Siddharth Srivastava
@sidsrivast
Followers
336
Following
269
Media
28
Statuses
147
Scientist. Associate Professor at ASU. Research focus in AI and Robotics. @[email protected]
Joined February 2019
How does logic arise from a real-valued real world? Our new approach considers this in the context of robot planning, and invents predicates and logic-based models from raw robot trajectories without any annotations. Joint w/ @shah__naman Jayesh Nagpal @pulkit_verma 🧵..1/4
1
7
35
Robots can finally invent their own symbols for reasoning and planning 🤯. We show the first method that learns symbolic world models directly from raw demos—no labels, no hand-coded actions. This lets robots generalize to tasks 18× larger than training. 👇🧵
5
41
229
Excited to share the success of the #IJCAI2025 Workshop on User-Aligned Assessment of Adaptive AI Systems. It featured invited talks from Reid Simmons, @XujieSi, and @ruqi_zhang; and a panel discussion with @r_mirsky, @Sriraam_UTD, Reid, and @XujieSi. 🌐 https://t.co/AhhwUfjqMO
#IJCAI2025 Workshop on User-Aligned Assessment of Adaptive AI Systems (AIA2025) is now in progress. Please note that the room is changed to 520C.
1
2
12
Curious to hear about creating generalist robots from leaders in the field? Don’t miss our panel “Representations for Generalist Robots” (4-5pm) @corl_conf LEAP workshop! Feat. @chelseabfinn @animesh_garg Vincent Vanhoucke @Marc__Toussaint @sidsrivast and Leslie Kaelbling!
0
8
29
Researchers at @ASU are using AI to teach robots how to do jobs that humans don't want. The new technology would make the deployment of robots substantially less expensive and less time-consuming: https://t.co/6tIliBlQLm
0
2
3
Excited to announce 8th Workshop on Generalization in Planning (#GenPlan2025) at AAAI (#AAAI2025)! Consider submitting your work and join us as we explore generalization and transfer in sequential decision-making with a stellar line-up of speakers. https://t.co/AzzZJv3Fqf
1
5
12
I will also present our work on epistemic exploration in non-stationary settings, which shows that it is worth learning a STRIPS-like model if you want better efficiency and lower costs. Joint work w/ @RushangKaria, Alberto Speranzon, @sidsrivast Link:
0
1
3
I'll present our work "Epistemic Exploration for Generalizable Planning and Learning in Non-Stationary Settings" at #ICAPS2024 today. Joint Work w/ @RushangKaria, Alberto Speranzon, @sidsrivast ⏰ 01:45 PM MDT in Room KC 203 @ICAPSConference Join the session to learn more.
0
2
12
Congratulations to @pulkit_verma!! His dissertation helped kickstart the emerging area of user-driven assessment of AI systems that can learn and plan.
I got hooded recently. It was great to have my parents with me, who have been incredibly patient and supportive throughout my PhD journey. And, of course, thanks to @sidsrivast, without whose amazing mentorship, this would not have been possible. @SCAI_ASU #ASUgrad #PhDone
0
1
27
I got hooded recently. It was great to have my parents with me, who have been incredibly patient and supportive throughout my PhD journey. And, of course, thanks to @sidsrivast, without whose amazing mentorship, this would not have been possible. @SCAI_ASU #ASUgrad #PhDone
0
1
38
Congratulations to Dr. @shah__naman for a successful PhD defense and a great dissertation talk! 🥳🍾🎉 A special thanks to the committee, George Konidaris, @rao2z, Alberto Speranzon and Yu Zhang!
3
3
28
Congratulations to Dr. @pulkit_verma for completing his dissertation with a fabulous presentation and defense today! 🍾🎇🥳 Here's a big thanks to the committee members: Nancy Cooke, Georgios Fainekos, and Yu Zhang for all their time and effort along the way!
4
3
31
It’s a wrap! Check out this recap of the excellent #AAAI 2024 Spring Symposium, held last week at Stanford, facilitated by #SCAI Associate Professor @sidsrivast and his #PhD student @pulkit_verma. Thanks to all who attended and shared their work and perspectives.
0
2
3
I am looking to recruit several PhD students in human-robot interaction, accessibility, haptics, and virtual reality for fall 2024. If you are interested, please complete this form: https://t.co/wQccCwlOSn
@SCAI_ASU @ASUEngineering @ASU
4
27
77
The program for the #AAAI 2024 Spring Symposium on User-Aligned Assessment of Adaptive AI Systems is now available. We have a fantastic lineup of invited speakers. The symposium starts this Monday. Link: https://t.co/yJ8eUDLnN7
@Sriraam_UTD @sidsrivast @HazemTorfah @RealAAAI
3
1
8
Congrats to #SCAI Associate Professor @sidsrivast who has been named a Scialog Fellow by @RCSA1. As one of only approximately 50 new Fellows, Srivastava will work to develop innovative approaches and solutions to multidisciplinary problems. https://t.co/74FBkRQxea
rescorp.org
Scialog / 2024-2026 Major advances in automated instrumentation and artificial intelligence (AI) are creating enhanced opportunities for innovation in basic research. Integrating automation and AI …
4
1
10
We're looking forward to developing this approach for more general settings, including stochasticity, partial observability, and active learning, to make the overall approach more robust. Paper: https://t.co/kBuBpRw1Ny 4/4
arxiv.org
Robots still lag behind humans in their ability to generalize from limited experience, particularly when transferring learned behaviors to long-horizon tasks in unseen environments. We present the...
1
0
3
Interestingly, the auto-invented predicate and actions turn out to be richer and go beyond classical (human-intuition driven) notions of high-level actions! 3/4
1
0
2
Results indicate that the learned logic generalizes well, allowing the agent to solve more complex problems with many more objects and longer horizons without the need for reward shaping or hand-crafted representations. We focus on deterministic settings as a starting point. 2/4
1
0
2