Andreas Geiger
@andreasgeiger.bsky.social
Professor, University of Tübingen @unituebingen.bsky.social.
Head of Department of Computer Science 🎓.
Faculty, Tübingen AI Center 🇩🇪 @tuebingen-ai.bsky.social.
ELLIS Fellow, Founding Board Member 🇪🇺 @ellis.eu.
CV 📷, ML 🧠, Self-Driving 🚗, NLP 🖺
Head of Department of Computer Science 🎓.
Faculty, Tübingen AI Center 🇩🇪 @tuebingen-ai.bsky.social.
ELLIS Fellow, Founding Board Member 🇪🇺 @ellis.eu.
CV 📷, ML 🧠, Self-Driving 🚗, NLP 🖺
Reposted by Andreas Geiger
EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis
Sheng Miao, Sijin Li, Pan Wang, Dongfeng Bai, Bingbing Liu, Yue Wang, @andreasgeiger.bsky.social, @yiyiliao.bsky.social
tl;dr: EVolSplat journal version->dynamic scene
arxiv.org/abs/2601.15951
Sheng Miao, Sijin Li, Pan Wang, Dongfeng Bai, Bingbing Liu, Yue Wang, @andreasgeiger.bsky.social, @yiyiliao.bsky.social
tl;dr: EVolSplat journal version->dynamic scene
arxiv.org/abs/2601.15951
January 23, 2026 at 11:52 AM
EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis
Sheng Miao, Sijin Li, Pan Wang, Dongfeng Bai, Bingbing Liu, Yue Wang, @andreasgeiger.bsky.social, @yiyiliao.bsky.social
tl;dr: EVolSplat journal version->dynamic scene
arxiv.org/abs/2601.15951
Sheng Miao, Sijin Li, Pan Wang, Dongfeng Bai, Bingbing Liu, Yue Wang, @andreasgeiger.bsky.social, @yiyiliao.bsky.social
tl;dr: EVolSplat journal version->dynamic scene
arxiv.org/abs/2601.15951
I am so happy and excited that this project got funded!
We are so proud of our faculty member @andreasgeiger.bsky.social for securing an ERC Consolidator Grant! With CASIDO, his team will design human-centric AI assistants to support researchers in the face of ever more rapid scientific progress.
@unituebingen.bsky.social @ml4science.bsky.social
@unituebingen.bsky.social @ml4science.bsky.social
December 11, 2025 at 6:52 PM
I am so happy and excited that this project got funded!
Reposted by Andreas Geiger
Scholar Inbox in conference mode is soooo useful. Get your poster session recommendations with the poster number and access the paper....
Thanks @andreasgeiger.bsky.social and team!
Thanks @andreasgeiger.bsky.social and team!
December 3, 2025 at 8:41 PM
Scholar Inbox in conference mode is soooo useful. Get your poster session recommendations with the poster number and access the paper....
Thanks @andreasgeiger.bsky.social and team!
Thanks @andreasgeiger.bsky.social and team!
Attending #Neurips2025? Get your personalized Scholar Inbox conference program now to easily navigate the poster sessions and find what you are looking for:
www.scholar-inbox.com/conference/n...
www.scholar-inbox.com/conference/n...
December 2, 2025 at 6:37 AM
Attending #Neurips2025? Get your personalized Scholar Inbox conference program now to easily navigate the poster sessions and find what you are looking for:
www.scholar-inbox.com/conference/n...
www.scholar-inbox.com/conference/n...
🚀 New paper: ConeGS Error-Guided Densification Using Pixel Cones. We improve 3D Gaussian Splatting by placing Gaussians where they matter most: ConeGS adds primitives along pixel-view cones guided by image error, boosting quality with fewer Gaussians. baranowskibrt.github.io/conegs/
November 12, 2025 at 10:50 AM
🚀 New paper: ConeGS Error-Guided Densification Using Pixel Cones. We improve 3D Gaussian Splatting by placing Gaussians where they matter most: ConeGS adds primitives along pixel-view cones guided by image error, boosting quality with fewer Gaussians. baranowskibrt.github.io/conegs/
Congratulations to our PhD student @takerumiyato.bsky.social for winning the Google PhD Fellowship in the category "Machine Learning and ML Foundations". Takeru is pioneering new neural architectures that improve generalization and efficiency. Check out his research: takerum.github.io
Takeru Miyato - AI Research Scientist
PhD student at University of Tübingen working on artificial intelligence, machine learning, and deep learning research.
takerum.github.io
October 24, 2025 at 7:37 AM
Congratulations to our PhD student @takerumiyato.bsky.social for winning the Google PhD Fellowship in the category "Machine Learning and ML Foundations". Takeru is pioneering new neural architectures that improve generalization and efficiency. Check out his research: takerum.github.io
Reposted by Andreas Geiger
🚀Excited to share our recent work on test-time scaling for feed-forward Gaussian splatting:
we learn a recurrent model ReSplat that is able to iteratively improve the reconstruction quality in a feed-forward manner!
haofeixu.github.io/resplat/
we learn a recurrent model ReSplat that is able to iteratively improve the reconstruction quality in a feed-forward manner!
haofeixu.github.io/resplat/
October 10, 2025 at 8:12 PM
🚀Excited to share our recent work on test-time scaling for feed-forward Gaussian splatting:
we learn a recurrent model ReSplat that is able to iteratively improve the reconstruction quality in a feed-forward manner!
haofeixu.github.io/resplat/
we learn a recurrent model ReSplat that is able to iteratively improve the reconstruction quality in a feed-forward manner!
haofeixu.github.io/resplat/
Personal programs for ICCV 2025 are now available at:
www.scholar-inbox.com/conference/i...
www.scholar-inbox.com/conference/i...
October 10, 2025 at 6:19 AM
Personal programs for ICCV 2025 are now available at:
www.scholar-inbox.com/conference/i...
www.scholar-inbox.com/conference/i...
#TTT3R: 3D Reconstruction as Test-Time Training
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!
October 1, 2025 at 6:35 AM
#TTT3R: 3D Reconstruction as Test-Time Training
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!
TTT3R offers a simple state update rule to enhance length generalization for #CUT3R — No fine-tuning required!
🔗Page: rover-xingyu.github.io/TTT3R
We rebuilt @taylorswift13’s "22" live at the 2013 Billboard Music Awards - in 3D!
Excited about this new work from @haoyuhe.bsky.social. TLDR: Diffusion language models treat learning and inference differently which lowers performance. RL can be used to overcome this issue for certain problems.
🚀 Introducing our new paper, MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models.
📄 Paper: www.scholar-inbox.com/papers/He202...
arxiv.org/pdf/2508.13148
💻 Code: github.com/autonomousvi...
🌐 Project Page: cli212.github.io/MDPO/
📄 Paper: www.scholar-inbox.com/papers/He202...
arxiv.org/pdf/2508.13148
💻 Code: github.com/autonomousvi...
🌐 Project Page: cli212.github.io/MDPO/
August 20, 2025 at 8:25 PM
Excited about this new work from @haoyuhe.bsky.social. TLDR: Diffusion language models treat learning and inference differently which lowers performance. RL can be used to overcome this issue for certain problems.
Reposted by Andreas Geiger
One concern that I have as an AI researcher when publishing code is that it can potentially be used in dual-use applications.
To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose:
civil-software-licenses.github.io
To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose:
civil-software-licenses.github.io
Civil Software Licenses
civil-software-licenses.github.io
July 31, 2025 at 5:36 PM
One concern that I have as an AI researcher when publishing code is that it can potentially be used in dual-use applications.
To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose:
civil-software-licenses.github.io
To solve this, we propose Civil Software Licenses. They prevent dual-use while being minimal in the restrictions they impose:
civil-software-licenses.github.io
Scholar Inbox @ ACL 25! @aclmeeting.bsky.social
July 28, 2025 at 8:19 AM
Scholar Inbox @ ACL 25! @aclmeeting.bsky.social
Meme credit: @markusflicke.bsky.social
July 27, 2025 at 6:01 AM
Meme credit: @markusflicke.bsky.social
You might also want to try out www.scholar-inbox.com :)
July 27, 2025 at 5:28 AM
You might also want to try out www.scholar-inbox.com :)
We are excited that Scholar Inbox is supporting ACL 2025
@aclmeeting.bsky.social with personalized conference programs this year for the first time!
www.scholar-inbox.com/conference/a...
It would be great if you could widely share this news within the NLP community. See you next week in Vienna!
@aclmeeting.bsky.social with personalized conference programs this year for the first time!
www.scholar-inbox.com/conference/a...
It would be great if you could widely share this news within the NLP community. See you next week in Vienna!
July 24, 2025 at 9:06 AM
We are excited that Scholar Inbox is supporting ACL 2025
@aclmeeting.bsky.social with personalized conference programs this year for the first time!
www.scholar-inbox.com/conference/a...
It would be great if you could widely share this news within the NLP community. See you next week in Vienna!
@aclmeeting.bsky.social with personalized conference programs this year for the first time!
www.scholar-inbox.com/conference/a...
It would be great if you could widely share this news within the NLP community. See you next week in Vienna!
Last team member moving to the new office!
July 22, 2025 at 5:40 PM
Last team member moving to the new office!
Do people still do sth else?
July 22, 2025 at 4:35 AM
Do people still do sth else?
Today, we moved into our new building on the CyberValley campus. Everyone is super excited. PhD students went right back to work. But wait, is there something missing? ;)
July 21, 2025 at 7:07 PM
Today, we moved into our new building on the CyberValley campus. Everyone is super excited. PhD students went right back to work. But wait, is there something missing? ;)
Today we had our AVG Deep Cave Expedition Day! Exploring the challenges of the (unlit, narrow, crawling-only) Hofener Höhle near Grabenstetten ..
July 18, 2025 at 3:48 PM
Today we had our AVG Deep Cave Expedition Day! Exploring the challenges of the (unlit, narrow, crawling-only) Hofener Höhle near Grabenstetten ..
Actually, this helped. We will collaborate with ACL to host personal programs for the first time for an NLP conference this year!
July 16, 2025 at 8:37 AM
Actually, this helped. We will collaborate with ACL to host personal programs for the first time for an NLP conference this year!
A big milestone for us. Huge congrats to Bernhard, Daniel and team! The first comprehensive codebase for training RL self-driving agents with state-of-the-art performance on both CARLA 2.0 and nuPlan.
We have released the code for our work, CaRL: Learning Scalable Planning Policies with Simple Rewards.
The repository contains the first public code base for training RL agents with the CARLA leaderboard 2.0 and nuPlan.
github.com/autonomousvi...
The repository contains the first public code base for training RL agents with the CARLA leaderboard 2.0 and nuPlan.
github.com/autonomousvi...
GitHub - autonomousvision/CaRL: [ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards
[ArXiv 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards - autonomousvision/CaRL
github.com
July 15, 2025 at 7:07 PM
A big milestone for us. Huge congrats to Bernhard, Daniel and team! The first comprehensive codebase for training RL self-driving agents with state-of-the-art performance on both CARLA 2.0 and nuPlan.
We tried to contact the ACL PCs a few times, but unfortunately we were not very successful so far. It's my first ACL I will attend in person, so I was hoping I would be able to profit from our planner - let's see :)
July 15, 2025 at 11:35 AM
We tried to contact the ACL PCs a few times, but unfortunately we were not very successful so far. It's my first ACL I will attend in person, so I was hoping I would be able to profit from our planner - let's see :)
In case you find it as relaxing as we do: Here is a 2h+ video of our autonomous RL driving agent CaRL in action! @danieldauner.bsky.social @bernhard-jaeger.bsky.social @kashyap7x.bsky.social
youtube.com/watch?v=_god...
youtube.com/watch?v=_god...
CaRL: Learning Scalable Planning Policies with Simple Rewards
YouTube video by Daniel Dauner
youtube.com
July 15, 2025 at 6:17 AM
In case you find it as relaxing as we do: Here is a 2h+ video of our autonomous RL driving agent CaRL in action! @danieldauner.bsky.social @bernhard-jaeger.bsky.social @kashyap7x.bsky.social
youtube.com/watch?v=_god...
youtube.com/watch?v=_god...