Jiayi Ji

JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization

SpaCE-10: A Comprehensive Benchmark for Multimodal Large Language Models in Compositional Spatial Intelligence

MetaCaptioner: Towards Generalist Visual Captioning with Open-source Suites

RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning

FlexibleLLM: Making Low-Bit Quantization for Large Language Models More Flexible and Efficient

Training-Free Multimodal Large Language Model Orchestration

Breaking the Bias: Quantifying the Attention of Industrial Anomaly Detection

FastVGGT: Fast Visual Geometry Transformer

MDReID: Modality-Decoupled Learning for Any-to-Any Multi-Modal Object Re-Identification

Multi-Modal Object Re-identification via Sparse Mixture-of-Experts

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension

$\gamma-$MoD: Exploring Mixture-of-Depth Adaptation for Multimodal Large Language Models

GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification

Towards Semantic Equivalence of Tokenization in Multimodal LLM

Weakly-supervised 3D Referring Expression Segmentation

Tradiffusion++：Hierarchical Guidance for Fine-Grained Trajectory-Based Image Generation