was not sudden disruption, this was almost a planned strike to strongarm the government into giving it what it wants. What people went through doesn't matter to them, it's just collateral damage. And the fact that govt let this happen is on them. The fact that we essentially have monopolistic/duopolistic situations in so many major sectors is on this Government. But what to do, let's look for ways to blame RaGa on this too.

How can we effectively integrate information from multiple sensors, such as cameras, force-torque, and joint proprioception, for real-world contact-rich manipulation? Check out @RKrohn_'s work on multisensory representation learning for RL: arxiv.org/abs/2511.14427

@rz_california While I agree, RAL also has long timelines for conferences. Eg., to present at IROS in Oct. 2026, a RAL paper needs to be accepted and transferred by April 30th, so the paper should be submitted in Nov. 2025 in the most ideal case, almost a year before the conference

That’s one of the reasons why I recently prefer RA-L more. If there is a double-anonymous journal that can finish one-round constructive rebuttal and give you feedback within 3 months, then Conferences like ICRA and IROS will be less attractive. Especially RA-L paper can also be presented at these conferences.

Let's gooo!!!!

Small change, it's poster 283

If you're at ICCV and are interested in object pose estimation, gaussian splatting, and in general about 3D geometry, object-centric representations for robotics, come on over to Poster 744 at 3pm

Slides for my #ICCV2025 RANSAC in 2025 talk are here drive.google.com/file/d/1_1zYAo…

Meanwhile OpenAI is rolling out the iPhone pro max plus ultra super so that the next town over can have a water crisis

"2HandedAfforder" was a best workshop paper finalist at the H2R Workshop on Sensorizing, Modeling, and Learning from Humans at CoRL 2025!!! 🎉🎉🎉

Excited to be in Korea almost a year after being away from conferences. Now I come back for two conferences #CoRL2025 and #Humanoids2025 with a small guest 👶 While on maternity leave my amazing team continued progress on Structured Robot Learning! Here is a list of the activities of PEARL group at @corl_conf: 1. Today, Saturday Sept. 27 I will give a talk at the corl25-genpriors.github.io talking about Beyond Scale: Structured Priors for Efficient Robot Learning at 11:25. Join me to get a glimpse at the newest cool research from the pearl-lab.com 2. I’ll also be at the panel of the same workshop at 15:25! Looking forward to the fruitful discussions. 3. Also today,Vignesh @FatAndFurious42 will present our new work on extracting Bimanual Affordances from Human Videos (sites.google.com/view/2handedaf…) at the sites.google.com/view/h2r-corl2… and sites.google.com/stanford.edu/c… 4. While Frankie @FrankieZhang41 will present our new work on “Adaptive Diffusion Constrained Sampling for Bimanual Robot Manipulation” (…fusion-constrained-sampling.github.io) at the rational-robots.github.io 5. Tomorrow Sept 28, Steven @softraeh will present SYMDEX: Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation supersglzc.github.io/projects/symde…. Catch him at Spotlight 2 & Poster session 1. We have more to present at the Humanoids conference, so stay tuned!

Abacus, spelling bee, etc are all useless pursuits which does overall harm than good. Kids should grow up playing sports and musical instruments instead of all this grindjeetry.

Why I Went Silent After Launching Empowered Indian – And Why I'm Done Being Quiet 3 days ago, I launched the MPLADS Dashboard showing where public money really goes. Within hours, I got an email: "Take it down before things get messy. We know where you live. We're watching closely." So I went dark. For 3 days. Not because I'm scared. But because I needed to think. Here's what I decided: The dashboard is coming back. The data will be public. The truth will out. Because every threat proves we're onto something. Every attempt to silence us shows they have something to hide. They wanted me to "play smart" and disappear. Instead, I'm going loud. To whoever sent that threat: You just turned a website into a movement. Congratulations. To everyone else: They're scared of transparency. They're scared of YOU knowing where your money goes. Let's give them something to really fear. #EmpoweredIndian CC: @malpani