Imagen de Portada

Improving Diffusion Models's Data-Corruption Resistance using Scheduled Pseudo-Huber Loss

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Khrapov, Artem, Popov, Vadim, Sadekova, Tasnima, Yermekova, Assel, Kudinov, Mikhail
Formato:	Preprint
Publicado:	2024
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncoders
por: Aparin, Georgii, et al.
Publicado: (2026)

Training-Free Voice Conversion with Factorized Optimal Transport
por: Lobashev, Alexander, et al.
Publicado: (2025)

Residual-based Adaptive Huber Loss (RAHL) -- Design of an improved Huber loss for CQI prediction in 5G networks
por: Kaviani, Mina, et al.
Publicado: (2024)

Performance Modeling of Data Storage Systems using Generative Models
por: Al-Maeeni, Abdalaziz Rashid, et al.
Publicado: (2023)

Prompt Injection as an Emerging Threat: Evaluating the Resilience of Large Language Models
por: Ganiuly, Daniyal, et al.
Publicado: (2025)

A Huber Loss Minimization Approach to Byzantine Robust Federated Learning
por: Zhao, Puning, et al.
Publicado: (2023)

Trustworthiness Calibration Framework for Phishing Email Detection Using Large Language Models
por: Ganiuly, Daniyal, et al.
Publicado: (2025)

Bootstrapping Diffusion: Diffusion Model Training Leveraging Partial and Corrupted Data
por: Ma, Xudong
Publicado: (2025)

A Universal Knowledge Model and Cognitive Architecture for Prototyping AGI
por: Sukhobokov, Artem, et al.
Publicado: (2024)

Improved Noise Schedule for Diffusion Training
por: Hang, Tiankai, et al.
Publicado: (2024)

Slight Corruption in Pre-training Data Makes Better Diffusion Models
por: Chen, Hao, et al.
Publicado: (2024)

WavefrontDiffusion: Dynamic Decoding Schedule for Improved Reasoning
por: Yang, Haojin, et al.
Publicado: (2025)

Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
por: Aali, Asad, et al.
Publicado: (2024)

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
por: Ahmed, Kareem, et al.
Publicado: (2023)

DiffEM: Learning from Corrupted Data with Diffusion Models via Expectation Maximization
por: Hosseintabar, Danial, et al.
Publicado: (2025)

Self-Improving Diffusion Models with Synthetic Data
por: Alemohammad, Sina, et al.
Publicado: (2024)

Diff-KD: Diffusion-based Knowledge Distillation for Collaborative Perception under Corruptions
por: Lyu, Pengcheng, et al.
Publicado: (2026)

Diffusion Model-Based Multiobjective Optimization for Gasoline Blending Scheduling
por: Fang, Wenxuan, et al.
Publicado: (2024)

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling
por: Xu, Jiawei, et al.
Publicado: (2024)

Predictive Batch Scheduling: Accelerating Language Model Training Through Loss-Aware Sample Prioritization
por: Rasal, Sumedh
Publicado: (2026)

Entropic Time Schedulers for Generative Diffusion Models
por: Stancevic, Dejan, et al.
Publicado: (2025)

Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value
por: Xu, Yixian, et al.
Publicado: (2025)

VR-GPT: Visual Language Model for Intelligent Virtual Reality Applications
por: Konenkov, Mikhail, et al.
Publicado: (2024)

Huber-energy measure quantization
por: Turinici, Gabriel
Publicado: (2022)

Dynamic Learning Rate Scheduling based on Loss Changes Leads to Faster Convergence
por: Subramanian, Shreyas, et al.
Publicado: (2025)

Federated Loss Exploration for Improved Convergence on Non-IID Data
por: Internò, Christian, et al.
Publicado: (2025)

d3LLM: Ultra-Fast Diffusion LLM using Pseudo-Trajectory Distillation
por: Qian, Yu-Yang, et al.
Publicado: (2026)

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum
por: Lu, Wenquan, et al.
Publicado: (2025)

ANT: Adaptive Noise Schedule for Time Series Diffusion Models
por: Lee, Seunghan, et al.
Publicado: (2024)

In Search for Architectures and Loss Functions in Multi-Objective Reinforcement Learning
por: Terekhov, Mikhail, et al.
Publicado: (2024)

In-Context Ensemble Learning from Pseudo Labels Improves Video-Language Models for Low-Level Workflow Understanding
por: Xu, Moucheng, et al.
Publicado: (2024)

StableMotion: Training Motion Cleanup Models with Unpaired Corrupted Data
por: Mu, Yuxuan, et al.
Publicado: (2025)

Improving Complex Reasoning with Dynamic Prompt Corruption: A soft prompt Optimization Approach
por: Fan, Sinan, et al.
Publicado: (2025)

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning
por: Liu, Zeyuan, et al.
Publicado: (2025)

Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
por: Yang, Rui, et al.
Publicado: (2023)

I Can't Believe It's Corrupt: Evaluating Corruption in Multi-Agent Governance Systems
por: P, Vedanta S, et al.
Publicado: (2026)

Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning
por: Xiao, Qian, et al.
Publicado: (2024)

Improving Diffusion-Based Image Editing Faithfulness via Guidance and Scheduling
por: Cho, Hansam, et al.
Publicado: (2025)

Diffusion Model with Perceptual Loss
por: Lin, Shanchuan, et al.
Publicado: (2023)

Engineering an Exact Pseudo-Boolean Model Counter
por: Yang, Suwei, et al.
Publicado: (2023)