KX
Kaidi Xu
cs.LGcs.CVcs.AIcs.CRcs.CLstat.MLeess.SPcs.ITmath.ITmath.OC
On Valency
published · living versionsW_8hf6h7cw·v1 · currentpublished
SEEK: Skill Extraction with Evolving Knowledge against Frontier Science Agents
with Cheng Gui, Xiang Zheng, Yutao Wu, Hanxun Huang +3
1 version
Preprints & journals
79 papers in the corpus · 2017–2026B-PWL: GPU-Batched Branch-and-Bound for Piecewise-Linear Optimization with SOS2 Constraints2608.28988v1 · Yilin Guan, Shuqing Luo, Pingzhi Li et al.2026 · 0 citationsarXiv
KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling2607.09153v1 · Peng Kuang, Haibo Jin, Xiaoyu Han et al.2026 · 0 citationsarXiv
Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos2602.18466v2 · Yixuan Shen, Peng He, Honglu Liu et al.2026 · 1 citationarXiv
The Imitation Game: Using Large Language Models as Chatbots to Combat Chat-Based Cybercrimes2512.21371v1 · Yifan Yao, Baojuan Wang, Jinhao Duan et al.2025 · 0 citationsarXiv
Leave It to the Experts: Detecting Knowledge Distillation via MoE Expert Signatures2510.16968v1 · Pingzhi Li, Morris Yu-Chao Huang, Zhen Tan et al.2025 · 0 citationsarXiv
FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning2510.04040v2 · Xu Shen, Song Wang, Zhen Tan et al.2025 · 0 citationsarXiv
Sparse Neurons Carry Strong Signals of Question Ambiguity in LLMs2509.13664v1 · Zhuoxuan Zhang, Jinhao Duan, Edward Kim et al.2025 · 0 citationsarXiv
LIFT: Automating Symbolic Execution Optimization with Large Language Models for AI Networks2507.04931v1 · Ruoxi Wang, Kun Li, Minghui Xu et al.2025 · 1 citationarXiv
Neural Collapse based Deep Supervised Federated Learning for Signal Detection in OFDM Systems2506.19476v1 · Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li2025 · 0 citationsarXiv
Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models2503.11519v4 · Hao Cheng, Erjia Xiao, Yichi Wang et al.2025 · 0 citationsarXiv
TruthPrInt: Mitigating Large Vision-Language Models Object Hallucination Via Latent Truthful-Guided Pre-Intervention2503.10602v3 · Jinhao Duan, Fei Kong, Hao Cheng et al.2025 · 0 citationsarXiv
MedHallu: A Comprehensive Benchmark for Detecting Medical Hallucinations in Large Language Models2502.14302v1 · Shrey Pandit, Jiawei Xu, Junyuan Hong et al.2025 · 29 citationsarXiv
GuideLLM: Exploring LLM-Guided Conversation with Applications in Autobiography Interviewing2502.06494v1 · Jinhao Duan, Xinyu Zhao, Zhuoxuan Zhang et al.2025 · 1 citationarXiv
Optimizing Robustness and Accuracy in Mixture of Experts: A Dual-Model Approach2502.06832v3 · Xu Zhang, Kaidi Xu, Ziqing Hu et al.2025 · 0 citationsarXiv
Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models2412.05538v2 · Hao Cheng, Erjia Xiao, Jiayan Yang et al.2024 · 1 citationarXiv
Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Models2409.13174v4 · Hao Cheng, Erjia Xiao, Yichi Wang et al.2024 · 0 citationsarXiv
Revisiting Physical-World Adversarial Attack on Traffic Sign Recognition: A Commercial Systems Perspective2409.09860v1 · Ningfei Wang, Shaoyuan Xie, Takami Sato et al.2024 · 11 citationsarXiv
DiffZOO: A Purely Query-Based Black-Box Attack for Red-teaming Text-to-Image Generative Model via Zeroth Order Optimization2408.11071v2 · Pucheng Dang, Xing Hu, Dong Li et al.2024 · 4 citationsarXiv
Transfer Attack for Bad and Good: Explain and Boost Adversarial Transferability across Multimodal Large Language Models2405.20090v5 · Hao Cheng, Erjia Xiao, Jiayan Yang et al.2024 · 0 citationsarXiv
Rescale-Invariant Federated Reinforcement Learning for Resource Allocation in V2X Networks2405.01961v1 · Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li2024 · 4 citationsarXiv
E3: Ensemble of Expert Embedders for Adapting Synthetic Image Detectors to New Generators Using Limited Data2404.08814v2 · Aref Azizpour, Tai D. Nguyen, Manil Shrestha et al.2024 · 4 citationsarXiv
Decoding Compressed Trust: Scrutinizing the Trustworthiness of Efficient LLMs Under Compression2403.15447v3 · Junyuan Hong, Jinhao Duan, Chenhui Zhang et al.2024 · 5 citationsarXiv
Medical Unlearnable Examples: Securing Medical Data from Unauthorized Training via Sparsity-Aware Local Masking2403.10573v2 · Weixiang Sun, Yixin Liu, Zhiling Yan et al.2024 · 0 citationsarXiv
Unveiling Typographic Deceptions: Insights of the Typographic Vulnerability in Large Vision-Language Model2402.19150v3 · Hao Cheng, Erjia Xiao, Jindong Gu et al.2024 · 0 citationsarXiv
Word-Sequence Entropy: Towards Uncertainty Estimation in Free-Form Medical Question Answering Applications and Beyond2402.14259v2 · Zhiyuan Wang, Jinhao Duan, Chenxi Yuan et al.2024 · 15 citationsarXiv
GTBench: Uncovering the Strategic Reasoning Limitations of LLMs via Game-Theoretic Evaluations2402.12348v2 · Jinhao Duan, Renming Zhang, James Diffenderfer et al.2024 · 4 citationsarXiv
Dynamic Adversarial Attacks on Autonomous Driving Systems2312.06701v3 · Amirhosein Chahe, Chenan Wang, Abhishek Jeyapratap et al.2023 · 18 citationsarXiv
A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly2312.02003v3 · Yifan Yao, Jinhao Duan, Kaidi Xu et al.2023 · 1,075 citationsarXiv
Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?2312.00084v2 · Zhengyue Zhao, Jinhao Duan, Kaidi Xu et al.2023 · 16 citationsarXiv
ACT-Diffusion: Efficient Adversarial Consistency Training for One-step Diffusion Models2311.14097v3 · Fei Kong, Jinhao Duan, Lichao Sun et al.2023 · 3 citationsarXiv
Stable Unlearnable Example: Enhancing the Robustness of Unlearnable Examples via Stable Error-Minimizing Noise2311.13091v2 · Yixin Liu, Kaidi Xu, Xun Chen et al.2023 · 12 citationsarXiv
PINNs-Based Uncertainty Quantification for Transient Stability Analysis2311.12947v1 · Ren Wang, Ming Zhong, Kaidi Xu et al.2023 · 0 citationsarXiv
Pursing the Sparse Limitation of Spiking Deep Learning Structures2311.12060v1 · Hao Cheng, Jiahang Cao, Erjia Xiao et al.2023 · 0 citationsarXiv
Federated Reinforcement Learning for Resource Allocation in V2X Networks2310.09858v1 · Kaidi Xu, Shenglong Zhou, Geoffrey Ye Li2023 · 15 citationsarXiv
RBFormer: Improve Adversarial Robustness of Transformer by Robust Bias2309.13245v1 · Hao Cheng, Jinhao Duan, Hui Li et al.2023 · 2 citationsarXiv
Semantic Adversarial Attacks via Diffusion Models2309.07398v1 · Chenan Wang, Jinhao Duan, Chaowei Xiao et al.2023 · 5 citationsarXiv
Does Physical Adversarial Example Really Matter to Autonomous Driving? Towards System-Level Effect of Adversarial Object Evasion Attack2308.11894v1 · Ningfei Wang, Yunpeng Luo, Takami Sato et al.2023 · 36 citationsarXiv
ReMiND: Recovery of Missing Neuroimaging using Diffusion Models with Application to Alzheimer's Disease.37662259 · Yuan, Chenxi, Duan, Jinhao, Tustison, Nicholas J et al.2025 · 13 citationsmedRxiv : the preprint server for health sciences. 2023
Exposing the Fake: Effective Diffusion-Generated Images Detection2307.06272v1 · Ruipeng Ma, Jinhao Duan, Fei Kong et al.2023 · 16 citationsarXiv
Shifting Attention to Relevance: Towards the Predictive Uncertainty Quantification of Free-Form Large Language Models2307.01379v3 · Jinhao Duan, Hao Cheng, Shiqi Wang et al.2023 · 52 citationsarXiv
Unlearnable Examples Give a False Sense of Data Privacy: Understanding and Relearning2306.02064v2 · Pucheng Dang, Xing Hu, Kaidi Xu et al.2023 · 0 citationsarXiv
Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitation2306.01902v2 · Zhengyue Zhao, Jinhao Duan, Xing Hu et al.2023 · 9 citationsarXiv
Caterpillar: A Pure-MLP Architecture with Shifted-Pillars-Concatenation2305.17644v3 · Jin Sun, Xiaoshuang Shi, Zhiyuan Wang et al.2023 · 1 citationarXiv
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization2305.18355v2 · Fei Kong, Jinhao Duan, RuiPeng Ma et al.2023 · 10 citationsarXiv
Improve Video Representation with Temporal Adversarial Augmentation2304.14601v2 · Jinhao Duan, Quanfu Fan, Hao Cheng et al.2023 · 3 citationsarXiv
Are Diffusion Models Vulnerable to Membership Inference Attacks?2302.01316v2 · Jinhao Duan, Fei Kong, Shiqi Wang et al.2023 · 29 citationsarXiv
Distributed-Training-and-Execution Multi-Agent Reinforcement Learning for Power Control in HetNet2212.07967v1 · Kaidi Xu, Nguyen Van Huynh, Geoffrey Ye Li2022 · 16 citationsarXiv
Secrecy Rate Maximization of RIS-assisted SWIPT Systems: A Two-Timescale Beamforming Design Approach2211.16666v1 · Ming-Min Zhao, Kaidi Xu, Yunlong Cai et al.2022 · 37 citationsarXiv
Audit and Improve Robustness of Private Neural Networks on Encrypted Data2209.09996v1 · Jiaqi Xue, Lei Xu, Lin Chen et al.2022 · 1 citationarXiv
Real-Time Robust Video Object Detection System Against Physical-World Adversarial Attacks2208.09195v1 · Husheng Han, Xing Hu, Kaidi Xu et al.2022 · 5 citationsarXiv
Career total: 124 works. 79 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.