Metraipolis › archive › dc_f0ec464ebe00

Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models — arXiv:2608.04130

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.04130
License (as archived)
CC0-1.0
Archived
2026-10-31T11:47:46.396Z
SHA-256 of the archived text
975113cda11cdce986eb6244ea1f9d4733fc3e61dda9b431098a347798e5b5ba
Stable URL of this page
https://metraipolis.com/documento/dc_f0ec464ebe00

How to cite

Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models — arXiv:2608.04130 — arXiv (en), https://arxiv.org/abs/2608.04130 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f0ec464ebe00 (Metraipolis archive dc_f0ec464ebe00, sha256 975113cda11cdce986eb6244ea1f9d4733fc3e61dda9b431098a347798e5b5ba)
BibTeX
@misc{dcf0ec464ebe00,
  title = {Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language Models — arXiv:2608.04130},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.04130},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f0ec464ebe00; sha256 975113cda11cdce986eb6244ea1f9d4733fc3e61dda9b431098a347798e5b5ba},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04130. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-language models for autonomous driving primarily rely on cameras and LiDAR, leaving 4D radar largely unexplored as a standalone perceptual modality despite its robustness to adverse visibility and direct measurement of radial velocity. We introduce Radar4D-VLM, a radar-only temporal vision-language model that reasons from ten consecutive 4D-radar point-cloud sweeps without camera or LiDAR input. Radar4D-VLM extracts geometrically grounded object proposals and organizes radar evidence into a compact hierarchy of object, scene, and kinematic tokens. A parameter-efficient projector maps these tokens into frozen language backbones, while auditable prediction heads jointly model object count, spatial distribution, motion state, collision risk, semantic category, and radial velocity. Radar4D-VLM combines proposal-grounded temporal object tokenization, global scene context, and explicit kinematic tokens within a unified frozen-backbone interface. On sequence-isolated K-Radar development validation, its Top-64 proposal recall reaches 98.13% at 4 m, exceeding fixed-lattice and uniform-random controls by 6.40 and 22.83 percentage points, respectively. We further evaluate 24 matched runs spanning eight frozen Qwen, Phi, Mistral, Llama, and Gemma backbones under an identical adaptation budget. The radar-token interface remains compatible across all five language-model families, while matched aligned, permuted, and no-language controls show sensor dependence but no stable direct-head gain from aligned language supervision. These results establish a reproducible foundation for radar-only multimodal scene and motion reasoning while separating interface compatibility from the benefit of language supervision.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-06 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.04130 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-31T11:37:40.646Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).