302 citations · 775 across the 27 of their papers we have counts for
13 papers · 1 filter
Tree-of-Mixed-Thought: Combining Fast and Slow Thinking for Multi-hop Visual Reasoning
Pengbo Hu, Ji Qi, Xingyu Li +5
There emerges a promising trend of using large language models (LLMs) to generate code-like plans for complex inference tasks such as visual reasoning. This paradigm, known as LLM-…
Semantic-Human: Neural Rendering of Humans from Monocular Video with Human Parsing
Jie Zhang, Pengcheng Shi, Zaiwang Gu +2
The neural rendering of humans is a topic of great research significance. However, previous works mostly focus on achieving photorealistic details, neglecting the exploration of hu…
Overlap Bias Matching is Necessary for Point Cloud Registration
Pengcheng Shi, Jie Zhang, Haozhe Cheng +4
Point cloud registration is a fundamental problem in many domains. Practically, the overlap between point clouds to be registered may be relatively small. Most unsupervised methods…
Boosting Multi-modal Model Performance with Adaptive Gradient Modulation
Hong Li, Xingyu Li, Pengbo Hu +3
While the field of multi-modal learning keeps growing fast, the deficiency of the standard joint training paradigm has become clear through recent studies. They attribute the sub-o…
Evaluation and Analysis of Hallucination in Large Vision-Language Models
Junyang Wang, Yiyang Zhou, Guohai Xu +9
Large Vision-Language Models (LVLMs) have recently achieved remarkable success. However, LVLMs are still plagued by the hallucination problem, which limits the practicality in many…
Contrastive Label Enhancement
Yifei Wang, Yiyang Zhou, Jihua Zhu +3
Label distribution learning (LDL) is a new machine learning paradigm for solving label ambiguity. Since it is difficult to directly obtain label distributions, many studies are foc…
LESS-VFL: Communication-Efficient Feature Selection for Vertical Federated Learning
Timothy Castiglia, Yi Zhou, Shiqiang Wang +3
We propose LESS-VFL, a communication-efficient feature selection method for distributed systems with vertically partitioned data. We consider a system of a server and several parti…
DualGenerator: Information Interaction-based Generative Network for Point Cloud Completion
Pengcheng Shi, Haozhe Cheng, Xu Han +2
Point cloud completion estimates complete shapes from incomplete point clouds to obtain higher-quality point cloud data. Most existing methods only consider global object features,…
Edge-cloud Collaborative Learning with Federated and Centralized Features
Zexi Li, Qunwei Li, Yi Zhou +3
Federated learning (FL) is a popular way of edge computing that doesn't compromise users' privacy. Current FL paradigms assume that data only resides on the edge, while cloud serve…
mPLUG-Owl: Modularization Empowers Large Language Models with Multimodality
Qinghao Ye, Haiyang Xu, Guohai Xu +15
Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-ended tasks, while recent research has also explored the use of LLMs for multi-mo…
Semantically Consistent Multi-view Representation Learning
Yiyang Zhou, Qinghai Zheng, Shunshun Bai +1
In this work, we devote ourselves to the challenging task of Unsupervised Multi-view Representation Learning (UMRL), which requires learning a unified feature representation from m…
Multi-view Semantic Consistency based Information Bottleneck for Clustering
Wenbiao Yan, Jihua Zhu, Yiyang Zhou +2
Multi-view clustering can make use of multi-source information for unsupervised clustering. Most existing methods focus on learning a fused representation matrix, while ignoring th…
MCoCo: Multi-level Consistency Collaborative Multi-view Clustering
Yiyang Zhou, Qinghai Zheng, Wenbiao Yan +3
Multi-view clustering can explore consistent information from different views to guide clustering. Most existing works focus on pursuing shallow consistency in the feature space an…