Maximilian Igl (@maxiigl) 's Twitter Profile
Maximilian Igl

@maxiigl

RS at Nvidia focussing on autonomous vehicles. Former Oxford PhD, MSR, Deepmind and Waymo. Opinions my own and do not represent those of my employer, Nvidia.

ID: 89467149

linkhttp://maximilianigl.com calendar_today12-11-2009 15:18:56

262 Tweet

2,2K Takipçi

447 Takip Edilen

Marco Pavone (@drmapavone) 's Twitter Profile Photo

Introducing DreamDrive, which combines the complementary strengths of generative AI (video diffusion) and neural reconstruction (Gaussian splatting) to transform any street-view image into a dynamic 4D driving scene! Web: pointscoder.github.io/DreamDrive/ Paper: arxiv.org/abs/2501.00601

Introducing DreamDrive, which combines the complementary strengths of generative AI (video diffusion) and neural reconstruction (Gaussian splatting) to transform any street-view image into a dynamic 4D driving scene!

Web: pointscoder.github.io/DreamDrive/
Paper: arxiv.org/abs/2501.00601
Marco Pavone (@drmapavone) 's Twitter Profile Photo

Complementing DreamDrive, I am thrilled to introduce STORM, which enables fast scene reconstruction with a single feed-forward model. STORM transforms camera logs into dynamic 3D models - in real time! Web: jiawei-yang.github.io/STORM/ Paper: arxiv.org/abs/2501.00602

Complementing DreamDrive, I am thrilled to introduce STORM, which enables fast scene reconstruction with a single feed-forward model.

STORM transforms camera logs into dynamic 3D models - in real time!

Web: jiawei-yang.github.io/STORM/
Paper: arxiv.org/abs/2501.00602
Marco Pavone (@drmapavone) 's Twitter Profile Photo

For the first time ever, NVIDIA is hosting an AV Safety Day at GTC - a multi-session workshop on AV safety. We will share our latest work on safe AV platforms, run-time monitoring, safety data flywheels, and more! #AutonomousVehicles #AI at #GTC25 ➡️ nvda.ws/3Xc3xPo

Boris Ivanovic (@iamborisi) 's Twitter Profile Photo

Don’t miss this deep dive into the future of autonomous vehicles! Excited to present about how foundation models are transforming AV technology with Jose M. Alvarez at #GTC25! Check out all the session details below 👇

Maximilian Igl (@maxiigl) 's Twitter Profile Photo

I hate how reading something nowadays (including reviews, unfortunately...) now starts with estimating the probability it's AI written and hence worthless.

Boris Ivanovic (@iamborisi) 's Twitter Profile Photo

Happy to share our latest work on efficient sensor tokenization for end-to-end driving architectures! arxiv.org/abs/2506.12251 We introduce a novel way to tokenize multi-camera input for AV Transformers that is resolution- and camera-count-agnostic, yet geometry-aware 🧵👇

Minqi Jiang (@minqijiang) 's Twitter Profile Photo

Recently, there has been a lot of talk of LLM agents automating ML research itself. If Llama 5 can create Llama 6, then surely the singularity is just around the corner. How can we get a pulse check on whether current LLMs are capable of driving this kind of total

Recently, there has been a lot of talk of LLM agents automating ML research itself. If Llama 5 can create Llama 6, then surely the singularity is just around the corner. 

How can we get a pulse check on whether current LLMs are capable of driving this kind of total
Marco Pavone (@drmapavone) 's Twitter Profile Photo

Can we use simulation to validate Physical AI? Yes—with far fewer real-world tests. We propose a control variates–based estimation framework that pairs sim & real data to dramatically cut validation costs. #AI #Robotics #Sim2Real" Paper: arxiv.org/pdf/2506.20553 NVIDIA DRIVE