Awesome World Model Hub Papers · Datasets · Projects
← Back to papers

Occ-LLM: Enhancing Autonomous Driving with Occupancy-Based Large Language Models

ICRA 25 2025 33.5 method, application

TLDR

Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving.

Reasoning

Fallback reasoning generated from available title and abstract metadata: Large Language Models (LLMs) have made substantial advancements in the field of robotic and autonomous driving. This study presents the first Occupancy-based Large Language Model (Occ-LLM), which represents a pioneering effort to integrate LLMs with an important representation....

Read-first score

Read-first score 33.5, weighted from topical fit, citation, graph, method, reproducibility, and recency signals.

Recency 8%
86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%
50

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=evaluation

Reproducibility 25%
38

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code

Topical relevance 42%
10.3

Matches configured research keywords against title, abstract, tags, and analysis text. matched=2

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 125.

Deep Analysis

Innovations

  • First integration of Large Language Models with occupancy representation for autonomous driving
  • Motion Separation Variational Autoencoder (MS-VAE) that uses prior knowledge to separate dynamic objects from static scenes before encoding

Methodology

Occ-LLM integrates LLMs with occupancy representation using a Motion Separation Variational Autoencoder (MS-VAE) that separates dynamic objects from static scenes to improve encoding and handle category imbalances. The model is evaluated on 4D occupancy forecasting, self-ego planning, and occupancy-based scene question answering tasks.

Key Results

Occ-LLM achieves about 6% improvement in Intersection over Union (IoU) and 4% in mean Intersection over Union (mIoU) for 4D occupancy forecasting over state-of-the-art methods.

Tags