Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks61 from public data
- 111
- AquaLoRA: Toward White-box Protection for Customized Stable Diffusion Models via Watermark LoRA93
A merge watermark information into the U-Net of Stable Diffusion Models via a watermark Low-Rank Adaptation (LoRA) module in a two-stage manner and a scaling matrix to achieve flexible message updates without retraining are proposed.
- On the Word Alignment from Neural Machine Translation87
This paper proposes two methods to induce word alignment which are general and agnostic to specific NMT models and experiments show that both methods induce much better word alignment than attention.
- Evaluating Explanation Methods for Neural Machine Translation29
An initial attempt to evaluate explanation methods from an alternative viewpoint and proposes a principled metric based on fidelity in regard to the predictive behavior of the NMT model.
- Enhancing Intrinsic Adversarial Robustness via Feature Pyramid Decoder26
Evaluated against a variety of white-box and black-box attacks, it is demonstrated that FPD-enhanced CNNs gain sufficient robustness against general adversarial samples on MNIST, SVHN and CALTECH.
- Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization26
Inspired by recent theoretic advances in deep learning, the paper understands DA from two perspectives towards the generalization ability of a model: input sensitivity and prediction margin, which are defined independent of specific test set thereby may lead to findings with relatively low variance.
- 24
- Fine-Grained Emotions Influence on Implicit Hate Speech Detection21
The experimental results show that the multi-task approach outperformed in classifying implicit hate speech compared to the baseline models and demonstrates that fine-grained emotional knowledge decreases the classification error across multiple implicit hate categories.
- 18
- Improving Adversarial Robustness of 3D Point Cloud Classification Models15
Two innovative methodologies to improve the adversarial robustness of 3D point cloud classification models are designed, including a novel point cloud architecture which can smooth and disrupt the adversarial perturbations and a novel data augmentation strategy to adaptively balance the model usability and robustness.
- Development of a Single-Leaf Disease Severity Automatic Grading System Based on Image Processing14
The effectiveness and adaptability of the single-leaf disease severity automatic grading system was evaluated using the images of grape downy mildew caused by Plasmopara viticola and showed that the effectiveness of the system was favorable with high accuracy.
- PRIME: Protect Your Videos From Malicious Editing10
This work introduces the protection method, PRIME, to significantly reduce the time cost and improve the protection performance, and evaluation results indicate that PRIME only costs 8.3% GPU hours of the cost of the previous state-of-the-art method and achieves better protection results on both human evaluation and objective metrics.
- 10
- Generative Bridging Network for Neural Sequence Prediction9
Three different GBNs, namely uniform GBN, language-model GBN and coaching GBN are proposed to penalize confidence, enhance language smoothness and relieve learning burden, show that they can yield significant improvements over strong baselines.
- Quantifying neck muscle activity during head fixation in VR6
How specific head orientations and fixation durations differentially load the neck musculature is highlighted, offering the basis for a physiological explanation for discomfort during prolonged VR use and establishing a baseline for future ergonomic assessments.
- 6
- Privacy-preserving Decentralized Deep Learning with Multiparty Homomorphic Encryption6
D-MHE is proposed, the first secure and efficient decentralized training framework with lossless precision that can reduce the communication complexity of general Secure Multiparty Computation tasks from quadratic to linear in the number of users, making it very suitable and scalable for large-scale decentralized learning systems.
- 5
- 5
- 4
- P2P Default Risk Prediction based on XGBoost, SVM and RF Fusion Model4
A P2P default risk prediction model based on XGBoost, SVM and RF fusion model, which combines the advantages of high accuracy, robustness and generalization ability of the three models and has better prediction.
- 2
- Improving Cross-lingual Transfer with Contrastive Negative Learning and Self-training2
This work extends the negative learning to the metric space by selecting negative pairs based on the complementary labels and then employ self-training to iteratively train the model to converge on the obtained clean pseudo-labels to leverage the information of low-confidence samples.
- 2
- 2
- Understanding and Improving Hidden Representations for Neural Machine Translation2
This work proposes to regularize the layer-wise representations with all tree-induced tasks and design efficient approximation methods by selecting a few coarse-to-fine tasks for regularization to overcome the computational bottleneck resulting from the large number of regularization terms.
- Neural Sequence Prediction by Coaching.2
This paper introduces a hybrid-coach framework to combine these two existing algorithms so that the supervision from MLE can stabilize RL training while RL can incorporate task-level loss into MLE training.
- Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning1
This study systematically examines the factors contributing to safety alignment degradation in benign fine-tuning scenarios and evaluates the reliability of state-of-the-art reward models (RMs), which are often used to guide alignment processes.
- 1
- 1
- Fingerprinting Image-to-Image Generative Adversarial Networks1
A novel finger-printing scheme for the Intellectual Property (IP) protection of image-to-image GANs based on a trusted third party and proves that these methods can satisfy different security requirements necessary for IP protection.
- Rethinking Adversarial Training with Neural Tangent Kernel1
An in-depth investigation of AT process and properties with NTK, such as NTK evolution, and the impact of data normalization on AT and the importance of unbiased estimators in batch normalization layers is disclosed.
- 1
- ShiftNAS: Towards Automatic Generation of Advanced Mulitplication-Less Neural Networks1
This work proposes ShiftNAS, the first framework tailoring Neural Architecture Search (NAS) to substantially reduce the accuracy gap between bit-shift neural networks and their real-valued counterparts, and sets a new state-of-the-art for bit- shift neural networks.
- 1
- 1
- 1
- –
- –
- StrainGain: Neck Strain Amplifies Head Pointing in VR–
StrainGain demonstrates how physiological-state-informed gain control can reduce head movement during VR pointing, reframing gain adaptation as a mechanism for sustained comfort and well-being rather than performance alone.
- –
- –
- The effect of Carrier Doping and Thickness on the Electronic Structures of La$3$Ni$2$O$7$ Thin Films–
- –
- –
- –
- –
- Singular Regularization with Information Bottleneck Improves Model's Adversarial Robustness–
This paper proposes a new module to regularize adversarial information and combine information bottleneck theory, which is proposed to theoretically restrict intermediate representations, and proves that the method is interpretable and able to be explained under regional faithfulness analysis.
- –
- A Benchmark of Long-tailed Instance Segmentation with Noisy Labels–
This paper proposes a new dataset, which is a large vocabulary long-tailed dataset containing label noise for instance segmentation, and indicates that the noise in the training dataset will hamper the model in learning rare categories and decrease the overall performance.
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.