Weijiang Yu
YOU?
Author Swipe
View article: OnlineHOI: Towards Online Human-Object Interaction Generation and Perception
OnlineHOI: Towards Online Human-Object Interaction Generation and Perception Open
The perception and generation of Human-Object Interaction (HOI) are crucial for fields such as robotics, AR/VR, and human behavior understanding. However, current approaches model this task in an offline setting, where information at each …
View article: CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells
CellFM: a large-scale foundation model pre-trained on transcriptomics of 100 million human cells Open
View article: PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis Open
Talking head synthesis with arbitrary speech audio is a crucial challenge in the field of digital humans. Recently, methods based on radiance fields have received increasing attention due to their ability to synthesize high-fidelity and id…
View article: ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters
ReMask-Animate: Refined Character Image Animation Using Mask-Guided Adapters Open
Pose-controlled human video generation is of significant interest and finds extensive applications in areas such as automated advertising and content creation on social media platforms. While existing methods employing pose sequences and r…
View article: PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis Open
Talking head synthesis with arbitrary speech audio is a crucial challenge in the field of digital humans. Recently, methods based on radiance fields have received increasing attention due to their ability to synthesize high-fidelity and id…
View article: A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions
A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions Open
The emergence of large language models (LLMs) has marked a significant breakthrough in natural language processing (NLP), fueling a paradigm shift in information acquisition. Nevertheless, LLMs are prone to hallucination, generating plausi…
View article: BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering
BeamAggR: Beam Aggregation Reasoning over Multi-source Knowledge for Multi-hop Question Answering Open
Large language models (LLMs) have demonstrated strong reasoning capabilities. Nevertheless, they still suffer from factual errors when tackling knowledge-intensive tasks. Retrieval-augmented reasoning represents a promising approach. Howev…
View article: Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Process
Stable Diffusion Segmentation for Biomedical Images with Single-step Reverse Process Open
Diffusion models have demonstrated their effectiveness across various generative tasks. However, when applied to medical image segmentation, these models encounter several challenges, including significant resource and time requirements. T…
View article: Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning
Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning Open
Most advances in medical image recognition supporting clinical auxiliary diagnosis meet challenges due to the low-resource situation in the medical field, where annotations are highly expensive and professional. This low-resource problem c…
View article: Intensive Vision-guided Network for Radiology Report Generation
Intensive Vision-guided Network for Radiology Report Generation Open
Automatic radiology report generation is booming due to its huge application potential for the healthcare industry. However, existing computer vision and natural language processing approaches to tackle this problem are limited in two aspe…
View article: Intensive vision-guided network for radiology report generation
Intensive vision-guided network for radiology report generation Open
Objective. Automatic radiology report generation is booming due to its huge application potential for the healthcare industry. However, existing computer vision and natural language processing approaches to tackle this problem are limited …
View article: AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts
AdaNAS: Adaptively Post-processing with Self-supervised Neural Architecture Search for Ensemble Rainfall Forecasts Open
Previous post-processing studies on rainfall forecasts using numerical weather prediction (NWP) mainly focus on statistics-based aspects, while learning-based aspects are rarely investigated. Although some manually-designed models are prop…
View article: Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System
Learning to Break: Knowledge-Enhanced Reasoning in Multi-Agent Debate System Open
Multi-agent debate system (MAD) imitating the process of human discussion in pursuit of truth, aims to align the correct cognition of different agents for the optimal solution. It is challenging to make various agents perform right and hig…
View article: TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models Open
Grasping the concept of time is a fundamental facet of human cognition, indispensable for truly comprehending the intricacies of the world. Previous studies typically focus on specific aspects of time, lacking a comprehensive temporal reas…
View article: Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model
Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model Open
Motivation Identifying the B-cell epitopes is an essential step for guiding rational vaccine development and immunotherapies. Since experimental approaches are expensive and time-consuming, many computational methods have been designed to …
View article: Identifying spatial domain by adapting transcriptomics with histology through contrastive learning
Identifying spatial domain by adapting transcriptomics with histology through contrastive learning Open
Recent advances in spatial transcriptomics have enabled measurements of gene expression at cell/spot resolution meanwhile retaining both the spatial information and the histology images of the tissues. Accurately identifying the spatial do…
View article: Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning
Exploring Low-Resource Medical Image Classification with Weakly Supervised Prompt Learning Open
View article: Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model
Identifying B-cell epitopes using AlphaFold2 predicted structures and pretrained language model Open
Motivation Identifying the B-cell epitopes is an essential step for guiding rational vaccine development and immunotherapies. Due to experimental approaches being expensive and time-consuming, many computational methods have been designed …
View article: A Meta-learning based Graph-Hierarchical Clustering Method for Single Cell RNA-Seq Data
A Meta-learning based Graph-Hierarchical Clustering Method for Single Cell RNA-Seq Data Open
Single cell sequencing techniques enable researchers view complex bio-tissues from a more precise perspective to identify cell types. However, more and more recent works have been done to find more detailed subtypes within already known ce…
View article: Deciphering Spatial Domains by Integrating Histopathological Image and Transcriptomics via Contrastive Learning
Deciphering Spatial Domains by Integrating Histopathological Image and Transcriptomics via Contrastive Learning Open
Recent advances in spatial transcriptomics have enabled measurements of gene expression at cell/spot resolution meanwhile retaining both the spatial information and the histopathological images of the tissues. Deciphering the spatial domai…
View article: A Meta-learning based Graph-Hierarchical Clustering Method for Single Cell RNA-Seq Data
A Meta-learning based Graph-Hierarchical Clustering Method for Single Cell RNA-Seq Data Open
Single cell sequencing techniques enable researchers view complex bio-tissues from a more precise perspective to identify cell types. However, more and more recent works have been done to find more detailed subtypes within already known ce…
View article: Spatial transcriptomics prediction from histology jointly through Transformer and graph neural networks
Spatial transcriptomics prediction from histology jointly through Transformer and graph neural networks Open
The rapid development of spatial transcriptomics allows the measurement of RNA abundance at a high spatial resolution, making it possible to simultaneously profile gene expression, spatial locations of cells or spots, and the corresponding…
View article: Hybrid Reasoning Network for Video-based Commonsense Captioning
Hybrid Reasoning Network for Video-based Commonsense Captioning Open
The task of video-based commonsense captioning aims to generate event-wise captions and meanwhile provide multiple commonsense descriptions (e.g., attribute, effect and intention) about the underlying event in the video. Prior works explor…
View article: Deep Animation Video Interpolation in the Wild
Deep Animation Video Interpolation in the Wild Open
In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming. Therefore, it is desirable to develop computational models that can automatically interpolate …
View article: Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning
Improving Math Word Problems with Pre-trained Knowledge and Hierarchical Reasoning Open
The recent algorithms for math word problems (MWP) neglect to use outside knowledge not present in the problems. Most of them only capture the word-level relationship and ignore to build hierarchical reasoning like the human being for mini…
View article: Heterogeneous Graph Learning for Visual Commonsense Reasoning
Heterogeneous Graph Learning for Visual Commonsense Reasoning Open
Visual commonsense reasoning task aims at leading the research field into solving cognition-level reasoning with the ability of predicting correct answers and meanwhile providing convincing reasoning paths, resulting in three sub-tasks i.e…
View article: Layout-Graph Reasoning for Fashion Landmark Detection
Layout-Graph Reasoning for Fashion Landmark Detection Open
Detecting dense landmarks for diverse clothes, as a fundamental technique for clothes analysis, has attracted increasing research attention due to its huge application potential. However, due to the lack of modeling underlying semantic lay…