Zsolt Kira
@zsoltkira.bsky.social
Associate Professor @ Georgia Tech
computer vision & robotics/embodied AI
http://faculty.cc.gatech.edu/~zk15
computer vision & robotics/embodied AI
http://faculty.cc.gatech.edu/~zk15
@cvprconference.bsky.social next week will be an exciting one! Check out our work below on VLMs, VLAs, and 3D for robotics (including the first 3D VLMs for Robotics workshop)!
June 6, 2025 at 8:54 PM
@cvprconference.bsky.social next week will be an exciting one! Check out our work below on VLMs, VLAs, and 3D for robotics (including the first 3D VLMs for Robotics workshop)!
3D VLMs + robotics! What's not to like?
Submit your works by April 15th!
Submit your works by April 15th!
🚀Exciting News! Join us at the inaugural #CVPR2025 Workshop on 3D Vision Language Models (VLMs) for Robotics Manipulation on June 11, 2025, in Nashville, TN! 🦾
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
robo-3dvlms.github.io
1/N
@cvprconference.bsky.social
February 26, 2025 at 9:58 PM
3D VLMs + robotics! What's not to like?
Submit your works by April 15th!
Submit your works by April 15th!
Check out #NeurIPS papers from RIPL! We will present robust finetuning of FMs, pre-trained diffusion models for action, and VLA action tokenization. I'll also be giving a (unfortunately remote) talk on continual learning.
arxiv.org/abs/2411.01713
arxiv.org/abs/2405.05852
arxiv.org/abs/2406.07904
arxiv.org/abs/2411.01713
arxiv.org/abs/2405.05852
arxiv.org/abs/2406.07904
December 12, 2024 at 8:43 PM
Check out #NeurIPS papers from RIPL! We will present robust finetuning of FMs, pre-trained diffusion models for action, and VLA action tokenization. I'll also be giving a (unfortunately remote) talk on continual learning.
arxiv.org/abs/2411.01713
arxiv.org/abs/2405.05852
arxiv.org/abs/2406.07904
arxiv.org/abs/2411.01713
arxiv.org/abs/2405.05852
arxiv.org/abs/2406.07904
Amazing move by Bluesky.
I think it's underappreciated how much computational social science was affected when X gated the data behind exorbitant pricing.
Lots of potential for multimodal models/AI research as well!
I think it's underappreciated how much computational social science was affected when X gated the data behind exorbitant pricing.
Lots of potential for multimodal models/AI research as well!
Bluesky's firehose is a treasure trove of public data for researchers and developers, and it's completely free. Check out our developer docs: docs.bsky.app
November 23, 2024 at 4:40 PM
Amazing move by Bluesky.
I think it's underappreciated how much computational social science was affected when X gated the data behind exorbitant pricing.
Lots of potential for multimodal models/AI research as well!
I think it's underappreciated how much computational social science was affected when X gated the data behind exorbitant pricing.
Lots of potential for multimodal models/AI research as well!
My new workflow: See interesting paper on other site, search for it to see who posted it on here, follow.
Eventually it will converge right?
Eventually it will converge right?
November 19, 2024 at 2:50 AM
My new workflow: See interesting paper on other site, search for it to see who posted it on here, follow.
Eventually it will converge right?
Eventually it will converge right?
Lots of advancements in using implicit representations for robotics! Check out this survey.
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
Neural Fields in Robotics: A Survey
Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D d...
arxiv.org
November 18, 2024 at 9:29 PM
Lots of advancements in using implicit representations for robotics! Check out this survey.
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
One day we will hopefully have a unified 3D representations as opposed to mixed ones depending on domain 🤞
📖arXiv: arxiv.org/abs/2410.20220
🖥️github list: github.com/zubair-irshad/…
Feature request: Filter feed by LLM instead of keywords!
I want to be able to say things like "No politics". Or "Research papers on multi-modal models".
I find it crazy that most platforms don't let you control your feed besides through behavior (likes/mutes), let alone use AI to do so.
I want to be able to say things like "No politics". Or "Research papers on multi-modal models".
I find it crazy that most platforms don't let you control your feed besides through behavior (likes/mutes), let alone use AI to do so.
November 16, 2024 at 12:56 AM
Feature request: Filter feed by LLM instead of keywords!
I want to be able to say things like "No politics". Or "Research papers on multi-modal models".
I find it crazy that most platforms don't let you control your feed besides through behavior (likes/mutes), let alone use AI to do so.
I want to be able to say things like "No politics". Or "Research papers on multi-modal models".
I find it crazy that most platforms don't let you control your feed besides through behavior (likes/mutes), let alone use AI to do so.