# Weather-Robust Scene Semantics with Vision-Aligned 4D Radar

arXiv: https://arxiv.org/abs/2605.07367 · HTML: https://mlsanity.com/paper/2605.07367/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 17 references that are in the map.
- First posted on arXiv 8 May 2026.

## Builds on (most cited first, 17 of 17)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [PETR: Position Embedding Transformation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2203.05625/) (2022)
- [PointLLM: Empowering Large Language Models to Understand Point Clouds](https://mlsanity.com/paper/2308.16911/) (2023)
- [LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark](https://mlsanity.com/paper/2306.06687/) (2023)
- [K-Radar: 4D Radar Object Detection for Autonomous Driving in Various Weather Conditions](https://mlsanity.com/paper/2206.08171/) (2022)
- [RADDet: Range-Azimuth-Doppler based Radar Object Detection for Dynamic Road Users](https://mlsanity.com/paper/2105.00363/) (2021)
- [L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection](https://mlsanity.com/paper/2408.03677/) (2024)
- [ColoRadar: The Direct 3D Millimeter Wave Radar Dataset](https://mlsanity.com/paper/2103.04510/) (2021)
- [Talk2Radar: Bridging Natural Language with 4D mmWave Radar for 3D Referring Expression Comprehension](https://mlsanity.com/paper/2405.12821/) (2024)
- [Enhanced K-Radar: Optimal Density Reduction to Improve Detection Performance and Accessibility of 4D Radar Tensor-based Object Detection](https://mlsanity.com/paper/2303.06342/) (2023)
- [Radar Spectra-Language Model for Automotive Scene Parsing](https://mlsanity.com/paper/2406.02158/) (2024)
- [RLM: A Vision-Language Model Approach for Radar Scene Understanding](https://mlsanity.com/paper/2511.21105/) (2025)

## Built on by (most cited first, 1 of 1)

- [Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models](https://mlsanity.com/paper/2608.04130/) (2026)

## Abstract (arXiv)

Cameras and LiDAR degrade in rain, fog, and snow, while millimeter-wave radar remains largely unaffected. We align a radar encoder to frozen SigLIP vision embeddings and decode structured scene captions through a frozen vision-language model (VLM) with approximately 7M trainable parameters. On K-RADAR with held-out fog, light snow, and heavy snow sequences, all radar configurations outperform a camera baseline that collapses to over 90% hallucination. We identify a token-norm mismatch as the dominant failure mode when bridging radar to a frozen VLM and show that projector-output LayerNorm resolves it. Analysis of encoder complexity, caption format, and pooling strategy reveals tradeoffs that inform future radar-VLM pipeline design.