1 citations · 2 across the 30 of their papers we have counts for
31 papers
Causal Scaffolding for Physical Reasoning: A Benchmark for Causally-Informed Physical World Understanding in VLMs
Tianyi Tang, Zhuoyi Lin, Zeyu Feng +4
Understanding and reasoning about the physical world is the foundation of intelligent behavior, yet state-of-the-art vision-language models (VLMs) still fail at causal physical rea…
Dataset Color Quantization: A Training-Oriented Framework for Dataset-Level Compression
Chenyue Yu, Lingao Xiao, Jinhong Deng +2
Large-scale image datasets are fundamental to deep learning, but their high storage demands pose challenges for deployment in resource-constrained environments. While existing appr…
Unifying Watermarking via Dimension-Aware Mapping
Jiale Meng, Runyi Hu, Jie Zhang +3
Deep watermarking methods often share similar encoder-decoder architectures, yet differ substantially in their functional behaviors. We propose DiM, a new multi-dimensional waterma…
Power of Boundary and Reflection: Semantic Transparent Object Segmentation using Pyramid Vision Transformer with Transparent Cues
Tuan-Anh Vu, Hai Nguyen-Truong, Ziqiang Zheng +4
Glass is a prevalent material among solid objects in everyday life, yet segmentation methods struggle to distinguish it from opaque materials due to its transparency and reflection…
Distributional Multi-objective Black-box Optimization for Diffusion-model Inference-time Multi-Target Generation
Kim Yong Tan, Yueming Lyu, Ivor Tsang +1
Diffusion models have been successful in learning complex data distributions. This capability has driven their application to high-dimensional multi-objective black-box optimizatio…
Lang-PINN: From Language to Physics-Informed Neural Networks via a Multi-Agent Framework
Xin He, Liangliang You, Hongduan Tian +3
Physics-informed neural networks (PINNs) provide a powerful approach for solving partial differential equations (PDEs), but constructing a usable PINN remains labor-intensive and e…
Personalized Vision via Visual In-Context Learning
Yuxin Jiang, Yuchao Gu, Yiren Song +2
Modern vision models, trained on large-scale annotated datasets, excel at predefined tasks but struggle with personalized vision -- tasks defined at test time by users with customi…
Evaluating LLMs Without Oracle Feedback: Agentic Annotation Evaluation Through Unsupervised Consistency Signals
Cheng Chen, Haiyan Yin, Ivor Tsang
Large Language Models (LLMs), when paired with prompt-based tasks, have significantly reduced data annotation costs and reliance on human annotators. However, evaluating the qualit…
Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
Jie Zhang, Ting Xu, Gelei Deng +5
Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fr…
FOCUS: Frequency-Optimized Conditioning of DiffUSion Models for mitigating catastrophic forgetting during Test-Time Adaptation
Gabriel Tjio, Jie Zhang, Xulei Yang +6
Test-time adaptation enables models to adapt to evolving domains. However, balancing the tradeoff between preserving knowledge and adapting to domain shifts remains challenging for…
Time-variant Image Inpainting via Interactive Distribution Transition Estimation
Yun Xing, Qing Guo, Xiaoguang Li +5
In this work, we focus on a novel and practical task, i.e., Time-vAriant iMage inPainting (TAMP). The aim of TAMP is to restore a damaged target image by leveraging the complementa…
Why Settle for One? Text-to-ImageSet Generation and Evaluation
Chengyou Jia, Xin Shen, Zhuohang Dang +6
Despite remarkable progress in Text-to-Image models, many real-world applications require generating coherent image sets with diverse consistency requirements. Existing consistent…
DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches
Yun Xing, Yue Cao, Nhat Chung +6
Stereo depth estimation is a critical task in autonomous driving and robotics, where inaccuracies (such as misidentifying nearby objects as distant) can lead to dangerous situation…
AngleRoCL: Angle-Robust Concept Learning for Physically View-Invariant T2I Adversarial Patches
Wenjun Ji, Yuxiang Fu, Luyang Ying +5
Cutting-edge works have demonstrated that text-to-image (T2I) diffusion models can generate adversarial patches that mislead state-of-the-art object detectors in the physical world…
MermaidFlow: Redefining Agentic Workflow Generation via Safety-Constrained Evolutionary Programming
Chengqi Zheng, Jianda Chen, Yueming Lyu +5
Despite the promise of autonomous agentic reasoning, existing workflow generation methods frequently produce fragile, unexecutable plans due to unconstrained LLM-driven constructio…
Exploring the Effectiveness and Interpretability of Texts in LLM-based Time Series Models
Zhengke Sun, Hangwei Qian, Ivor Tsang
Large Language Models (LLMs) have been applied to time series forecasting tasks, leveraging pre-trained language models as the backbone and incorporating textual data to purportedl…
Fast Direct: Query-Efficient Online Black-box Guidance for Diffusion-model Target Generation
Kim Yong Tan, Yueming Lyu, Ivor Tsang +1
Guided diffusion-model generation is a promising direction for customizing the generation process of a pre-trained diffusion model to address specific downstream tasks. Existing gu…
Mastering Continual Reinforcement Learning through Fine-Grained Sparse Network Allocation and Dormant Neuron Exploration
Chengqi Zheng, Haiyan Yin, Jianda Chen +3
Continual Reinforcement Learning (CRL) is essential for developing agents that can learn, adapt, and accumulate knowledge over time. However, a fundamental challenge persists as ag…
Balanced Image Stylization with Style Matching Score
Yuxin Jiang, Liming Jiang, Shuai Yang +3
We present Style Matching Score (SMS), a novel optimization method for image stylization with diffusion models. Balancing effective style transfer with content preservation is a lo…
Active Sampling for Node Attribute Completion on Graphs
Benyuan Liu, Xu Chen, Yanfeng Wang +3
Node attribute, a type of crucial information for graph analysis, may be partially or completely missing for certain nodes in real world applications. Restoring the missing attribu…
MAGIC: Mastering Physical Adversarial Generation in Context through Collaborative LLM Agents
Yun Xing, Nhat Chung, Jie Zhang +5
Physical adversarial attacks in driving scenarios can expose critical vulnerabilities in visual perception models. However, developing such attacks remains challenging due to diver…
SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments
Yue Cao, Yun Xing, Jie Zhang +5
Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately…
Semantic-Aligned Adversarial Evolution Triangle for High-Transferability Vision-Language Attack
Xiaojun Jia, Sensen Gao, Qing Guo +6
Vision-language pre-training (VLP) models excel at interpreting both images and text but remain vulnerable to multimodal adversarial examples (AEs). Advancing the generation of tra…
Imitation from Diverse Behaviors: Wasserstein Quality Diversity Imitation Learning with Single-Step Archive Exploration
Xingrui Yu, Zhenglin Wan, David Mark Bossens +3
Learning diverse and high-performance behaviors from a limited set of demonstrations is a grand challenge. Traditional imitation learning methods usually fail in this task because…