Full episode dropping soon! Geeking out with @nishanthkumar23 on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models pix2pred.csail.mit.edu Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @nishanthkumar23 on From Pixels to Predicates: Learning Symbolic World Models via Pretrained Vision-Language Models pix2pred.csail.mit.edu Co-hosted by @micoolcho @chris_j_paxton
Walking robots can do all kinds of exciting things like dancing, running, and martial arts — but for them to be useful, they must be able to use their legs to handle terrain, to move over obstacles not just around them. So, how can we best train walking policies for legged…
Full episode dropping soon! Geeking out with @ChongZitaZhang on Attention-based map encoding for learning generalized legged locomotion science.org/doi/10.1126/sc… Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @ChongZitaZhang on Attention-based map encoding for learning generalized legged locomotion science.org/doi/10.1126/sc… Co-hosted by @micoolcho @chris_j_paxton
With enough data, robots and AI can learn “world models” that let them predict the results of their actions. These models are a way to learn how embodied AI agents can perform a wide variety of useful tasks — but they require a huge amount of data. The team at General Intuition…
Full episode dropping soon! Geeking out with @PimDeWitte @AdamJelley2 , cofounders of @gen_intuition leveraging large-scale game recordings to build agents with deep spatial/temporal reasonings. Built upon the work by Adam, @EloiAlonso1 @micheli_vincent (all cofounders at…
Full episode dropping soon! Geeking out with @PimDeWitte @AdamJelley2 , cofounders of @gen_intuition leveraging large-scale game recordings to build agents with deep spatial/temporal reasonings. Built upon the work by Adam, @EloiAlonso1 @micheli_vincent (all cofounders at…
How can we make a humanoid robot play table tennis? The robot must hit a moving ball and return it over and over again, requiring precise whole-body control over again. @ZhiSu22 tells us about how he developed a hierarchical approach for planning an whole body control that lets…
How can we build robotic hands with truly superhuman dexterity? @DaxoRobotics is developing a unique tendon-driven soft robot hand, which aims to be tougher and more capable than a traditional humanoid hand. Each finger consists of many different tendons, which act in concert to…
Full episode dropping soon! Geeking out with @ZhiSu22 on HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning humanoid-table-tennis.github.io Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @ZhiSu22 on HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning humanoid-table-tennis.github.io Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @tom_jiahao on @DaxoRobotics Co-hosted by @micoolcho @chris_j_paxton
Reasoning models have massively expanded what LLMs are capable of, but this hasn’t necessarily applied to robotics. Perhaps this is in part because robots need to reason over space, not just words and symbols; so the robotics version of a reasoning model would need to think in…
Full episode dropping soon! Geeking out with @tom_jiahao on @DaxoRobotics Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @jason_lee328 @hq_fang @DJiafei on MolmoAct: An Action Reasoning Model that reasons in 3D space allenai.org/blog/molmoact Co-hosted by @micoolcho @chris_j_paxton
Offline reinforcement learning is crucial for robotics, but does it scale? We talk to @seohong_park , who discusses how for long-horizon manipulation problems the answer may be no — at least not yet. But there are tricks that you can use to make it work effectively. Watch…
Full episode dropping soon! Geeking out with @jason_lee328 @hq_fang @DJiafei on MolmoAct: An Action Reasoning Model that reasons in 3D space allenai.org/blog/molmoact Co-hosted by @micoolcho @chris_j_paxton
Full episode dropping soon! Geeking out with @seohong_park on Q-learning is not yet scalable seohong.me/blog/q-learnin… Co-hosted by @micoolcho @chris_j_paxton
Robots has a data problem, in that robotics data is rare. While human video is quite common, it’s not usually directly usable for robots for a variety of reasons, most significantly that it’s missing explicit, accurate robot actions. Instead, @jerthesquare_ proposes that we…
United States 趨勢
- 1. #RiyadhSeason 14.6K posts
- 2. Mason 38.2K posts
- 3. Syracuse 8,232 posts
- 4. Lincoln Riley 1,543 posts
- 5. #AEWTailgateBrawl 1,901 posts
- 6. Oregon 27.9K posts
- 7. #AEWFullGear 7,174 posts
- 8. Arch Manning 3,227 posts
- 9. #TheRingIV 4,217 posts
- 10. Joe Jackson 1,189 posts
- 11. Stoops 1,713 posts
- 12. Kansas State 3,109 posts
- 13. #GoBlue 2,539 posts
- 14. Arkansas 9,965 posts
- 15. Vandy 3,422 posts
- 16. Bam Rodriguez 1,647 posts
- 17. Jonathan Smith N/A
- 18. Fran Brown N/A
- 19. Jeremiyah Love 3,863 posts
- 20. Sadiq 8,172 posts
Something went wrong.
Something went wrong.