Latest Research
ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset
The dataset is suitable for training image annotation models based on image-caption pairs, or for multi-label image classification using Unified Medical Language System (UMLS) concepts provided with each image.
Whole-Song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
A cascaded diffusion model is trained to model the hierarchical language, where each level is conditioned on its upper levels.
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
v-manhlt3/m-ltm-audio-text-retrieval
•
•
The Learning-to-match (LTM) framework proves to be an effective inverse optimal transport approach for learning the underlying ground metric between two sources of data, facilitating subsequent matching.
CatCMA : Stochastic Optimization for Mixed-Category Problems
CatCMA updates the parameters of the joint probability distribution in the natural gradient direction.
Generative Unlearning for Any Identity
khu-agi/guide
•
•
In the generative identity unlearning, we target the following objectives: (i) preventing the generation of images with a certain identity, and (ii) preserving the overall quality of the generative model.
Bilateral Event Mining and Complementary for Event Stream Super-Resolution
lqm26/bmcnet-esr
•
•
In this paper, we propose a bilateral event mining and complementary network (BMCNet) to fully leverage the potential of each event and capture the shared information to complement each other simultaneously.
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
In this paper, we propose methodologies for aggregating prediction intervals to obtain one with minimal width and adequate coverage on the target domain under unsupervised domain shift, under which we have labeled samples from a related source domain and unlabeled covariates from the target domain.
Language-Oriented Semantic Latent Representation for Image Transmission
In the new paradigm of semantic communication (SC), the focus is on delivering meanings behind bits by extracting semantic information from raw data.
PIR: Remote Sensing Image-Text Retrieval with Prior Instruction Representation Learning
Continuing with the above, we propose PIR-CLIP, a domain-specific CLIP-based framework for remote sensing image-text retrieval, to address semantic noise in remote sensing vision-language representations and further improve open-domain retrieval performance.
LFED: A Literary Fiction Evaluation Dataset for Large Language Models
The rapid evolution of large language models (LLMs) has ushered in the need for comprehensive assessments of their performance across various dimensions.
