Ganesh Iyer

@gowthami_s Genuine question since I’m new to this, are AWM/NFT not worth pursuing at a larger scale?

Maybe hot take - I’ve read a bunch of RL for image generation papers over last few months and honestly it’s been pretty disappointing. All of them are variations of GRPO and all of them are incremental algo changes. Tbh most of these don’t even matter for large models + large group size with good reward model setting. I see most grad students are still optimizing their projects for reviewers rather than genuinely trying to solve some of the real problems in visual generation. For example - the biggest alpha in my eyes would’ve been an artifact detection model - not just for mangled limbs, most image models produce far more artifacts which are hard to quantitatively measure, but I haven’t seen a single research paper or a model on this. So my 2c, if you are a grad student targeting a job in industry, target for impact, no one cares about your third CVPR paper, one is enough to get you in the door, building a model industry actually uses gives you all the leverage. Impact > Publications. 🫳🎤

@brenthyi who worked on FPO/FPO++ is finishing his PhD and going on the job market 😭✨ He is also the person behind viser, pyroki, egoallo, jaxls, tyro and more! I can't express how amazing it is to have Brent on your team..! Any team would be incredibly lucky to have him!!

@fanf666 @JoshuaK78925 TPU

@JoshuaK78925 What material is the orange part?

How can robots handle fragile, soft everyday objects like humans do, using vision & tactile to regulate force? 🤖🥚 Introducing our full-stack solution: a low-cost ($150) force gripper (0.45~45N), a force-aware teleoperator, and a reactive policy for learning force control.

@a_yukh Le Me*

Me after visiting Hugging Face office in Paris

@deliprao The first one even has a broken textures png

Agents training in RL gym

@DJiafei Thank you so much for sharing this Jiafei! :)

Amid all the noise and rapid pace in the field, I really appreciated Russ Tedrake’s talk on their LBM work and the rigorous evaluations that go beyond flashy demos—some papers these days don’t even include error bars. The talk offered valuable insights on avoiding reinvention. Highly recommend everyone to watch the lecture. FYI: This is easily one of the most impressive demos I’ve ever seen. youtube.com/watch?v=TN1M6v…

@akashshrm02 Hi Akash, Can't DM you, but would love to sync over the next few days, whenever you have time.

I will be at #CVPR2025! Looking forward to catch up with colleagues, talk about SSL, robots, tactile sensing, world models and all else in between! I'm also starting to look for Research Scientist roles starting 2026. Details at akashsharma02.github.io Hmu if interested!

Robotics 101: An Odyssey from A Vision Perspective Link: opendrivelab.com/cvpr2025/tutor… Date: 6/11 Full Day Speakers: Davide Scaramuzza, Deepak Pathak, Guanya Shi, Yilun Du, Angjoo Kanazawa, Boris Ivanovic, Dhruv Shah, Chonghao Sima

(Tutorial) From Video Generation to World Model Link: world-model-tutorial.github.io Date: 6/11 Full Day Speakers: Jack Parker-Holder, Hong-Xing "Koven" Yu, Jiaming Song, Pengfei Wan, Angjoo Kanazawa, Sherry Yang

(Tutorial) 3D Deep Learning, Gaussian Splats and Physics Simulation Hands-On Lab with NVIDIA Kaolin Library Link: kaolin.readthedocs.io/en/latest/note… Date: 6/11 Morning Organizers: Clement Fuji Tsang, Vismay Modi, Or Perel, Masha (Maria) Shugrina

Agent in Interactions, from Humans to Robots Link: agents-in-interactions.github.io Date: 6/12 Full Day Speakers: Jitendra Malik, Dorsa Sadigh, Joseph Sivic, C. Karen Liu, Hanbyul Joo, Richard Newcombe, Michael Black

I'm excited to attend #CVPR2025! Signal boosting thread of all the workshops and tutorials in the embodied AI, world models, robotics, simulation etc. spaces I'd really like to attend for personal research interests (but cannot due to work research interest differences)🧵⬇️

6th Embodied AI Workshop Link: embodied-ai.org/cvpr2025/ Date: 6/12 Full Day Speakers: Anthony Francis, David Hall, Lerrel Pinto, Jianwei Yang, Jiayun (Peter) Wang, Rika Antonova, Rareș Ambruș, Nikhil Mohan, Huan Ling

3D Digital Twin: Progress, Challenges, and Future Directions Link: projectaria.com/events/CVPR202… Date: 6/12 Full Day Speakers: Richard Newcombe, Andrea Vedaldi, Hao (Richard) Zhang, Qianqian Wang, Xiaoshuai Zhang, Xiaolong Wang, Milos Hasan, Shuang Zhao, James Fort

Open-World 3D Scene Understanding with Foundation Models Link: opensun3d.github.io/index.html Date: 6/12 Afternoon Speakers: Laura Leal-Taixé, Lukas Schmid, Jeannette Bohg, Vasileios Balntas, Afshin Dehghan

Workshop on Perception for Industrial Robotics Automation Link: pira-workshop.github.io Date: 6/12 Afternoon Speakers: Vincent Vanhoucke, Kartik Iyer, Bowen Wen, Kartik Venkatraman

Workshop on 3D-LLM/VLA: Bridging Language, Vision and Action in 3D Environments Link: 3d-llm-vla.github.io Date: 6/12 Morning Speakers: Jitendra Malik, Dieter Fox, Katerina Fragkiadaki, Angel X. Chang, Siyuan Huang, Yilun Du, Andy Zeng

3D Vision Language Model for Robotics Manipulation: Opportunities and Challenges Link: robo-3dvlms.github.io Date: 6/11 Full Day Speakers: Angel Chang, Chelsea Finn, Chuang Gan, Hao Su, Katerina Fragkiadaki, Yunzhu Li, Ranjay Krishna, Dieter Fox

The 1st Workshop on Humanoid Agents Link: humanoid-agents.github.io Date: 6/11 Full Day Speakers: Angelica Lim, Libin Liu, Xue Bin Peng, Gerard Pons-Moll, Xavier Puig, Guanya Shi, Tianmin Shu, Sebastian Starke, Xiaolong Wang

Embodied Intelligence for Autonomous Systems on the Horizon Link: opendrivelab.com/cvpr2025/works… Date: 6/11 Full Day Speakers: Jitendra Malik, Abhinav Gupta, Felix Heide, David Crandall, Vincent Vanhoucke, Antonio Loquercio, Fatma Güney

Foundation Models for Embodied Agents Link: …models-meet-embodied-agents.github.io Date: 6/11 Full Day Speakers: Manling Li, Yunzhu Li, Jiayuan Mao, Wenlong Huang

Real-to-Sim: Bridging the Gap Between Neural Rendering and Robot Learning Link: real2simworkshop.github.io Date: 6/11 Afternoon Speakers: Marco Pavone, Dhruv Shah, Gordon Wetzstein, Lingje Liu