The rapid development of large language models (LLMs) has been witnessed in recent
years. Based on the powerful LLMs, multi-modal LLMs (MLLMs) extend the modality from …

Zero-shot customized video generation has gained significant attention due to its substantial
application potential. Existing methods rely on additional models to extract and inject …

Open-vocabulary semantic segmentation aims to assign semantic labels to each pixel
without relying on a predefined set of categories. Contrastive Language-Image Pre-training …

In recent years, Contrastive Language-Image Pre-training (CLIP) has become a cornerstone
in multimodal intelligence. However, recent studies have identified that the information loss …

Large-scale AI model training divides work across thousands of GPUs, then synchronizes
gradients across them at each step. This incurs a significant network burden that only …

Detection Transformer (DETR) predicts object bounding boxes and classes from learned
object queries. However, DETR exhibits three major flaws:(1) Only a subset of object queries …

Language has been useful in extending the vision encoder to data from diverse distributions
without empirical discovery in training domains. However, as the image description is mostly …

As machine learning models grow in size and complexity, their maintainability becomes a
critical concern, especially when they are increasingly deployed in dynamic, real-world …

Data serves as the foundation in building effective deep learning algorithms, yet the process
of annotation and curation to maintain high data quality is time-intensive. The challenges …