Andreas Geiger

@weijiewang.bsky.social, Qihang Cao, Sensen Gao, @donydchen.bsky.social, @haofeixu.bsky.social, @wenjingbian.bsky.social, @songyoupeng.bsky.social, Tat-Jen Cham, @chuanxiaz.bsky.social, @andreasgeiger.bsky.social, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang Author's thread: bsky.app/profile/weij...

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

I am so happy and excited that this project got funded!

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!

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...

🚀 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

🚀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/

Personal programs for ICCV 2025 are now available at: 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!

ellis.eu/news/ellis-p...

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.

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

Scholar Inbox @ ACL 25! @aclmeeting.bsky.social

Meme credit: @markusflicke.bsky.social

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!

Last team member moving to the new office!

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 ..

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.

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...

Thanks for being our #1 ambassador, Claire! Enjoy ICML!

Yesterday, the founding team behind scholar-inbox.com took home the Audience Award 🏆 and the Best Business Model Award 🏆! Philipp Hühn and @markusflicke.bsky.social impressed everyone with a clear and engaging pitch of their smart recommender tool for academic papers.

Attending ICML 25 @icmlconf.bsky.social next week? Check out your personalized conference program at to know where to stop: www.scholar-inbox.com/conference/i...

I am very proud of my group! These are the nationalities of my current and past team members. Diversity is key. 🇩🇪 🇬🇷 🇮🇹 🇮🇳 🇷🇺 🇺🇦 🇨🇳 🇷🇸 🇯🇵 🇧🇪 🇺🇸 🇰🇷 🇹🇷

Last day of our AVG Summer retreat 2025 in Balderschwang! Many talks and for the first time 2 panel discussions and a PhD life hack session. And of course some sports,games,swimming and lots of fun..

Join us for our RealADSim Challenge! Closed-loop Driving in a 3DGS-based Simulator .. how cool is that? ;)

Scholar Inbox is featured on the ML for Science blog!

Christina's new work PrITTI generates high-quality, controllable 3D semantic urban scenes in a compact primitive-based representation using a latent diffusion model. This enables applications like scene editing, inpainting, and photo-realistic street view synthesis! raniatze.github.io/pritti/

Very happy that finally - after ~2 years of review - PanopticNERF-360 has been accepted to TPAMI :) Panoramic 3D-to-2D Label Transfer in Urban Scenes. Kudos to the team and Yiyi Liao for leading the effort. Here is the project page: fuxiao0719.github.io/projects/pan...

The 2025 Waymo Challenge results are out! We achieved second place in the End-to-End Driving Challenge with DiffusionLTF and third place in the Scenario Generation Challenge with SHRED. Our approaches prioritized simplicity, and we're preparing to make them publicly available soon.

Hooray! Shaofei's "Relightable Full-body Gaussian Codec Avatars" work neuralbodies.github.io/RFGCA/ is featured in this years SIGGRAPH 2025 Technical Papers Trailer! @acmsiggraph.bsky.social: www.youtube.com/watch?v=HfHC...

How can we reliably simulate future driving scenarios under a wide range of ego driving behaviors? Check out: ReSim: Reliable World Simulation for Autonomous Driving resim-world-model.github.io

Excited to present our #CVPR2025 paper DepthSplat next week! DepthSplat is a feed-forward model that achieves high-quality Gaussian reconstruction and view synthesis in just 0.6 seconds. Looking forward to great conversations at the conference!

🚗 Pseudo-simulation combines the efficiency of open-loop and robustness of closed-loop evaluation. It uses real data + 3D Gaussian Splatting synthetic views to assess error recovery, achieving strong correlation with closed-loop simulations while requiring 6x less compute. arxiv.org/abs/2506.04218

Your personalized CVPR 25 @cvprconference.bsky.social conference programs are now available for you! www.scholar-inbox.com/conference/c...

While we mostly like to get rid of the steering wheel, sometimes we still need one. @bernhard-jaeger.bsky.social posting for a press release about his grant..

Many thanks to the Vector Stiftung vector-stiftung.de for funding our research on efficient scaling of reinforcement learning as part of their MINT innovation program! And big congratulations to @bernhard-jaeger.bsky.social for this success!

Congratulations to Dr. Stefan Baur for defending his PhD work on self-supervised Lidar scene flow, motion segmentation and object detection! baurst.github.io

📣 Excited to share our #CVPR2025 Spotlight paper and my internship project @wayve: SimLingo. A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities. Code: github.com/RenzKa/simli... Paper: arxiv.org/abs/2503.09594

📢 New paper CVPR 25! Can meshes capture fuzzy geometry? Volumetric Surfaces uses adaptive textured shells to model hair, fur without the splatting / volume overhead. It’s fast, looks great, and runs in real time even on budget phones. 🔗 autonomousvision.github.io/volsurfs/ 📄 arxiv.org/pdf/2409.02482

📣 New #CVPR25 Paper: UrbanCAD builds photorealistic and highly controllable hybrid digital twins from a single urban image and a large collection of 3D CAD models, supporting various editing operations. xdimlab.github.io/UrbanCAD/

🚗🌆 We introduce EVolSplat — a feed-forward 3D Gaussian Splatting model that enables real-time, photorealistic rendering without per-scene optimization. Trained on KITTI-360 & Waymo, it sets a new SOTA for autonomous driving applications. #CVPR25. Paper & Code: xdimlab.github.io/EVolSplat/

Introducing CaRL: Learning Scalable Planning Policies with Simple Rewards We show how simple rewards enable scaling up PPO for planning. CaRL outperforms all prior learning-based approaches on nuPlan Val14 and CARLA longest6 v2, using less inference compute. arxiv.org/abs/2504.17838

⏰ Heads up! The deadline for two #CVPR2025 Autonomous Grand Challenge tracks is May 10th, 2025: 1️⃣ NAVSIM v2 Challenge: huggingface.co/spaces/AGC20... 2️⃣ World Model Challenge by 1X: huggingface.co/spaces/1x-te...

🔥 Prometheus: 3D-Aware Latent Diffusion for Feed-Forward Text-to-3D Scene Generation. Allows object- and scene-level generation from text in seconds. freemty.github.io/project-prom...