Imagen de Portada

Data Attribution for Diffusion Models: Timestep-induced Bias in Influence Estimation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xie, Tong, Li, Haoyu, Bai, Andrew, Hsieh, Cho-Jui
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

When Distance Distracts: Representation Distance Bias in BT-Loss for Reward Models
por: Xie, Tong, et al.
Publicado: (2025)

CLUE: Concept-Level Uncertainty Estimation for Large Language Models
por: Wang, Yu-Hsiang, et al.
Publicado: (2024)

Embedding Space Selection for Detecting Memorization and Fingerprinting in Generative Models
por: He, Jack, et al.
Publicado: (2024)

Concepts or Skills? Rethinking Instruction Selection for Multi-modal Models
por: Bai, Andrew, et al.
Publicado: (2025)

An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuning
por: Bai, Andrew, et al.
Publicado: (2024)

On the Loss of Context-awareness in General Instruction Fine-tuning
por: Wang, Yihan, et al.
Publicado: (2024)

Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control
por: Shi, Zhouxing, et al.
Publicado: (2024)

Mitigating Bias in Dataset Distillation
por: Cui, Justin, et al.
Publicado: (2024)

Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs
por: Hong, Yunqi, et al.
Publicado: (2025)

Influence Functions for Scalable Data Attribution in Diffusion Models
por: Mlodozeniec, Bruno, et al.
Publicado: (2024)

On Discrete Prompt Optimization for Diffusion Models
por: Wang, Ruochen, et al.
Publicado: (2024)

Concept Gradient: Concept-based Interpretation Without Linear Assumption
por: Bai, Andrew, et al.
Publicado: (2022)

Diffusion Attribution Score: Evaluating Training Data Influence in Diffusion Models
por: Lin, Jinxu, et al.
Publicado: (2024)

Accumulative SGD Influence Estimation for Data Attribution
por: Shi, Yunxiao, et al.
Publicado: (2025)

Daunce: Data Attribution through Uncertainty Estimation
por: Pan, Xingyuan, et al.
Publicado: (2025)

Solving for X and Beyond: Can Large Language Models Solve Complex Math Problems with More-Than-Two Unknowns?
por: Kao, Kuei-Chun, et al.
Publicado: (2024)

Efficient Frameworks for Generalized Low-Rank Matrix Bandit Problems
por: Kang, Yue, et al.
Publicado: (2024)

Low-rank Matrix Bandits with Heavy-tailed Rewards
por: Kang, Yue, et al.
Publicado: (2024)

Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits
por: Kang, Yue, et al.
Publicado: (2023)

Imperfect Influence, Preserved Rankings: A Theory of TRAK for Data Attribution
por: Tong, Han, et al.
Publicado: (2026)

Provably Robust Training of Quantum Circuit Classifiers Against Parameter Noise
por: Tecot, Lucas, et al.
Publicado: (2025)

Nonparametric Data Attribution for Diffusion Models
por: Zhao, Yutian, et al.
Publicado: (2025)

Fine-tuning Diffusion Policies with Backpropagation Through Diffusion Timesteps
por: Yang, Ningyuan, et al.
Publicado: (2025)

Do Synthetic Trajectories Reflect Real Reward Hacking? A Systematic Study on Monitoring In-the-Wild Hacking in Code Generation
por: Li, Lichen, et al.
Publicado: (2026)

Rethinking Timesteps Samplers and Prediction Types
por: Xie, Bin, et al.
Publicado: (2025)

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach
por: Liu, Yaofang, et al.
Publicado: (2024)

Influence Dynamics and Stagewise Data Attribution
por: Lee, Jin Hwa, et al.
Publicado: (2025)

Adaptive Non-uniform Timestep Sampling for Accelerating Diffusion Model Training
por: Kim, Myunsoo, et al.
Publicado: (2024)

FlexAct: Why Learn when you can Pick?
por: Kumar, Ramnath, et al.
Publicado: (2026)

Model Generalization on Text Attribute Graphs: Principles with Large Language Models
por: Wang, Haoyu, et al.
Publicado: (2025)

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
por: Kwon, Yongchan, et al.
Publicado: (2023)

DiffPro: Joint Timestep and Layer-Wise Precision Optimization for Efficient Diffusion Inference
por: Amin, Farhana, et al.
Publicado: (2025)

POME: Post Optimization Model Edit via Muon-style Projection
por: Liu, Yong, et al.
Publicado: (2025)

AutoRubric-T2I: Robust Rule-Based Reward Model for Text-to-Image Alignment
por: Kao, Kuei-Chun, et al.
Publicado: (2026)

Revisiting Data Attribution for Influence Functions
por: Zhu, Hongbo, et al.
Publicado: (2025)

Integrated Influence: Data Attribution with Baseline
por: Yang, Linxiao, et al.
Publicado: (2025)

Adversarial Examples Detection with Bayesian Neural Network
por: Li, Yao, et al.
Publicado: (2021)

Bayesian Influence Functions for Hessian-Free Data Attribution
por: Kreer, Philipp Alexander, et al.
Publicado: (2025)

TMPQ-DM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models
por: Sun, Haojun, et al.
Publicado: (2024)

Adversarial Bias: Data Poisoning Attacks on Fairness
por: Chan, Eunice, et al.
Publicado: (2025)