1 citations · 2 across the 18 of their papers we have counts for
18 papers
Suppression Is Not Forgetting: Residual Recoverability in Visual Concept Unlearning for VLMs
Zhangyun Tan, Zeliang Zhang, Jiani Liu +5
Vision-language models (VLMs) may need to forget visual concepts after deployment because of privacy, copyright, licensing, safety, or policy changes. Conventional machine unlearni…
Why Instruction-Based Unlearning Fails in Diffusion Models?
Zeliang Zhang, Rui Sun, Jiani Liu +2
Instruction-based unlearning has proven effective for modifying the behavior of large language models at inference time, but whether this paradigm extends to other generative model…
Training Large Reasoning Models Efficiently via Progressive Thought Encoding
Zeliang Zhang, Xiaodong Liu, Hao Cheng +3
Large reasoning models (LRMs) excel on complex problems but face a critical barrier to efficiency: reinforcement learning (RL) training requires long rollouts for outcome-based rew…
AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning
Zhenyu Pan, Yiting Zhang, Zhuo Liu +13
LLM-based multi-agent systems excel at planning, tool use, and role coordination, but their openness and interaction complexity also expose them to jailbreak, prompt-injection, and…
Targeted Forgetting of Image Subgroups in CLIP Models
Zeliang Zhang, Gaowen Liu, Charles Fleming +2
Foundation models (FMs) such as CLIP have demonstrated impressive zero-shot performance across various tasks by leveraging large-scale, unsupervised pre-training. However, they oft…
Forward Learning with Differential Privacy
Mingqian Feng, Zeliang Zhang, Jinyang Jiang +2
Differential privacy (DP) in deep learning is a critical concern as it ensures the confidentiality of training data while maintaining model utility. Existing DP training algorithms…
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
Insu Han, Zeliang Zhang, Zhiyuan Wang +8
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a cri…
Rethinking Audio-Visual Adversarial Vulnerability from Temporal and Modality Perspectives
Zeliang Zhang, Susan Liang, Daiki Shimada +1
While audio-visual learning equips models with a richer understanding of the real world by leveraging multiple sensory modalities, this integration also introduces new vulnerabilit…
Treat Visual Tokens as Text? But Your MLLM Only Needs Fewer Efforts to See
Zeliang Zhang, Phu Pham, Wentian Zhao +6
By treating visual tokens from visual encoders as text tokens, Multimodal Large Language Models (MLLMs) have achieved remarkable progress across diverse visual understanding tasks,…
VidComposition: Can MLLMs Analyze Compositions in Compiled Videos?
Yolo Y. Tang, Junjia Guo, Hang Hua +9
The advancement of Multimodal Large Language Models (MLLMs) has enabled significant progress in multimodal understanding, expanding their capacity to analyze video content. However…
Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?
Zeliang Zhang, Xin Liang, Mingqian Feng +2
As the demand for high-quality training data escalates, researchers have increasingly turned to generative models to create synthetic data, addressing data scarcity and enabling co…
Can CLIP Count Stars? An Empirical Study on Quantity Bias in CLIP
Zeliang Zhang, Zhuo Liu, Mingqian Feng +1
CLIP has demonstrated great versatility in adapting to various downstream tasks, such as image editing and generation, visual question answering, and video understanding. However,…
Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts
Zeliang Zhang, Xiaodong Liu, Hao Cheng +2
By increasing model parameters but activating them sparsely when performing a task, the use of Mixture-of-Experts (MoE) architecture significantly improves the performance of Large…
Learning to Transform Dynamically for Better Adversarial Transferability
Rongyi Zhu, Zeliang Zhang, Susan Liang +2
Adversarial examples, crafted by adding perturbations imperceptible to humans, can deceive neural networks. Recent studies identify the adversarial transferability across various m…
Discover and Mitigate Multiple Biased Subgroups in Image Classifiers
Zeliang Zhang, Mingqian Feng, Zhiheng Li +1
Machine learning models can perform well on in-distribution data but often fail on biased subgroups that are underrepresented in the training data, hindering the robustness of mode…
Approximated Likelihood Ratio: A Forward-Only and Parallel Framework for Boosting Neural Network Training
Zeliang Zhang, Jinyang Jiang, Zhuo Liu +3
Efficient and biologically plausible alternatives to backpropagation in neural network training remain a challenge due to issues such as high computational complexity and additiona…
Forward Learning for Gradient-based Black-box Saliency Map Generation
Zeliang Zhang, Mingqian Feng, Jinyang Jiang +3
Gradient-based saliency maps are widely used to explain deep neural network decisions. However, as models become deeper and more black-box, such as in closed-source APIs like ChatG…
Bag of Tricks to Boost Adversarial Transferability
Zeliang Zhang, Wei Yao, Xiaosen Wang
Deep neural networks are widely known to be vulnerable to adversarial examples. However, vanilla adversarial examples generated under the white-box setting often exhibit low transf…