103 citations · 293 across the 25 of their papers we have counts for
27 papers
Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms
Qi Li, Bo Yin, Weiqi Huang +6
Vision-Language-Action (VLA) models are emerging as a unified substrate for embodied intelligence. This shift raises a new class of safety challenges, stemming from the embodied na…
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models
Lexiang Xiong, Qi Li, Jingwen Ye +1
Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements - posing a critical barrier to their trustworthy deployment. In this…
Reinforced Model Merging
Jiaqi Han, Jingwen Ye, Shunyu Liu +4
The success of large language models has garnered widespread attention for model merging techniques, especially training-free methods which combine model capabilities within the pa…
Adversarial Training: A Survey
Mengnan Zhao, Lihe Zhang, Jingwen Ye +3
Adversarial training (AT) refers to integrating adversarial examples -- inputs altered with imperceptible perturbations that can significantly impact model predictions -- into the…
Teddy: Efficient Large-Scale Dataset Distillation via Taylor-Approximated Matching
Ruonan Yu, Songhua Liu, Jingwen Ye +1
Dataset distillation or condensation refers to compressing a large-scale dataset into a much smaller one, enabling models trained on this synthetic dataset to generalize effectivel…
Heavy Labels Out! Dataset Distillation with Label Space Lightening
Ruonan Yu, Songhua Liu, Zigeng Chen +2
Dataset distillation or condensation aims to condense a large-scale training dataset into a much smaller synthetic one such that the training performance of distilled and original…
Improving Adversarial Robustness via Feature Pattern Consistency Constraint
Jiacong Hu, Jingwen Ye, Zunlei Feng +5
Convolutional Neural Networks (CNNs) are well-known for their vulnerability to adversarial attacks, posing significant security concerns. In response to these threats, various defe…
StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization
Songhua Liu, Xin Jin, Xingyi Yang +2
Single domain generalization (single DG) aims at learning a robust model generalizable to unseen domains from only one training domain, making it a highly ambitious and challenging…
Distilled Datamodel with Reverse Gradient Matching
Jingwen Ye, Ruonan Yu, Songhua Liu +1
The proliferation of large-scale AI models trained on extensive datasets has revolutionized machine learning. With these models taking on increasingly central roles in various appl…
Mutual-modality Adversarial Attack with Semantic Perturbation
Jingwen Ye, Ruonan Yu, Songhua Liu +1
Adversarial attacks constitute a notable threat to machine learning systems, given their potential to induce erroneous predictions and classifications. However, within real-world c…
Improving Expressivity of GNNs with Subgraph-specific Factor Embedded Normalization
Kaixuan Chen, Shunyu Liu, Tongtian Zhu +5
Graph Neural Networks (GNNs) have emerged as a powerful category of learning architecture for handling graph-structured data. However, existing GNNs typically ignore crucial struct…
Any-to-Any Style Transfer: Making Picasso and Da Vinci Collaborate
Songhua Liu, Jingwen Ye, Xinchao Wang
Style transfer aims to render the style of a given image for style reference to another given image for content reference, and has been widely adopted in artistic generation and im…
Partial Network Cloning
Jingwen Ye, Songhua Liu, Xinchao Wang
In this paper, we study a novel task that enables partial knowledge transfer from pre-trained models, which we term as Partial Network Cloning (PNC). Unlike prior methods that upda…
Deep Model Reassembly
Xingyi Yang, Daquan Zhou, Songhua Liu +2
In this paper, we explore a novel knowledge-transfer task, termed as Deep Model Reassembly (DeRy), for general-purpose model reuse. Given a collection of heterogeneous models pre-t…
Dataset Distillation via Factorization
Songhua Liu, Kai Wang, Xingyi Yang +2
In this paper, we study \xw{dataset distillation (DD)}, from a novel perspective and introduce a \emph{dataset factorization} approach, termed \emph{HaBa}, which is a plug-and-play…
A Survey of Neural Trees
Haoling Li, Jie Song, Mengqi Xue +4
Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning, yet coming with mutually exclusive advantages and limitations. To bring the best of the…
Learning with Recoverable Forgetting
Jingwen Ye, Yifang Fu, Jie Song +5
Life-long learning aims at learning a sequence of tasks without forgetting the previously acquired knowledge. However, the involved training data may not be life-long legitimate du…
DynaST: Dynamic Sparse Transformer for Exemplar-Guided Image Generation
Songhua Liu, Jingwen Ye, Sucheng Ren +1
One key challenge of exemplar-guided image generation lies in establishing fine-grained correspondences between input and guided images. Prior approaches, despite the promising res…
Factorizing Knowledge in Neural Networks
Xingyi Yang, Jingwen Ye, Xinchao Wang
In this paper, we explore a novel and ambitious knowledge-transfer task, termed Knowledge Factorization~(KF). The core idea of KF lies in the modularization and assemblability of k…
Spot-adaptive Knowledge Distillation
Jie Song, Ying Chen, Jingwen Ye +1
Knowledge distillation (KD) has become a well established paradigm for compressing deep neural networks. The typical way of conducting knowledge distillation is to train the studen…
Safe Distillation Box
Jingwen Ye, Yining Mao, Jie Song +3
Knowledge distillation (KD) has recently emerged as a powerful strategy to transfer knowledge from a pre-trained teacher model to a lightweight student, and has demonstrated its un…
Online Knowledge Distillation for Efficient Pose Estimation
Zheng Li, Jingwen Ye, Mingli Song +2
Existing state-of-the-art human pose estimation methods require heavy computational resources for accurate predictions. One promising technique to obtain an accurate yet lightweigh…
Data-Free Knowledge Amalgamation via Group-Stack Dual-GAN
Jingwen Ye, Yixin Ji, Xinchao Wang +2
Recent advances in deep learning have provided procedures for learning one network to amalgamate multiple streams of knowledge from the pre-trained Convolutional Neural Network (CN…
DEPARA: Deep Attribution Graph for Deep Knowledge Transferability
Jie Song, Yixin Chen, Jingwen Ye +4
Exploring the intrinsic interconnections between the knowledge encoded in PRe-trained Deep Neural Networks (PR-DNNs) of heterogeneous tasks sheds light on their mutual transferabil…