26 citations · 75 across the 25 of their papers we have counts for
27 papers
SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait Animation
Juncheng Ma, Yuxuan Du, Yanan Sun +8
Diffusion Transformers (DiTs) have significantly advanced audio-driven portrait animation, but their high computational cost leads to substantial inference latency. Although traini…
GeoSense: Internalizing Geometric Necessity Perception for Multimodal Reasoning
Ruiheng Liu, Haihong Hao, Mingfei Han +4
Advancing towards artificial superintelligence requires rich and intelligent perceptual capabilities. A critical frontier in this pursuit is overcoming the limited spatial understa…
Do VLMs Perceive or Recall? Probing Visual Perception vs. Memory with Classic Visual Illusions
Xiaoxiao Sun, Mingyang Li, Kun Yuan +7
Large Vision-Language Models (VLMs) often answer classic visual illusions "correctly" on original images, yet persist with the same responses when illusion factors are inverted, ev…
Efficient Training for Human Video Generation with Entropy-Guided Prioritized Progressive Learning
Changlin Li, Jiawei Zhang, Shuhao Liu +4
Human video generation has advanced rapidly with the development of diffusion models, but the high computational cost and substantial memory consumption associated with training th…
Which Layer Causes Distribution Deviation? Entropy-Guided Adaptive Pruning for Diffusion and Flow Models
Changlin Li, Jiawei Zhang, Zeyi Shi +3
Large-scale vision generative models, including diffusion and flow models, have demonstrated remarkable performance in visual generation tasks. However, transferring these pre-trai…
CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation
Haihong Hao, Mingfei Han, Changlin Li +2
Embodied navigation demands comprehensive scene understanding and precise spatial reasoning. While image-text models excel at interpreting pixel-level color and lighting cues, 3D-t…
Efficient Training of Large Vision Models via Advanced Automated Progressive Learning
Changlin Li, Jiawei Zhang, Sihao Lin +4
The rapid advancements in Large Vision Models (LVMs), such as Vision Transformers (ViTs) and diffusion models, have led to an increasing demand for computational resources, resulti…
DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions
Guangrun Wang, Changlin Li, Liuchun Yuan +5
Neural Architecture Search (NAS), aiming at automatically designing neural architectures by machines, has been considered a key step toward automatic machine learning. One notable…
No Token Left Behind: Efficient Vision Transformer via Dynamic Token Idling
Xuwei Xu, Changlin Li, Yudong Chen +3
Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resour…
Aspect-oriented Opinion Alignment Network for Aspect-Based Sentiment Classification
Xueyi Liu, Rui Hou, Yanglei Gan +4
Aspect-based sentiment classification is a crucial problem in fine-grained sentiment analysis, which aims to predict the sentiment polarity of the given aspect according to its con…
GrowCLIP: Data-aware Automatic Model Growing for Large-scale Contrastive Language-Image Pre-training
Xinchi Deng, Han Shi, Runhui Huang +7
Cross-modal pre-training has shown impressive performance on a wide range of downstream tasks, benefiting from massive image-text pairs collected from the Internet. In practice, on…
MixReorg: Cross-Modal Mixed Patch Reorganization is a Good Mask Learner for Open-World Semantic Segmentation
Kaixin Cai, Pengzhen Ren, Yi Zhu +5
Recently, semantic segmentation models trained with image-level text supervision have shown promising results in challenging open-world scenarios. However, these models still face…
ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency
Pengzhen Ren, Changlin Li, Hang Xu +5
Recently, great success has been made in learning visual representations from text supervision, facilitating the emergence of text-supervised semantic segmentation. However, existi…
H-VFI: Hierarchical Frame Interpolation for Videos with Large Motions
Changlin Li, Guangyang Wu, Yanan Sun +3
Capitalizing on the rapid development of neural networks, recent video frame interpolation (VFI) methods have achieved notable improvements. However, they still fall short for real…
Learning Self-Regularized Adversarial Views for Self-Supervised Vision Transformers
Tao Tang, Changlin Li, Guangrun Wang +3
Automatic data augmentation (AutoAugment) strategies are indispensable in supervised data-efficient training protocols of vision transformers, and have led to state-of-the-art resu…
DeViT: Deformed Vision Transformers in Video Inpainting
Jiayin Cai, Changlin Li, Xin Tao +2
This paper proposes a novel video inpainting method. We make three main contributions: First, we extended previous Transformers with patch alignment by introducing Deformed Patch-b…
Mitigating Data Redundancy to Revitalize Transformer-based Long-Term Time Series Forecasting System
Mingjie Li, Rui Liu, Guangsi Shi +5
Long-term time-series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability t…
Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism
Binbin Yang, Xinchi Deng, Han Shi +6
Continual learning is a challenging real-world problem for constructing a mature AI system when data are provided in a streaming fashion. Despite recent progress in continual class…
Look Back and Forth: Video Super-Resolution with Explicit Temporal Difference Modeling
Takashi Isobe, Xu Jia, Xin Tao +6
Temporal modeling is crucial for video super-resolution. Most of the video super-resolution methods adopt the optical flow or deformable convolution for explicitly motion compensat…
Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search
Minbin Huang, Zhijian Huang, Changlin Li +4
Neural Architecture Search (NAS) aims to find efficient models for multiple tasks. Beyond seeking solutions for a single task, there are surging interests in transferring network d…
Beyond Fixation: Dynamic Window Visual Transformer
Pengzhen Ren, Changlin Li, Guangrun Wang +4
Recently, a surge of interest in visual transformers is to reduce the computational cost by limiting the calculation of self-attention to a local window. Most current work uses a f…
Automated Progressive Learning for Efficient Training of Vision Transformers
Changlin Li, Bohan Zhuang, Guangrun Wang +3
Recent advances in vision Transformers (ViTs) have come with a voracious appetite for computing power, high-lighting the urgent need to develop efficient training methods for ViTs.…
Dynamic Slimmable Denoising Network
Zutao Jiang, Changlin Li, Xiaojun Chang +2
Recently, tremendous human-designed and automatically searched neural networks have been applied to image denoising. However, previous works intend to handle all noisy images in a…
Pi-NAS: Improving Neural Architecture Search by Reducing Supernet Training Consistency Shift
Jiefeng Peng, Jiqi Zhang, Changlin Li +3
Recently proposed neural architecture search (NAS) methods co-train billions of architectures in a supernet and estimate their potential accuracy using the network weights detached…