14 citations · 20 across the 14 of their papers we have counts for
14 papers
Do Joint Audio-Video Generation Models Understand Physics?
Zijun Cui, Xiulong Liu, Hao Fang +8
Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate…
OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text
Weiguo Pian, Saksham Singh Kushwaha, Zhimin Chen +4
In this paper, we propose Universal Holistic Audio Generation (UniHAGen), a task for synthesizing comprehensive auditory scenes that include both on-screen and off-screen sounds ac…
Towards Online Multi-Modal Social Interaction Understanding
Xinpeng Li, Shijian Deng, Bolin Lai +3
In this paper, we introduce a new problem, Online-MMSI, where the model must perform multimodal social interaction understanding (MMSI) using only historical information. Given a r…
Modality-Inconsistent Continual Learning of Multimodal Large Language Models
Weiguo Pian, Shijian Deng, Shentong Mo +3
In this paper, we introduce Modality-Inconsistent Continual Learning (MICL), a new continual learning scenario for Multimodal Large Language Models (MLLMs) that involves tasks with…
Continual Audio-Visual Sound Separation
Weiguo Pian, Yiyang Nan, Shijian Deng +3
In this paper, we introduce a novel continual audio-visual sound separation task, aiming to continuously separate sound sources for new classes while preserving performance on prev…
CREF: An LLM-based Conversational Software Repair Framework for Programming Tutors
Boyang Yang, Haoye Tian, Weiguo Pian +5
Program repair techniques offer cost-saving benefits for debugging within software development and programming education scenarios. With the proven effectiveness of Large Language…
Class-Incremental Grouping Network for Continual Audio-Visual Learning
Shentong Mo, Weiguo Pian, Yapeng Tian
Continual learning is a challenging problem in which models need to be trained on non-stationary data across sequential tasks for class-incremental learning. While previous methods…
Learning to Represent Patches
Xunzhu Tang, Haoye Tian, Zhenghan Chen +6
Patch representation is crucial in automating various software engineering tasks, like determining patch accuracy or summarizing code changes. While recent research has employed de…
Audio-Visual Class-Incremental Learning
Weiguo Pian, Shentong Mo, Yunhui Guo +1
In this paper, we introduce audio-visual class-incremental learning, a class-incremental learning scenario for audio-visual video recognition. We demonstrate that joint audio-visua…
LaFiCMIL: Rethinking Large File Classification from the Perspective of Correlated Multiple Instance Learning
Tiezhu Sun, Weiguo Pian, Nadia Daoudi +3
Transfomer-based models have significantly advanced natural language processing, in particular the performance in text classification tasks. Nevertheless, these models face challen…
MetaTPTrans: A Meta Learning Approach for Multilingual Code Representation Learning
Weiguo Pian, Hanyu Peng, Xunzhu Tang +5
Representation learning of source code is essential for applying machine learning to software engineering tasks. Learning code representation from a multilingual source code datase…
Predicting Patch Correctness Based on the Similarity of Failing Test Cases
Haoye Tian, Yinghua Li, Weiguo Pian +5
Towards predicting patch correctness in APR, we propose a simple, but novel hypothesis on how the link between the patch behaviour and failing test specifications can be drawn: sim…
Spatial-Temporal Dynamic Graph Attention Networks for Ride-hailing Demand Prediction
Weiguo Pian, Yingbo Wu, Xiangmou Qu +2
Ride-hailing demand prediction is an essential task in spatial-temporal data mining. Accurate Ride-hailing demand prediction can help to pre-allocate resources, improve vehicle uti…
STDI-Net: Spatial-Temporal Network with Dynamic Interval Mapping for Bike Sharing Demand Prediction
Weiguo Pian, Yingbo Wu, Ziyi Kou
As an economical and healthy mode of shared transportation, Bike Sharing System (BSS) develops quickly in many big cities. An accurate prediction method can help BSS schedule resou…