You might like
CogNVS was accepted to @NeurIPSConf 2025! 🎉We are releasing the code today for you all to try: 🆕Code: github.com/Kaihua-Chen/co… Paper: arxiv.org/pdf/2507.12646 With CogNVS, we reformulate dynamic novel-view synthesis as a structured inpainting task: (1) we reconstruct input…
![tarashakhurana's tweet card. [NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos - Kaihua-Chen/cog-nvs](https://pbs.twimg.com/card_img/1987689800548392960/HMxejUHG?format=jpg&name=orig)
Excited to share recent work with @kaihuac5 and @RamananDeva where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…
Introducing RaC: A data collection protocol that boosts data efficiency by 10x compared to some of the best imitation results. Key idea: scale recovery & correction data systematically => policies can reset+retry when acting (consistent self-correct) => better performance. 🧵0/N
Ever wish a robot could just move to any goal in any environment—avoiding all collisions and reacting in real time? 🚀Excited to share our #CoRL2025 paper, Deep Reactive Policy (DRP), a learning-based motion planner that navigates complex scenes with moving obstacles—directly…
Our team is presenting work at the Conference on Robot Learning, @corl_conf, in Munich, Germany this week! Learn more about our accepted research — theaiinstitute.com/news/corl-roun…
One of the benefits of working in a relatively new field is getting to hear from its founders. We finally got around to uploading the talks from our keynote speakers at #RLC2024, including the one and only Barto!
"In the Beginning, ML was RL". Andrew Barto gave RLC 2024 an amazing overview of the intertwined history of ML and RL (Link below)
📢lots of people asked for the video of this talk, and happy it (and most* of the other @RL_Conference keynotes) are finally up! 🎉 youtube.com/watch?v=Az5BoT… * sadly, doina's keynote is not available as there was a technical issue when recording it 😰
youtube.com
YouTube
Sergey Levine - Reinforcement Learning in the Age of Foundation...
Great keynote by David Silver, arguing that we need to re-focus on RL to get out of the LLM Valley @RL_Conference
dynamic whole-body locomotion and manipulation 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 𝗼𝗳𝗳𝗹𝗶𝗻𝗲 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴. very simple online sampling with mppi is all you need!! website: whole-body-mppi.github.io arxiv: arxiv.org/abs/2409.10469
🎉 Diffusion-style annealing + sampling-based MPC can surpass RL, and seamlessly adapt to task parameters, all 𝘁𝗿𝗮𝗶𝗻𝗶𝗻𝗴-𝗳𝗿𝗲𝗲! We open sourced DIAL-MPC, the first training-free method for whole-body torque control using full-order dynamics 🧵 lecar-lab.github.io/dial-mpc/
For more detail: Check out our website (w/ code on github!): greedyperspectives.github.io The paper is on arxiv: arxiv.org/abs/2310.10863 Or track us down at @ieeeiros in October!
We just got done submitting Greedy Perspectives to #IROS24! This work looks at planning for filming tasks with occlusions and collisions. The quoted thread described the general approach. Look here for details and figures. Featuring: @_krishnasuresh @AdityaR14458961 @AirLabCMU
🤖🎥 I recently had some papers on planning for videography and reconstruction accepted to #IROS24 and #CDC24 from my postdoc with @AirLabCMU. But, summer travel and the start of classes left me with little mental space to write about them!
So proud of @ben_eysenbach for coming up with this idea and implementing it – and so proud to be in a field with these amazing women. Next @RL_Conference we'll have to get a group photo!
Really nice initiative by @ben_eysenbach , who prepared these posters (hung around @RL_Conference ) of notable women in RL !
Ta-da, the Olin students in question: Luke Raus, Jessica Brown, Krishna Suresh (@_krishnasuresh), and Brooke Wager
I'm at @RL_Conference this week; let me know if you want to meet up! Especially down to chat about RL for building energy management. Bonus: I can intro you to 4 wonderful @OlinCollege undergrads I've worked with this year who are here (and would make excellent PhD Students)✨
Can't trip Atlas up! Our humanoid robot gets ready for real work combining strength, perception, and mobility.
youtube.com/watch?v=68rz8g… hard working on a 5 Stone auto for #skystone
youtube.com
YouTube
5ish Stone Auto - FTC SkyStone - Juniper Robotics 16449
Robot teaser for the Ohio State Championship youtu.be/RlFEspJoIPg. Hyped to stack some more power!
youtube.com
YouTube
PowerStackers 5029 Rover Ruckus Teaser Ohio States
United States Trends
- 1. Kevin James 3,069 posts
- 2. Jack Hughes 1,691 posts
- 3. Bubba 30.7K posts
- 4. Bill Clinton 120K posts
- 5. RIP Coach Beam N/A
- 6. #BravoCon 4,902 posts
- 7. Last Chance U 4,903 posts
- 8. Metroid 11.3K posts
- 9. $EDEL N/A
- 10. $GOOGL 21.2K posts
- 11. Wale 45.9K posts
- 12. Oakland 10.4K posts
- 13. Vatican 15.2K posts
- 14. Hunter Biden 21.3K posts
- 15. Zverev 3,911 posts
- 16. Paul Blart N/A
- 17. Crooks 80.2K posts
- 18. Donica Lewinsky 1,731 posts
- 19. Matt Taylor 2,527 posts
- 20. Berkshire 4,266 posts
Something went wrong.
Something went wrong.