First benchmarking framework for evaluating vision-language model scene understanding via inverse rendering tasks through agentic tool use.

First explored vLLM-based agentic interaction in generated 3D contents.

Enhance multimodal fusion via conditional mutual information maximization for balanced cross-modal representation learning.

JarvisArt outperforms GPT-4o with a 60% improvement in average pixel-level metrics on MMArt-Bench for content fidelity.

JarvisIR is a VLM-powered intelligent system that dynamically schedules expert models for restoration.

A granular video anomaly detection framework that integrates the detection of multiple fine-grained anomalous objects into a unified framework, achieving state-of-the-art performance.

A pioneering foray into the intriguing realm of embedding, relating and perceiving the heterogeneous patterns from various biomedical modalities holistically via a graph theory.

A novel approach that leverages the ambiguity and uncertainty in object boundaries to improve segmentation performance, turning traditional segmentation "flaws" into advantages.

Training large networks efficiently and smartly by progressive data distillation.

An initial exploration into embedding customizable, imperceptible, and recoverable information within the renders produced by off-the-line 3D generative models, while ensuring minimal impact on the rendered content's quality.

Train once, deploy everywhere with many-in-one flexible 3D Gaussian splatting for efficient multi-device deployment.

DynamicVerse is a physical‑scale, multimodal 4D modeling framework for real-world video.

A pioneering exploration into high-fidelity medical video generation on endoscopy scenes.

Embedding multimodal invisible information (image, video, audio) into distributed visual assets.