Copertina

Explainable Synthetic Image Detection through Diffusion Timestep Ensembling

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wu, Yixin, Zhang, Feiran, Shi, Tianyuan, Yin, Ruicheng, Wang, Zhenghua, Gan, Zhenliang, Wang, Xiaohua, Lv, Changze, Zheng, Xiaoqing, Huang, Xuanjing
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence Computation and Language
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
di: Zhang, Feiran, et al.
Pubblicazione: (2026)

Improving Continual Pre-training Through Seamless Data Packing
di: Yin, Ruicheng, et al.
Pubblicazione: (2025)

Searching for Best Practices in Retrieval-Augmented Generation
di: Wang, Xiaohua, et al.
Pubblicazione: (2024)

Layer-Specific Scaling of Positional Encodings for Superior Long-Context Modeling
di: Wang, Zhenghua, et al.
Pubblicazione: (2025)

UPLex: Fine-Grained Personality Control in Large Language Models via Unsupervised Lexical Modulation
di: Li, Tianlong, et al.
Pubblicazione: (2023)

Revisiting Jailbreaking for Large Language Models: A Representation Engineering Perspective
di: Li, Tianlong, et al.
Pubblicazione: (2024)

Towards Biologically Plausible Computing: A Comprehensive Comparison
di: Lv, Changze, et al.
Pubblicazione: (2024)

Dendritic Localized Learning: Toward Biologically Plausible Algorithm
di: Lv, Changze, et al.
Pubblicazione: (2025)

Aligning Large Language Models with Human Preferences through Representation Engineering
di: Liu, Wenhao, et al.
Pubblicazione: (2023)

Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern Generators
di: Lv, Changze, et al.
Pubblicazione: (2024)

Efficient and Effective Time-Series Forecasting with Spiking Neural Networks
di: Lv, Changze, et al.
Pubblicazione: (2024)

Enhancing the Capability and Robustness of Large Language Models through Reinforcement Learning-Driven Query Refinement
di: Wang, Xiaohua, et al.
Pubblicazione: (2024)

Spiking Convolutional Neural Networks for Text Classification
di: Lv, Changze, et al.
Pubblicazione: (2024)

Decoding Continuous Character-based Language from Non-invasive Brain Recordings
di: Zhang, Cenyuan, et al.
Pubblicazione: (2024)

Promoting Data and Model Privacy in Federated Learning through Quantized LoRA
di: Zhu, JianHao, et al.
Pubblicazione: (2024)

Toward Relative Positional Encoding in Spiking Transformers
di: Lv, Changze, et al.
Pubblicazione: (2025)

Biologically Plausible Learning via Bidirectional Spike-Based Distillation
di: Lv, Changze, et al.
Pubblicazione: (2025)

SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network
di: Lv, Changze, et al.
Pubblicazione: (2023)

Beyond Single Labels: Improving Conversational Recommendation through LLM-Powered Data Augmentation
di: Xu, Haozhe, et al.
Pubblicazione: (2025)

Advancing Parameter Efficiency in Fine-tuning via Representation Editing
di: Wu, Muling, et al.
Pubblicazione: (2024)

Progressive Mastery: Customized Curriculum Learning with Guided Prompting for Mathematical Reasoning
di: Wu, Muling, et al.
Pubblicazione: (2025)

SATER: A Self-Aware and Token-Efficient Approach to Routing and Cascading
di: Shen, Yuanzhe, et al.
Pubblicazione: (2025)

SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation
di: Lv, Changze, et al.
Pubblicazione: (2023)

Benchmark^2: Systematic Evaluation of LLM Benchmarks
di: Qian, Qi, et al.
Pubblicazione: (2026)

TASR: Timestep-Aware Diffusion Model for Image Super-Resolution
di: Lin, Qinwei, et al.
Pubblicazione: (2024)

AsyncDiff: Asynchronous Timestep Conditioning for Enhanced Text-to-Image Diffusion Inference
di: Xu, Longhuan, et al.
Pubblicazione: (2025)

Timestep-Aware Diffusion Model for Extreme Image Rescaling
di: Wang, Ce, et al.
Pubblicazione: (2024)

TripTailor: A Real-World Benchmark for Personalized Travel Planning
di: Shen, Yuanzhe, et al.
Pubblicazione: (2025)

Timestep-Compressed Attack on Spiking Neural Networks through Timestep-Level Backpropagation
di: Kang, Donghwa, et al.
Pubblicazione: (2025)

Exploring Multi-Timestep Multi-Stage Diffusion Features for Hyperspectral Image Classification
di: Zhou, Jingyi, et al.
Pubblicazione: (2023)

Timestep-Aware Correction for Quantized Diffusion Models
di: Yao, Yuzhe, et al.
Pubblicazione: (2024)

Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation
di: Lv, Changze, et al.
Pubblicazione: (2026)

Diffusion Models are Geometry Critics: Single Image 3D Editing Using Pre-Trained Diffusion Priors
di: Wang, Ruicheng, et al.
Pubblicazione: (2024)

Populating cellular metamaterials on the extrema of attainable elasticity through neuroevolution
di: Yan, Maohua, et al.
Pubblicazione: (2024)

Compute Only 16 Tokens in One Timestep: Accelerating Diffusion Transformers with Cluster-Driven Feature Caching
di: Zheng, Zhixin, et al.
Pubblicazione: (2025)

Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
di: Pan, Kaihang, et al.
Pubblicazione: (2025)

ERTACache: Error Rectification and Timesteps Adjustment for Efficient Diffusion
di: Peng, Xurui, et al.
Pubblicazione: (2025)

TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models
di: Huang, Haocheng, et al.
Pubblicazione: (2024)

Tuning Timestep-Distilled Diffusion Model Using Pairwise Sample Optimization
di: Miao, Zichen, et al.
Pubblicazione: (2024)

Ensembling LLM-Induced Decision Trees for Explainable and Robust Error Detection
di: Wang, Mengqi, et al.
Pubblicazione: (2025)