Imagen de Portada

SineProject: Machine Unlearning for Stable Vision Language Alignment

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Garg, Arpit, Saratchandran, Hemanth, Lucey, Simon
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
por: Xu, Runze, et al.
Publicado: (2026)

Enhancing Transformers Through Conditioned Embedded Tokens
por: Saratchandran, Hemanth, et al.
Publicado: (2025)

Efficient Learning With Sine-Activated Low-rank Matrices
por: Ji, Yiping, et al.
Publicado: (2024)

Structured Initialization for Vision Transformers
por: Zheng, Jianqiao, et al.
Publicado: (2025)

Invertible Neural Warp for NeRF
por: Chng, Shin-Fang, et al.
Publicado: (2024)

Leaner Transformers: More Heads, Less Depth
por: Saratchandran, Hemanth, et al.
Publicado: (2025)

From Activation to Initialization: Scaling Insights for Optimizing Neural Fields
por: Saratchandran, Hemanth, et al.
Publicado: (2024)

Weight Conditioning for Smooth Optimization of Neural Networks
por: Saratchandran, Hemanth, et al.
Publicado: (2024)

Preconditioners for the Stochastic Training of Neural Fields
por: Chng, Shin-Fang, et al.
Publicado: (2024)

Always Skip Attention
por: Ji, Yiping, et al.
Publicado: (2025)

Stable Forgetting: Bounded Parameter-Efficient Unlearning in Foundation Models
por: Garg, Arpit, et al.
Publicado: (2025)

From Tables to Signals: Revealing Spectral Adaptivity in TabPFN
por: Zheng, Jianqiao, et al.
Publicado: (2025)

Rethinking Attention: Polynomial Alternatives to Softmax in Transformers
por: Saratchandran, Hemanth, et al.
Publicado: (2024)

D'OH: Decoder-Only Random Hypernetworks for Implicit Neural Representations
por: Gordon, Cameron, et al.
Publicado: (2024)

Can You Learn to See Without Images? Procedural Warm-Up for Vision Transformers
por: Shinnick, Zachary, et al.
Publicado: (2025)

Structured Initialization for Attention in Vision Transformers
por: Zheng, Jianqiao, et al.
Publicado: (2024)

Convolutional Initialization for Data-Efficient Vision Transformers
por: Zheng, Jianqiao, et al.
Publicado: (2024)

Gradient Descent as a Shrinkage Operator for Spectral Bias
por: Lucey, Simon
Publicado: (2025)

Fast Kernel Scene Flow
por: Li, Xueqian, et al.
Publicado: (2024)

SineLoRA$Δ$: Sine-Activated Delta Compression
por: Gordon, Cameron, et al.
Publicado: (2025)

Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models
por: Balakrishnan, Ravikumar, et al.
Publicado: (2026)

G3Splat: Geometrically Consistent Generalizable Gaussian Splatting
por: Hosseinzadeh, Mehdi, et al.
Publicado: (2025)

Towards Higher Effective Rank in Parameter-efficient Fine-tuning using Khatri--Rao Product
por: Albert, Paul, et al.
Publicado: (2025)

Cross-Modal Attention Guided Unlearning in Vision-Language Models
por: Bhaila, Karuna, et al.
Publicado: (2025)

Object Hallucination-Free Reinforcement Unlearning for Vision-Language Models
por: Jia, Kaidi, et al.
Publicado: (2026)

3D Gaussian Point Encoders
por: James, Jim, et al.
Publicado: (2025)

SMORE: Simultaneous Map and Object REconstruction
por: Chodosh, Nathaniel, et al.
Publicado: (2024)

Trading Positional Complexity vs. Deepness in Coordinate Networks
por: Zheng, Jianqiao, et al.
Publicado: (2022)

Spectral Conditioning of Attention Improves Transformer Performance
por: Saratchandran, Hemanth, et al.
Publicado: (2026)

Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach
por: Mishra, Ashish, et al.
Publicado: (2025)

STRIDE: Training-Free Diversity Guidance via PCA-Directed Feature Perturbation in Single-Step Diffusion Models
por: Yadav, Ankit, et al.
Publicado: (2026)

Suppression or Deletion: A Restoration-Based Representation-Level Analysis of Machine Unlearning
por: Jang, Yurim, et al.
Publicado: (2026)

Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
por: Li, Jiaqi, et al.
Publicado: (2024)

Erasing CLIP Memories: Non-Destructive, Data-Free Zero-Shot class Unlearning in CLIP Models
por: Mishra, Ashish, et al.
Publicado: (2025)

NOVO: Unlearning-Compliant Vision Transformers
por: Roy, Soumya, et al.
Publicado: (2025)

Benchmarking Vision Language Model Unlearning via Fictitious Facial Identity Dataset
por: Ma, Yingzi, et al.
Publicado: (2024)

Rethinking the Role of Spatial Mixing
por: Cazenavette, George, et al.
Publicado: (2025)

Locality Alignment Improves Vision-Language Models
por: Covert, Ian, et al.
Publicado: (2024)

UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
por: Zhang, Yihua, et al.
Publicado: (2024)

Mapillary Vistas Validation for Fine-Grained Traffic Signs: A Benchmark Revealing Vision-Language Model Limitations
por: Garg, Sparsh, et al.
Publicado: (2025)