Building smarter maps with GPT-4o vision fine-tuning

Introducing vision to the fine-tuning API

Developers can now fine-tune GPT-4o with images and text to improve vision capabilities

Fine-tuning now available for GPT-4o

GPT-4o mini: advancing cost-efficient intelligence

Introducing 4o Image Generation

At OpenAI, we have long believed image generation should be a primary capability of our language models. That’s why we’ve built our most advanced image generator yet into GPT‑4o.

NavOne: One-Step Global Planning for Vision-Language Navigation on Top-Down Maps

arXiv:2605. 06317v4 Announce Type: replace-cross Abstract: Existing Vision-Language Navigation (VLN) methods typically adopt an egocentric, step-by-step paradigm, which struggles with error accumulation and limits efficiency.

Transforming visual accessibility

Be My Eyes uses GPT-4 to transform visual accessibility.

Fine-tuning GPT-3 to scale video creation

Fine-tuning GPT-3 to power and scale done-for-you video creation.

Addendum to GPT-4o System Card: 4o image generation

4o image generation is a new, significantly more capable image generation approach than our earlier DALL·E 3 series of models. It can create photorealistic output.

DSP-SLAM++: A Unified Framework for Multi-Class, High-Fidelity Object SLAM in the Wild

Existing object-aware SLAM systems force a trade-off between real-time performance, multi-class support, and the generation of high-fidelity, semantically coherent object models. To address this trade-off, we present DSP-SLAM++, which extends the DSP-SLAM framework with an asynchronous mapping pipeline for real-time performance and dedicated sensor fusion adaptations for a monocular fisheye-LiDAR suite.

Fusion of Pervasive RF Data with Spatial Images via Vision Transformers for Enhanced Mapping in Smart Cities

arXiv:2508. 03736v2 Announce Type: replace-cross Abstract: In this paper, we present a deep learning-based approach that integrates the DINOv2 architecture to improve building mapping by combining (possibly erroneous) maps from open-source platforms with pervasive radio frequency (RF) data collected from multiple wireless user equipments and base stations.

MapDream: Task-Driven Map Learning for Vision-Language Navigation

arXiv:2602. 00222v3 Announce Type: replace-cross Abstract: Vision-Language Navigation (VLN) requires agents to follow natural language instructions in partially observed 3D environments, motivating map representations that aggregate spatial context beyond local perception.

PixelLoop: Shortcut Topological Navigation with Pixel-Level Loops

arXiv:2607. 12811v1 Announce Type: cross Abstract: Although topological mapping and navigation have been studied extensively, the specific role and downstream effect of loop closures in purely topological representations has received relatively little attention.