02 / OUR TECHNOLOGY

Grounded intelligence for the physical world.

Advancing the architectures and methods behind trustworthy multimodal intelligence, efficient AI models, 3D perception, and predictive understanding of real-world systems.

01

Multimodal Model Architectures & Grounding

Developing and advancing vision-language models (VLMs) through architectural innovation, grounding-aware training, reinforcement learning, multilingual OCR understanding, visual reasoning, and hallucination reduction.

02

Compact & Efficient AI Models

Designing compact VLM architectures and efficient post-training methods including reinforcement learning, to deliver strong multimodal capabilities with reduced computational and memory requirements, enabling deployment across GPUs, CPUs, and edge devices.

03

Efficient 3D Physical Perception

Developing DVNet (Distributive Convolutional Neural Network), an efficient 3D perception architecture that distributes volumetric feature processing to reduce computational complexity while preserving three-dimensional spatial information.

04

Sensor Fusion & Physical Prediction

Integrating heterogeneous measurements with spatial and temporal modeling to estimate and predict physical properties in real-world environments.

Multimodal Grounding & Hallucination Reduction

Vision-language models can generate plausible descriptions that are not supported by visual evidence. We investigate grounding-aware supervised fine-tuning and preference optimization to improve factual reliability and reduce hallucinations. Our research focuses on aligning model responses with observable image content, supported by curated training data, evaluation benchmarks, and experimental results.

Click a slide to enlarge.

OCR-Aware Visual Understanding

Reading text in real-world images is challenging due to blur, occlusion, perspective distortion, and multilingual content. We develop OCR-aware multimodal post-training methods to improve text extraction and grounded visual reasoning. In our experiments, information completeness improved from 71.3 to 84.6, while hallucination decreased from 18.3% to 5.5%, using the same frozen visual encoder.

Click a slide to enlarge.

DVNet: Efficient 3D Physical Perception

Processing volumetric images with conventional 3D neural networks can be computationally expensive. We are developing a Distributive Volumetric Networks (DVNet), which integrate features across orthogonal spatial planes to capture three-dimensional information efficiently. An initial implementation demonstrates efficient feature mapping, providing a foundation for the next 3D X-ray classification and object detection.

Click a slide to enlarge.

Sensor Fusion & Spatiotemporal Prediction

Physical-world measurements are often sparse, noisy, and distributed across multiple sensors, locations, and time periods. We investigate sensor fusion, spatial statistical modeling, and temporal data analysis to reconstruct and predict physical properties. Prior applications include intelligent road construction, where heterogeneous measurements support spatial prediction and data-driven understanding of material and infrastructure conditions.

Click a slide to enlarge.