Bernhard Jaeger
@bernhard-jaeger.bsky.social
๐ค 484
๐ฅ 178
๐ 89
PhD student with Andreas Geiger and IMPRS-IS. Studying embodied intelligence via autonomous driving.
pinned post!
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
9 months ago
0
25
15
reposted by
Bernhard Jaeger
Daphne Cornelisse
10 days ago
What if you could train agents on a ๐ฑ๐ฒ๐ฐ๐ฎ๐ฑ๐ฒ of driving experience in ๐๐ป๐ฑ๐ฒ๐ฟ ๐ฎ๐ป ๐ต๐ผ๐๐ฟ, on a single GPU? Excited to share ๐๐ช๐๐๐๐ง๐ฟ๐ง๐๐ซ๐ 2.0: A fast, friendly driving simulator with RL training via PufferLib at ๐ฏ๐ฌ๐ฌ๐ ๐๐๐ฒ๐ฝ๐/๐๐ฒ๐ฐ ๐ก + ๐
youtu.be/LfQ324R-cbE?...
loading . . .
PufferDrive 2.0 release
YouTube video by Daphne Cornelisse
https://youtu.be/LfQ324R-cbE?si=hn_A1w67zEOHv3g_
2
50
11
Our new E2E driving method, TransFuser v6, is out on ArXiv. It outperforms all other methods on CARLA by a wide margin, 95 DS on Bench2Drive! We show that minimizing the asymmetry between data annotator and policy is key for strong IL results. Code, models, and paper:
ln2697.github.io/lead/
loading . . .
14 days ago
0
29
7
reposted by
Bernhard Jaeger
Alexander Berger
21 days ago
Our staff's 2025 recommendations for individual donors, fresh off the press:
coefficientgiving.org/research/su...
loading . . .
Suggestions for Individual Donors from Coefficient Giving Staff โ 2025 | Coefficient Giving
The 2025 edition of our annual tradition: a list of giving opportunities suggested by Coefficient Giving program staff.
https://coefficientgiving.org/research/suggestions-for-individual-donors-from-coefficient-giving-staff-2025/
0
2
3
reposted by
Bernhard Jaeger
Nikolai Slavov
23 days ago
This article is from people who have thought about FROs for years and have experience with what works and what doesn't. I have always appreciated the restraint in defining the niche of FROs in the broader ecosystem; it comes out clearly in this piece.
www.essentialtechnology.blog/p/the-future...
loading . . .
The Future of Focused Research Organizations:
Working with Convergent on the NSF Tech Labs Initiative
https://www.essentialtechnology.blog/p/the-future-of-focused-research-organizations
0
3
3
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
26 days ago
Unfortunately it appears much of the academic community has reconstituted itself on LinkedIn
11
59
10
reposted by
Bernhard Jaeger
Andreas Geiger
29 days ago
I am so happy and excited that this project got funded!
add a skeleton here at some point
4
28
3
reposted by
Bernhard Jaeger
Tรผbingen AI Center
29 days ago
More details at
tuebingen.ai/news/ai-powe...
loading . . .
AI-powered assistants for scientific discovery
Andreas Geiger receives ERC Consolidator Grant
https://tuebingen.ai/news/ai-powered-assistants-for-scientific-discovery
0
8
2
Speaking of RL, Nvidia also just published a survey on the importance of closed-loop training (RL, etc.) in E2E driving.
research.nvidia.com/publication/...
loading . . .
Beyond Behavior Cloning in Autonomous Driving: a Survey of Closed-Loop Training Techniques | Research
Behavior cloning, the dominant approach for training autonomous vehicle (AV) policies, suffers from a fundamental gap: policies trained open-loop on temporally independent samples must operate in clos...
https://research.nvidia.com/publication/2025-12_beyond-behavior-cloning-autonomous-driving-survey-closed-loop-training
about 1 month ago
1
9
2
waymo.com/blog/2025/12...
Waymo is training End-to-End driving models with RL in simulation.
loading . . .
Demonstrably Safe AI For Autonomous Driving
Autonomous driving is the ultimate challenge for AI in the physical world. At Waymo, weโre solving it by prioritizing demonstrably safe AI, where safety is central to how we engineer our models and AI...
https://waymo.com/blog/2025/12/demonstrably-safe-ai-for-autonomous-driving
about 1 month ago
2
24
8
reposted by
Bernhard Jaeger
Andrei Bursuc
about 1 month ago
Tired Europe: Let's do tons of AI regulations Wired Europe: Let's do tons of AI open source
#aiPULSE2025
0
10
1
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
about 1 month ago
This essay, roughly on dual use, has been haunting me for a while now:
dl.acm.org/doi/pdf/10.1...
3
28
3
reposted by
Bernhard Jaeger
Mila Gorecki
about 1 month ago
Excited to be at
#Neurips2025
this week to present our paper "Monoculture or Multiplicity: Which is it?", joint work with Moritz Hardt. ๐ Paper #1000:
openreview.net/pdf?id=DO5Lt...
๐ Wed, Dec 3, 2025 โข 4:30 PM โ 7:30 PM Feel free to come by and reach out! A short ๐งต.
1
16
4
reposted by
Bernhard Jaeger
Andreas Geiger
about 1 month ago
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...
0
34
12
Scholar Inbox for NeurIPS is live now.
add a skeleton here at some point
about 1 month ago
0
14
7
www.nature.com/articles/d41...
ArXiv banned surveys due to AI slop spam. Now we need to wait for them to be peer-reviewed. Bad development, we need to find better solutions to AI slop than banning unreviewed papers. Getting a survey reviewed at a good journal can take over a year. :(
loading . . .
Preprint site arXiv is banning computer-science reviews: hereโs why
The repository is taking steps to tackle a surge in low quality, AI-generated content.
https://www.nature.com/articles/d41586-025-03664-7
about 1 month ago
0
0
0
reposted by
Bernhard Jaeger
Wenzel Jakob
about 1 month ago
Quick reminder about the EPFL PhD program deadline (EDIC) on Dec 15.
add a skeleton here at some point
0
4
2
reposted by
Bernhard Jaeger
Paul Vicol
about 1 month ago
๐ Introducing TMLR Beyond PDF! ๐ฌ This is a new, HTML-based submission format for TMLR, that supports interactive figures and videos, along with the usual LaTeX and images. ๐ Thanks to TMLR Editors in Chief: Hugo Larochelle,
@gautamkamath.com
, Naila Murray, Nihar B. Shah, and Laurent Charlin!
loading . . .
1
75
25
reposted by
Bernhard Jaeger
Convergent Research
about 2 months ago
Congratulations to
@cworthy.org
on their announcement today! Learn more about this wonderful FRO here:
www.youtube.com/watch?v=DA-e...
add a skeleton here at some point
0
4
1
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
about 2 months ago
Come be our colleague in the robotics and embodied intelligence center at NYU! ๐ท Professor in Robotics / Embodied AI (Open Rank)
apply.interfolio.com/176977
๐ท Faculty Fellow in Robotics / Embodied AI
apply.interfolio.com/177077
loading . . .
Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio
https://apply.interfolio.com/176977
1
20
6
reposted by
Bernhard Jaeger
Andreas Geiger
about 2 months ago
๐ 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/
0
14
4
New SOTA in imitation learning (IL) for planning in CARLA, and an in-depth analysis of all the overfitting that is going on with IL policies.
arxiv.org/abs/2511.07292
about 2 months ago
1
6
1
Bench2Drive has become a popular autonomous driving benchmark with over 40 methods. Papers only report a few baselines due to space constraints, making it hard to keep an overview. To fix this, we made a leaderboard that contains every published result:
github.com/autonomousvi...
loading . . .
GitHub - autonomousvision/Bench2Drive-Leaderboard: Bench2Drive Leaderboard
Bench2Drive Leaderboard. Contribute to autonomousvision/Bench2Drive-Leaderboard development by creating an account on GitHub.
https://github.com/autonomousvision/Bench2Drive-Leaderboard
about 2 months ago
0
7
1
reposted by
Bernhard Jaeger
Tรผbingen AI Center
2 months ago
๐ฃ JobAlert: 12 days left, hit the Apply button now: Join Tรผbingen AI Center as a Scientific Project Coordinator for OpenEuroLLM - support, building a series of open-source foundation models for transparent AI in Europe! ๐
lnkd.in/eTptRaFy
๐ Deadline: November 19, 2025
@unituebingen.bsky.social
0
2
2
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
2 months ago
Personally I would not want to be in the camp of arguing that we simply *must* have 40k vehicular deaths a year. Status quo bias is an insane drug
3
44
1
reposted by
Bernhard Jaeger
Ulrike Luxburg
2 months ago
Here is a formal impossibility result for XAI: Informative Post-Hoc Explanations Only Exist for Simple Functions. I'll give an online presentation about this work next tuesday in
@timvanerven.nl
's Theory of Interpretable AI Seminar:
arxiv.org/abs/2508.11441
tverven.github.io/tiai-seminar/
0
15
5
reposted by
Bernhard Jaeger
Kashyap Chitta
2 months ago
Launching the Physical AI AV Dataset! ๐
huggingface.co/datasets/nvi...
One of the largest, most diverse & commercially usable open-source datasets for AVs. - 1727 hours of driving data - Camera, LiDAR, & radar - 25 countries, 2500+ cities This is just the beginning, more features to come!
loading . . .
0
28
7
Big day for autonomous driving research. Nvidia just dropped 1700 hours of public driving data on HuggingFace from over 2500 cities:
huggingface.co/datasets/nvi...
loading . . .
https://huggingface.co/datasets/nvidi
2 months ago
1
16
4
reposted by
Bernhard Jaeger
Andreas Geiger
3 months ago
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
loading . . .
Takeru Miyato - AI Research Scientist
PhD student at University of Tรผbingen working on artificial intelligence, machine learning, and deep learning research.
https://takerum.github.io/
0
29
4
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
3 months ago
I now understand the position of the YOLO author a lot better than I did before
1
10
1
reposted by
Bernhard Jaeger
Yiyi Liao
3 months ago
๐ Join us for the RealADSim Workshop @ ICCV 2025! ๐ Oct 19 morning | ๐ Hawaii Conv. Center, 305A Featuring exciting talks and winner presentations from our challenges (70+ regs, ~30 subs). Donโt miss it! ๐
#ICCV2025
add a skeleton here at some point
0
7
4
reposted by
Bernhard Jaeger
Haofei Xu
3 months ago
๐Excited 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/
loading . . .
1
10
3
reposted by
Bernhard Jaeger
Andreas Geiger
3 months ago
Personal programs for ICCV 2025 are now available at:
www.scholar-inbox.com/conference/i...
0
24
7
Just published the CaRL v1.1 release on GitHub. Lots of software engineering improvements, including more stable code, better determinism, and lower RAM and CPU requirements. This allowed me to double # envs. The resulting model gained a nice +9 DS boost.
github.com/autonomousvi...
3 months ago
0
5
0
reposted by
Bernhard Jaeger
Serge Belongie
3 months ago
@belongielab.org
welcomes applications for a PhD position in CV/ML (fine-grained analysis of multimodal data, 2D/3D generative models, misinformation detection, self-supervised learning) / Apply though the ELLIS portal / Deadline 31-Oct-2025
add a skeleton here at some point
0
23
9
reposted by
Bernhard Jaeger
Eugene Vinitsky ๐
3 months ago
We're finally out of stealth:
percepta.ai
We're a research / engineering team working together in industries like health and logistics to ship ML tools that drastically improve productivity. If you're interested in ML and RL work that matters, come join us ๐
loading . . .
Percepta | A General Catalyst Transformation Company
Transforming critical institutions using applied AI. Let's harness the frontier.
https://percepta.ai
7
118
20
I am attending CoRL 2025 in Seoul. DM me if you are too and want to chat.
3 months ago
0
1
0
reposted by
Bernhard Jaeger
Kashyap Chitta
4 months ago
We're recruiting our next batch of interns. Come join the team!
nvidia.wd5.myworkdayjobs.com/en-US/NVIDIA...
loading . . .
NVIDIA 2026 Internships: PhD Autonomous Vehicles Research - US
By submitting your resume, youโre expressing interest in one of our 2026 Autonomous Vehicles focused Research Internships. Weโll review resumes on an ongoing basis, and a recruiter may reach out if yo...
https://nvidia.wd5.myworkdayjobs.com/en-US/NVIDIAExternalCareerSite/job/US-CA-Santa-Clara/NVIDIA-2026-Internships--PhD-Autonomous-Vehicles-Research_JR2003244
0
6
1
IMPRS-IS is recruiting another round of PhD students this year. If you are looking for a PhD position in machine learning or robotics in Germany, this is the best program to apply to.
imprs.is.mpg.de/application
4 months ago
0
3
0
thinkingmachines.ai/blog/defeati...
Blog post about determinism in LLMs. They make a very interesting point at the end about how the numerical differences between data collection and training forward passes can make an RL algorithm lose its On-policy property.
4 months ago
0
1
0
Curious: Has an LLM ever replied with "I don't know." or equivalent to a question you asked?
4 months ago
0
0
0
Civil software licenses are a useful tool for those who decide that they don't want their research software be used in dual use applications: civil-software-licenses.github.io
add a skeleton here at some point
4 months ago
0
0
0
reposted by
Bernhard Jaeger
Andreas Geiger
4 months ago
ellis.eu/news/ellis-p...
loading . . .
ELLIS PhD Program: Call for Applications 2025
The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...
https://ellis.eu/news/ellis-phd-program-call-for-applications-2025
0
17
9
reposted by
Bernhard Jaeger
Kashyap Chitta
4 months ago
Announcing the
@iccv.bsky.social
NAVSIM Challenge! What's new? We're testing not only on real recordings, but also perturbed futures generated from the real ones via pseudo-simulation! $8K in prizes + several $1.5k travel grants. Submit by September 20!
opendrivelab.com/challenge2025/
๐งต๐
1
14
10
reposted by
Bernhard Jaeger
Katrin Renz
5 months ago
After finishing my papers for my PhD, I spent some time exploring new directions. I ended up working on Diffusion Language Models with
@haoyuhe.bsky.social
(he made it work ๐),
@yongcao.bsky.social
,
@andreasgeiger.bsky.social
. I learned a lot of new things and I am very excited about the results. ๐ฅณ
add a skeleton here at some point
0
5
1
reposted by
Bernhard Jaeger
5 months ago
๐ Introducing our new paper, MDPO: Overcoming the Training-Inference Divide of Masked Diffusion Language Models. ๐ Paper:
www.scholar-inbox.com/papers/He202...
arxiv.org/pdf/2508.13148
๐ป Code:
github.com/autonomousvi...
๐ Project Page:
cli212.github.io/MDPO/
1
12
10
reposted by
Bernhard Jaeger
Max Seitzer
5 months ago
Introducing DINOv3 ๐ฆ๐ฆ๐ฆ A SotA-enabling vision foundation model, trained with pure self-supervised learning (SSL) at scale. High quality dense features, combining unprecedented semantic and geometric scene understanding. Three reasons why this matters๐
2
25
10
reposted by
Bernhard Jaeger
Abby Stylianou
5 months ago
I have found ACing for NeurIPS this year a miserable experience and I've been struggling to articulate why without basically whining about it being too much work (although.....true. My god the amount of words I'm reading...). But I think I've figured out part of my dislike for this process.
2
41
7
reposted by
Bernhard Jaeger
Convergent Research
5 months ago
How can we identify what capabilities will matter most in an increasingly intelligence-saturated world? 1. Avoid fast obsolescence 2. Complement AI 3. Use the steering wheel, not just the pedals 4. Imagine good futures + our AI-inflected priorities across 7 fields.
loading . . .
Prioritizing Fundamental Capabilities for the Intelligence Age
What science & technology should we steer towards?
https://convergentresearch.substack.com/p/prioritizing-fundamental-capabilities
0
2
1
Our paper "CaRL: Learning Scalable Planning Policies with Simple Rewards" has been accepted to the Conference on Robot Learning (CoRL 2025). See you in Seoul at the end of September. Code & Paper:
github.com/autonomousvi...
loading . . .
GitHub - autonomousvision/CaRL: [CoRL 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards
[CoRL 2025] CaRL: Learning Scalable Planning Policies with Simple Rewards - autonomousvision/CaRL
https://github.com/autonomousvision/CaRL
5 months ago
0
3
1
reposted by
Bernhard Jaeger
Wenzel Jakob
5 months ago
My lab will be recruiting at all levels. PhD students, postdocs, and a research engineering position (worldwide for PhD/postdoc, EU candidates only for the engineering position). If you're at SIGGRAPH, I'd love to talk to you if you are interested in any of these.
0
12
8
Load more
feeds!
log in