om-ai-lab

Solve Visual Understanding with Reinforced VLMs

[EMNLP-2024] Build multimodal language agents for fast prototype and production

VLX-Seek is an efficient VLM that grounds fine-grained visual targets with high precision in wild environments.

Real-time and accurate open-vocabulary end-to-end object detection

VLX-Flow: streaming VLM for real-time general vision intelligence

VLM-FO1: Bridging the Gap Between High-Level Reasoning and Fine-Grained Perception in VLMs

RS5M: a large-scale vision language dataset for remote sensing [TGRS]

Open & Reproducible Research for Tracking VLAs

VLX-Go is a lightweight vision-language waypoint planner that enables robots to perceive their surroundings, track targets, and navigate the physical world in real time.

Collection of Remote Sensing Vision-Language Models

Evaluating Vision & Language Pretraining Models with Objects, Attributes and Relations. [EMNLP 2022]

[EMNLP-2025 Oral] ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration

GroundVLP: Harnessing Zero-shot Visual Grounding from Vision-Language Pre-training and Open-Vocabulary Object Detection (AAAI 2024)

SDK to use VLX-VR: An Agentic-Aware Video Reasoning Model

A Comprehensive Evaluation Benchmark for Open-Vocabulary Detection (AAAI 2024)