Image de couverture de livre

TraSCE: Trajectory Steering for Concept Erasure

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Jain, Anubhav, Kobayashi, Yuya, Shibuya, Takashi, Takida, Yuhta, Memon, Nasir, Togelius, Julian, Mitsufuji, Yuki
Format:	Preprint
Publié:	2024
Sujets:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Classifier-Free Guidance inside the Attraction Basin May Cause Memorization
par: Jain, Anubhav, et autres
Publié: (2024)

Forging and Removing Latent-Noise Diffusion Watermarks Using a Single Image
par: Jain, Anubhav, et autres
Publié: (2025)

Efficiency without Compromise: CLIP-aided Text-to-Image GANs with Increased Diversity
par: Kobayashi, Yuya, et autres
Publié: (2025)

MoLA: Motion Generation and Editing with Latent Diffusion Enhanced by Adversarial Training
par: Uchida, Kengo, et autres
Publié: (2024)

Denoising Multi-Beta VAE: Representation Learning for Disentanglement and Generation
par: Uppal, Anshuk, et autres
Publié: (2025)

Alpha-wolves and Alpha-mammals: Exploring Dictionary Attacks on Iris Recognition Systems
par: Banerjee, Sudipta, et autres
Publié: (2023)

SONA: Learning Conditional, Unconditional, and Mismatching-Aware Discriminator
par: Takida, Yuhta, et autres
Publié: (2025)

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
par: Kim, Dongjun, et autres
Publié: (2023)

Improved Object-Centric Diffusion Learning with Registers and Contrastive Alignment
par: Nguyen, Bac, et autres
Publié: (2026)

$\textit{Jump Your Steps}$: Optimizing Sampling Schedule of Discrete Diffusion Models
par: Park, Yong-Hyun, et autres
Publié: (2024)

BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Network
par: Shibuya, Takashi, et autres
Publié: (2023)

HQ-VAE: Hierarchical Discrete Representation Learning with Variational Bayes
par: Takida, Yuhta, et autres
Publié: (2023)

G2D2: Gradient-Guided Discrete Diffusion for Inverse Problem Solving
par: Murata, Naoki, et autres
Publié: (2024)

VCT: Training Consistency Models with Variational Noise Coupling
par: Silvestri, Gianluigi, et autres
Publié: (2025)

FaceCloak: Learning to Protect Face Templates
par: Banerjee, Sudipta, et autres
Publié: (2025)

PAVAS: Physics-Aware Video-to-Audio Synthesis
par: Hyun-Bin, Oh, et autres
Publié: (2025)

A Unified View of Score-Based and Drifting Models
par: Lai, Chieh-Hsin, et autres
Publié: (2026)

Dyadic Mamba: Long-term Dyadic Human Motion Synthesis
par: Tanke, Julian, et autres
Publié: (2025)

PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
par: Kim, Dongjun, et autres
Publié: (2024)

Noise Scheduling as Information-Guided Allocation in Diffusion Training
par: Raya, Gabriel, et autres
Publié: (2026)

Concept-TRAK: Understanding how diffusion models learn concepts through concept-level attribution
par: Park, Yonghyun, et autres
Publié: (2025)

Step-by-Step Video-to-Audio Synthesis via Negative Audio Guidance
par: Hayakawa, Akio, et autres
Publié: (2025)

HumanGif: Single-View Human Diffusion with Generative Prior
par: Hu, Shoukang, et autres
Publié: (2025)

MMDisCo: Multi-Modal Discriminator-Guided Cooperative Diffusion for Joint Audio and Video Generation
par: Hayakawa, Akio, et autres
Publié: (2024)

TRACE: Trajectory-Constrained Concept Erasure in Diffusion Models
par: Carter, Finn
Publié: (2025)

Dynamic Eraser for Guided Concept Erasure in Diffusion Models
par: Gong, Qinghui
Publié: (2026)

GOTCHA: Real-Time Video Deepfake Detection via Challenge-Response
par: Mittal, Govind, et autres
Publié: (2022)

Mass Concept Erasure in Diffusion Models with Concept Hierarchy
par: Tu, Jiahang, et autres
Publié: (2026)

TITAN-Guide: Taming Inference-Time AligNment for Guided Text-to-Video Diffusion Models
par: Simon, Christian, et autres
Publié: (2025)

AutoRefiner: Improving Autoregressive Video Diffusion Models via Reflective Refinement Over the Stochastic Sampling Path
par: Yu, Zhengyang, et autres
Publié: (2025)

Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models
par: Xiong, Lexiang, et autres
Publié: (2025)

SCE-MAE: Selective Correspondence Enhancement with Masked Autoencoder for Self-Supervised Landmark Estimation
par: Yin, Kejia, et autres
Publié: (2024)

Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models
par: Simon, Christian, et autres
Publié: (2026)

Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
par: Seo, Hoigi, et autres
Publié: (2026)

MACE: Mass Concept Erasure in Diffusion Models
par: Lu, Shilin, et autres
Publié: (2024)

A Comprehensive Survey on Concept Erasure in Text-to-Image Diffusion Models
par: Kim, Changhoon, et autres
Publié: (2025)

Mosaic: Compositional Multi-Concept Erasure via Vector Field Blending
par: Ko, Junseok, et autres
Publié: (2026)

TraNCE: Transformative Non-linear Concept Explainer for CNNs
par: Akpudo, Ugochukwu Ejike, et autres
Publié: (2025)

TRCE: Towards Reliable Malicious Concept Erasure in Text-to-Image Diffusion Models
par: Chen, Ruidong, et autres
Publié: (2025)

CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
par: Chen, Yuanhong, et autres
Publié: (2025)