Siddharth Karamcheti
@siddkaramcheti
Followers
4K
Following
5K
Media
54
Statuses
1K
Incoming Assistant Professor @GeorgiaTech / @ICatGT / @GTrobotics. Prev: PhD from @StanfordAILab @stanfordnlp. I like robots, language, and people.
Stanford, CA
Joined September 2018
Thrilled to share that I'll be starting as an Assistant Professor at Georgia Tech (@ICatGT / @GTrobotics / @mlatgt) in Fall 2026. My lab will tackle problems in robot learning, multimodal ML, and interaction. I'm recruiting PhD students this next cycle – please apply/reach out!
68
27
546
RT @WilliamBarrHeld: The time I invested in learning Jax has been paid back ten-fold both in TPU FLOPs and great infra from @dlwh. Would….
marin.community
0
10
0
RT @danfei_xu: Honored to receive the NSF CAREER Award from the Foundational Research in Robotics (FRR) program!. Deep gratitude to my @ICa….
0
6
0
This was a rough year to be on the academic job market in the US, and I'm so grateful to all of my supporters. I especially want to thank my advisors @DorsaSadigh and @percyliang for their unwavering faith in me, my amazing collaborators, and my family. Onwards!.
3
0
19
I can't wait to join the GT community next year. Until then, I'll continue at @ToyotaResearch (in Boston). Check out @RussTedrake's recent talk; beyond results, it describes a philosophy for scientific exploration that I hope to carry forward.
1
0
14
Introducing ProVox — new work on building proactive and personalized agents for human-robot collaboration!. ProVox is the next chapter in the Vocal Sandbox saga, and makes it even easier to deploy adaptive robots alongside real people. See @jenngrannen’s thread for more!.
Meet ProVox: a proactive robot teammate that gets you 🤖❤️🔥. ProVox models your goals and expectations before a task starts — enabling personalized, proactive help for smoother, more natural collaboration. All powered by LLM commonsense. Recently accepted at @ieeeras R-AL!. 🧵1/7
0
1
22
RT @LerrelPinto: It was nice engaging with the CV community on ways to stand out in the crowd. My answer was simple: work on robotics. Th….
0
25
0
RT @percyliang: For a rare look into how LLMs are really built, check out @dlwh's retrospective on how we trained the Marin 8B model from s….
0
73
0
RT @percyliang: What would truly open-source AI look like? Not just open weights, open code/data, but *open development*, where the entire….
0
203
0
RT @lucy3_li: I'm joining @WisconsinCS @uwcdis as an assistant professor in fall 2026!! There, I'll continue working on language models, co….
0
39
0
RT @ebiyik_: We developed a computational model of human interventions/corrections and a method to learn from such feedback. We don't need….
0
2
0
RT @amberxie_: Introducing ✨Latent Diffusion Planning✨ (LDP)! We explore how to use expert, suboptimal, & action-free data. To do so, we le….
0
43
0
RT @SurajNair_1: Since the first year of my PhD, every talk I’ve given has opened with a slide about the distant north star: dropping a rob….
0
4
0
RT @KarlPertsch: Training with discrete FAST action tokenization now powers all of our pre-training in π-0.5! .When combined with π-0 style….
0
2
0
RT @DorsaSadigh: Here is another uncut video of real-time interactions with @GoogleDeepMind 's Gemini Robotics!
0
174
0
Is there a nice solution for porting a Flax model to PyTorch (and vice-versa)? Or minimally a list of common gotchas in the porting process/important unit tests to write (with expected tolerances for specific ops)?.
2
0
2
RT @andrea_bajcsy: 📢 Announcing the first @ieee_ras_icra workshop on Safely Leveraging VLMs in Robotics! #ICRA2025. 🎯 How can we safely le….
0
17
0
RT @HRIPioneers: Welcome #HRIPioneers2025! @megha_byte from Stanford University will present their work 'Robotics for Personalized Motor Sk….
0
10
0
RT @Raunaqmb: Ever struggled with multi-sensor data from cameras, depth sensors, and other custom sensors? Meet AnySense—an iPhone app for….
0
27
0