2 citations · 11 across the 18 of their papers we have counts for
21 papers
Positivity and negativity for -bases for
Wouter van Doorn, Pietro Monticone, Melvyn B. Nathanson
A set of integers is an -basis for if every integer in belongs to the sumset , that is, can be represented as the sum of exactly not…
Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language Models
Yu Zhang, Xinchen Li, Jialei Zhou +6
Block-wise decoding effectively improves the inference speed and quality in diffusion language models (DLMs) by combining inter-block sequential denoising and intra-block parallel…
Adaptive Visual Autoregressive Acceleration via Dual-Linkage Entropy Analysis
Yu Zhang, Jingyi Liu, Feng Liu +5
Visual AutoRegressive modeling (VAR) suffers from substantial computational cost due to the massive token count involved. Failing to account for the continuous evolution of modelin…
Markovian Scale Prediction: A New Era of Visual Autoregressive Generation
Yu Zhang, Jingyi Liu, Yiwei Shi +4
Visual AutoRegressive modeling (VAR) based on next-scale prediction has revitalized autoregressive visual generation. Although its full-context dependency, i.e., modeling all previ…
Cross-Modal Distillation For Widely Differing Modalities
Cairong Zhao, Yufeng Jin, Zifan Song +3
Deep learning achieved great progress recently, however, it is not easy or efficient to further improve its performance by increasing the size of the model. Multi-modal learning ca…
Transformer-Based Person Search with High-Frequency Augmentation and Multi-Wave Mixing
Qilin Shu, Qixian Zhang, Qi Zhang +3
The person search task aims to locate a target person within a set of scene images. In recent years, transformer-based models in this field have made some progress. However, they s…
Improving Prediction Certainty Estimation for Reliable Early Exiting via Null Space Projection
Jianing He, Qi Zhang, Duoqian Miao +4
Early exiting has demonstrated great potential in accelerating the inference of pre-trained language models (PLMs) by enabling easy samples to exit at shallow layers, eliminating t…
Boosting Adversarial Transferability via Commonality-Oriented Gradient Optimization
Yanting Gao, Yepeng Liu, Junming Liu +4
Exploring effective and transferable adversarial examples is vital for understanding the characteristics and mechanisms of Vision Transformers (ViTs). However, adversarial examples…
Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning
Yu Zhang, Jialei Zhou, Xinchen Li +6
Current text-to-image diffusion generation typically employs complete-text conditioning. Due to the intricate syntax, diffusion transformers (DiTs) inherently suffer from a compreh…
MindSimulator: Exploring Brain Concept Localization via Synthetic FMRI
Guangyin Bao, Qi Zhang, Zixuan Gong +2
Concept-selective regions within the human cerebral cortex exhibit significant activation in response to specific visual stimuli associated with particular concepts. Precisely loca…
COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism
Jianing He, Qi Zhang, Hongyun Zhang +3
Early exiting is an effective paradigm for improving the inference efficiency of pre-trained language models (PLMs) by dynamically adjusting the number of executed layers for each…
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
Zixuan Gong, Guangyin Bao, Qi Zhang +9
Reconstruction of static visual stimuli from non-invasion brain activity fMRI achieves great success, owning to advanced deep learning models such as CLIP and Stable Diffusion. How…
FedMinds: Privacy-Preserving Personalized Brain Visual Decoding
Guangyin Bao, Duoqian Miao
Exploring the mysteries of the human brain is a long-term research topic in neuroscience. With the help of deep learning, decoding visual information from human brain activity fMRI…
MLIP: Efficient Multi-Perspective Language-Image Pretraining with Exhaustive Data Utilization
Yu Zhang, Qi Zhang, Zixuan Gong +9
Contrastive Language-Image Pretraining (CLIP) has achieved remarkable success, leading to rapid advancements in multimodal studies. However, CLIP faces a notable challenge in terms…
HyDiscGAN: A Hybrid Distributed cGAN for Audio-Visual Privacy Preservation in Multimodal Sentiment Analysis
Zhuojia Wu, Qi Zhang, Duoqian Miao +3
Multimodal Sentiment Analysis (MSA) aims to identify speakers' sentiment tendencies in multimodal video content, raising serious concerns about privacy risks associated with multim…
Wills Aligner: Multi-Subject Collaborative Brain Visual Decoding
Guangyin Bao, Qi Zhang, Zixuan Gong +6
Decoding visual information from human brain activity has seen remarkable advancements in recent research. However, the diversity in cortical parcellation and fMRI patterns across…
MindTuner: Cross-Subject Visual Decoding with Visual Fingerprint and Semantic Correction
Zixuan Gong, Qi Zhang, Guangyin Bao +4
Decoding natural visual scenes from brain activity has flourished, with extensive research in single-subject tasks and, however, less in cross-subject tasks. Reconstructing high-qu…
DE-BERT: Distance-Enhanced Early Exiting for BERT based on Prototypical Networks
Jianing He, Qi Zhang, Weiping Ding +4
Early exiting has demonstrated its effectiveness in accelerating the inference of pre-trained language models like BERT by dynamically adjusting the number of layers executed. Howe…
Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detector
An Lao, Qi Zhang, Chongyang Shi +4
Multimodal content, such as mixing text with images, presents significant challenges to rumor detection in social media. Existing multimodal rumor detection has focused on mixing t…
Multimodal Federated Learning with Missing Modality via Prototype Mask and Contrast
Guangyin Bao, Qi Zhang, Duoqian Miao +5
In real-world scenarios, multimodal federated learning often faces the practical challenge of intricate modality missing, which poses constraints on building federated frameworks a…
Lite-Mind: Towards Efficient and Robust Brain Representation Network
Zixuan Gong, Qi Zhang, Guangyin Bao +5
The limited data availability and the low signal-to-noise ratio of fMRI signals lead to the challenging task of fMRI-to-image retrieval. State-of-the-art MindEye remarkably improve…