ACML 2025

79 papers

$δ$-STEAL: LLM Stealing Attack with Local Differential Privacy Kieu Dang, Phung Lai, Hai Phan, Yelong Shen, Ruoming Jin, Abdallah Khreishah

Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language Model Sihao Wu, Gaojie Jin, Wei Huang, Jianhong Wang, Xiaowei Huang

AHSG: Adversarial Attack on High-Level Semantics in Graph Neural Networks Kai Yuan, Jiahao Zhang, Yidi Wang, Pei Xiaobing

Asymptotically Optimal Problem-Dependent Bandit Policies for Transfer Learning Adrien Prevost, Timothée Mathieu, Odalric-Ambrym Maillard

Balancing Knowledge Updates: Toward Unified Modular Editing in LLMs Jiahao Liu, Zijian Wang, Zhao Kuo, Dong Hu

Beyond UDA: Examining Temporal and Frequency Representations in Time Series Transfer Ching Chieh Tsao, Fang-Yi Su, Jung-Hsien Chiang

Both Asymptotic and Non-Asymptotic Convergence of Quasi-Hyperbolic Momentum Using Increasing Batch Size Kento Imaizumi, Hideaki Iiduka

Boundary-Aware Refinement with Environment-Robust Adapter Tuning for Underwater Instance Segmentation Pin-Chi Pan, Soo-Chang Pei

Bridging the Gap Between Learning and Inference for Diffusion-Based Molecule Generation Peidong Liu, Wenbo Zhang, Wei Ju, Jiancheng Lv, Xianggen Liu

CAD-HLLM: Generating Executable CAD from Text with Hierarchical LLM Planning Zhuo Zuo, Yantao Gan, Junfeng Long, Xianggen Liu

CAP: Conformalized Abstention Policies for Context-Adaptive Risk Management for LLMs and VLMs Sina Tayebati, Divake Kumar, Nastaran Darabi, Dinithi Jayasuriya, Theja Tulabandhula, Ranganath Krishnan, Amit Ranjan Trivedi

ChameleonBench: Quantifying Alignment Faking in Large Language Models Archie Chaudhury, Shikhar Shiromani

Continual Pre-Training Is (not) What You Need in Domain Adaptation Pin-Er Chen, Da Chen Lian, Shu-Kai Hsieh, Sieh-Chuen Huang, Hsuan-Lei Shao, Jun Wei Chiu, Yang-Hsien Lin, Zih-Ching Chen, Cheng-Kuang Lee, Eddie Tzungchi Huang, Simon See

CrossPyEval: Enhancing LLM-Based Evaluation of Low-Resource Code via Code Translation Weijie Wu, Ling-I Wu, Guoqiang Li

CryChime: When Large Language Models Learn to Listen to Distant Cries - A Counterfactual PEFT Framework for Urgent Need Detection in Disaster Social Media Junhong Cai, Geng Zhao, Jiaxin Li

D$^3$epth: Distilling Diffusion Models for Efficient Depth Estimation Through a Two-Stage Approach Bo-Chih Chuang, Wei-Tung Lin, Shang-Fu Chen, Kailung Hua

Data-Centric Graph Condensation via Diffusion Matching Hengrui Zhang, Philip S. Yu

Data-Dependent Algorithmic Robustness Analysis of Pairwise Learning Donglai Wu, Runqiu Wu, Yunwen Lei

Deviation-Based Multiple Coefficient Item Mixer for Heterogeneous Set-to-Set Matching Hirotaka Hachiya, Kajishiro Yukito

Direct Quantized Training of Language Models with Stochastic Rounding Kaiyan Zhao, Tsuguchika Tabaru, Kenichi Kobayashi, Takumi Honda, Masafumi Yamazaki, Yoshimasa Tsuruoka

Domain Adaptation with Hybrid Modeling for Learning Dynamical Systems Akira Osaka, Naoya Takeishi, Takehisa Yairi

Dual Color Space Underwater Image Enhancement Network Jiaying He, K. L. Eddie Law

Dual-Module Collaborative LoRA for Effective Large Language Model Fine-Tuning Lecheng Cao, Junhao Zhang, Xiaohan Zhang, Huaxiong Li

Efficient Subsampling for GNN Downstream Tasks Hirad Daneshvar, Reza Samavi

EIKEA:Enhancing In-Context Knowledge Editing by Agents Zibo Xu, Xin Wang

Emergence of the Primacy Effect in Structured State-Space Models Takashi Morita

Enhanced Blind Image Restoration with Channel Attention Transformers and Multi-Scale Attention Prompt-Based Learning Jianhua Hu, K. L. Eddie Law

Explainable Dynamic Graph Neural Networks for Predictive Maintenance in Vehicle Chassis Systems Wu You, Junwei Su, Sirui Zhang, Zhijian Li

Faster Convergence of Riemannian Stochastic Gradient Descent with Increasing Batch Size Kanata Oowada, Hideaki Iiduka

FeelNet: A Lightweight Fast Fourier Transform EEG-Based Emotion Recognition Network Xueyao Wang, Xiuding Cai, Yaoyao Zhu, Yu Yao

FG-MSTGNN: Cross-Subject EEG Emotion Recognition via Frequency-Guided Multi-Period Spatial-Temporal Graph Neural Network Chenchen Zhang, Yanrong Hao, Xin Wen, Mengni Zhou, Fei Yuan, Rui Cao

FIRM: Fusion-Injected Residual Memory Brings Token-Level Alignment to Unsupervised VI-ReID Ze Rong, Xiaofeng Shen, Haoyang Qin, Yue Xu, Hongjun Li, Lei Ma

GIIM: A Graph Information Integration Method for Chinese-Kazakh CLIR Ping Hu, He Yang, Changle Yin, Tao Wang, Yuchao Chen

Graph Mediator Networks Bridging Local and Global Semantics via Serial Message Passing Jiangfeng Sun, SiHao He, Yanlong Lin, Zhonghong Ou, Meina Song

Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition Razieh Ghaedi, AmirReza BabaAhmadi, Reyer Zwiggelaar, Xinqi Fan, Nashid Alam

Harnessing Large Language and Vision-Language Models for Robust Out-of-Distribution Detection Pei-Kang Lee, Jun-Cheng Chen, Ja-ling Wu

High-Order Consistency-Guided User Identity Linkage with Large Language Model Tianpeng Li, Xiangjun Pei, Yinghui Wang, Qiyao Peng, Wenjun Wang

HIPPD: Brain-Inspired Hierarchical Information Processing for Personality Detection Guanming Chen, Lingzhi Shen, Xiaohao Cai, Imran Razzak, Shoaib Jameel

Increasing Batch Size Improves Convergence of Stochastic Gradient Descent with Momentum Keisuke Kamo, Hideaki Iiduka

Information-Based Exploration via Random Features for Reinforcement Learning Waris Radji, Odalric-Ambrym Maillard

Iterative Selection with Self-Review for Vocabulary Test Distractor Generation Yu-Cheng Liu, An-Zi Yen

Jailbreak Defense in LLM via Attention Head Analysis and Selective Intervention Masaki Arai, Toshiki Shibahara, Daiki Chiba, Mitsuaki Akiyama, Masato Uchida

JurisGraph Insight Engine 1.0v: A Legal Question Answering System Based on Large Language Models and Knowledge Graphs Haiguang Zhang

Kairos: Redefining Event and Time Prediction with Language Modeling Akash Gupta, Sahil Verma, Sumit Bisht, Nitika Verma, Purav Aggarwal, Venkata Phanindra Kumar Grandhi, Abhishek Persad

Kernel-Based Enhanced Oversampling Method for Imbalanced Classification Li Wenjie, Hanlin Wang, Sibo Zhu, Zhijian Li

KVCrush: Key Value Cache Size-Reduction Using Similarity in Head-Behaviour Gopi Krishna Jha, Sameh Gobriel, Liubov Talamanova, Nilesh Jain

Label-Perceptive Adversarial Domain Adaptation for Named Entity Recognition in Traditional Chinese Medicine: Dataset and Approach Yu Tong

Learning Curves of Classification Metrics Based on Confusion Matrices Yan Xue, Ruibo Wang, Xuefei Cao, Jing Yang, Jihong Li

Local Shuffled Skeleton Position Embedding Vision Transformer for Human Activity Recognition Zihui Yan, Xiyu Shi, Varuna De SIlva De SIlva

MagicMask: A Fast and High-Fidelity Face Swapping Method Robust to Face Pose Jongmin Yu, Anoushka Harit, Jiankang Deng, Shan Luo, Jinhong Yang, Zhongtian Sun

Mega-CE$^2$ : A Multimodal Heterogeneous Aggregation Framework for End-Edge-Cloud Computing Zinuo Cheng, Haodi Wang, Rongfang Bie

MKD: Multi-Knowledge Distillation for Real-Time Object Detection on Edge Devices Yanjun Xu, Chunqi Tian, Xuhui Xia, Yaoru Sun

Multi-Play Multi-Armed Bandits with Shareable Arm Capacities Revisited: Settling Scarce Capacity Hanyang Li, Hong Xie, Defu Lian

Multi-Thresholding Good Arm Identification with Bandit Feedback Xuanke Jiang, Sherief Hashima, Kohei Hatano, Eiji Takimoto

Multi-View Privileged Information-Based Representation Learning for Liver Cancer Diagnosis Bangming Gong, Huo Yan

On the Privacy-Preserving Generalized Eigenvalue Problem Wei-Hong Chen, Yu-Feng Huang, Chen Yu Lee, Hung Yi Chen, Shi-Chun Tsai

Optimizing Trajectory Matching Distillation via Parameter Difference-Driven Pruning Xinyu Cao, He Liu, Liyuan Zhang, Zhongliang Kan

Outcome-Based Semifactuals for Reinforcement Learning Yanzhe Bekkemoen, Helge Langseth

Overcoming Domain Knowledge Forgetting in Continual Test-Time Adaptation via Siamese Networks Zhihong Xu, Wenjun Shi, Dongchen Zhu, Xiaolin Zhang, Lei Wang, Jiamao Li

POIL:Preference Optimization for Imitation Learning Kuanyen Liu, Renjyun Huang, Chang Chih Meng, I-Chen Wu

Policy Iteration for Two-Player General-Sum Stochastic Stackelberg Games Mikoto Kudo, Youhei Akimoto

Punching Above Precision: Small Quantized Model Distillation with Learnable Regularizer Abdur Rehman, S M A Sharif, Md Abdur Rahaman, Mohamed Jismy Aashik Rasool, Seongwan Kim, Jaeho Lee

Reduced-Rank Factorized Fourier Neural Operator Chieh-An Chou, Lu-Hung Chen

Relaxed Transition Kernels Can Cure Underestimation in Adversarial Offline Reinforcement Learning Ziyu Wang, Ping-Chun Hsieh, Yu-Shuen Wang, Yun-Hsuan Lien

ReSa2: A Two-Stage Retrieval-Sampling Algorithm for Negative Sampling in Dense Retrieval Muyang Li, Zihan Wang, Sijia Chen, Yijun Chen, Jiayu Li, Yiming Qiao, Xinyi Li, Bo Ji

Risk-Averse Best Arm Set Identification with Fixed Budget and Fixed Confidence Shunta Nonaga, Koji Tabata, Yuta Mizuno, Tamiki Komatsuzaki

Round Attention: A Novel Round-Level Attention Mechanism to Accelerate LLM Inference Yaohua Tang, Zhicheng Hu, Kun Cheng, Fan Mo, Qiheng Lyu, Hua Wang, Zhi Chen

RSTSIC: Reparameterized Swin Transformer Stereo Image Compression Yuxuan Zhao, Junwei Zhou, Jiaxin Li, Cheng Tan, Jianwen Xiang

SAFE: Spiking Neural Network-Based Audio Fidelity Evaluation Aaditya Arunkumar Khant, Raveen Wijewickrama, Murtuza Jadliwala

Sampling Boundary for Causal Effect Estimation Yue Yin, Jiaoyun Yang, Ning An, Lian Li

SEMINAR: SEMantic InformatioN Augmented JailbReak Attack in LLM Junjie Yang, Fenghua Weng, Yue Xu, Wenjie Wang

SparseSegNet: A Boundary-Aware Lightweight Segmentation Architecture for Skin Lesions Soma Dasgupta, Swarnava Dey, Arijit Mukherjee, Arpan Pal

Suicidal Posts Detection System Incorporating Psychological Risk Factors Chih-Ning Chen, Chieh-Jou Lin, Kunhua Lee, Yu Ping Ma, Kuo-Liang Ou, Daw-Wei Wang

TAEGAN: Revisit GANs for Tabular Data Generation Jiayu Li, Zilong Zhao, Kevin Yee, Uzair Javaid, Biplab Sikdar

Target Return Optimizer for Multi-Game Decision Transformer Kensuke Tatematsu, Akifumi Wachi

The Great Contradiction Showdown: How Jailbreak and Stealth Wrestle in Vision-Language Models? Ching-Chia Kao, Chia-Mu Yu, Chun-Shien Lu, Chu-Song Chen

TLSD: Breaking the Limit of Topological Lane Mapping with Graph Knowledge and Distance Awareness Anh Nguyen Trong, Gia-Bao Phan, Minh Tri Huynh, Duc Dung Nguyen

Towards Robust and Scalable Knowledge Editing in Text-to-Image Diffusion Models YiFei Liu, Xin Wang

Training Data Soft Selection via Joint Density Ratio Estimation Ryuta Matsuno