Driving on Registers: DrivoR for lean, adaptive end-to-end driving

Kari Jaaskelainen

10 Jan 2026 — 1 min read

Meet DrivoR, a simple, efficient transformer for end-to-end autonomous driving.

It builds on pretrained Vision Transformers and adds camera-aware "register tokens" that compress multi-camera views into a compact scene summary, cutting downstream compute without sacrificing accuracy.

DrivoR then runs two lightweight decoders: one to propose driving paths, and one to score them by mimicking an oracle, with interpretable sub-scores you can tune at inference:

Safety
Comfort
Efficiency

Despite its minimal design, DrivoR matches or beats strong baselines on NAVSIM-v1, NAVSIM-v2, and the photorealistic, closed-loop HUGSIM benchmark.

Takeaway: a pure-transformer stack plus targeted token compression can deliver accurate, efficient, and behavior-adaptive end-to-end driving. Paper: https://arxiv.org/abs/2601.05083v1. Code and checkpoints will be released on the project page.

Paper: https://arxiv.org/abs/2601.05083v1

Register: https://www.AiFeta.com

#AutonomousDriving #AI #ComputerVision #Transformers #Robotics #Safety #Efficiency

Meet GRACE: a moral governor for safer, more transparent AI

AI agents are getting powerful—so how do we make sure they do the right thing, not just the effective thing? Meet GRACE, a reason-based moral governor that keeps AI behavior aligned with human norms by separating moral reasoning from goal-driven decision-making. * Moral Module: uses deontic logic and explicit reasons

Why some fine-tuned LLMs miss phishing—and how to fix it

Not all fine-tuned LLMs spot phishing equally. A new study tests Llama 3.1 8B, Gemma 2 9B, and Mistral on high-stakes phishing detection—and uses SHAP and mechanistic interpretability to reveal why models do (or don’t) generalize. * Architecture × data diversity matters: Gemma 2 9B hits state-of-the-art performance (F1

AI that explains itself—by following the science

AI that explains itself—by following the science Black-box AI can be powerful, but it often can’t tell us why it made a decision. Concept Bottleneck Models (CBMs) try to fix that by predicting human-understandable concepts first, then the final answer. The catch: standard CBMs ignore domain-specific cause-and-effect and

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A

TL;DR: Finding reliable answers in genomics is hard. GenomAgent turns one big AI into a coordinating team of specialists—and beats the current leader by 12% on a key benchmark. Genomic facts live across many databases. Standard chatbots struggle because they can’t flexibly query those sources. GeneGPT added

Read more

Meet GRACE: a moral governor for safer, more transparent AI

Why some fine-tuned LLMs miss phishing—and how to fix it

AI that explains itself—by following the science

Meet GenomAgent: A Team of AI Specialists for Smarter Genomics Q&A