Cover Image

AEGIS: Anchor-Enforced Gradient Isolation for Knowledge-Preserving Vision-Language-Action Fine-Tuning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Singh, Guransh
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Efficient Fine-Tuning with Domain Adaptation for Privacy-Preserving Vision Transformer
by: Nagamori, Teru, et al.
Published: (2024)

Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
by: Kim, Moo Jin, et al.
Published: (2025)

FedVLMBench: Benchmarking Federated Fine-Tuning of Vision-Language Models
by: Zheng, Weiying, et al.
Published: (2025)

Rethinking Fine-Tuning: Unlocking Hidden Capabilities in Vision-Language Models
by: Zhang, Mingyuan, et al.
Published: (2025)

AnchorFormer: Differentiable Anchor Attention for Efficient Vision Transformer
by: Shan, Jiquan, et al.
Published: (2025)

Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
by: Schlarmann, Christian, et al.
Published: (2024)

Fairness-Aware Fine-Tuning of Vision-Language Models for Medical Glaucoma Diagnosis
by: Gu, Zijian, et al.
Published: (2025)

Preserving Domain Generalization in Fine-Tuning via Joint Parameter Selection
by: Pan, Bin, et al.
Published: (2025)

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
by: Jie, Shibo, et al.
Published: (2024)

pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models
by: Ghiasvand, Sajjad, et al.
Published: (2025)

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning
by: Peleg, Amit, et al.
Published: (2025)

Taming Noise-Induced Prototype Degradation for Privacy-Preserving Personalized Federated Fine-Tuning
by: Wang, Yuhua, et al.
Published: (2026)

How Does Fine-Tuning Impact Out-of-Distribution Detection for Vision-Language Models?
by: Ming, Yifei, et al.
Published: (2023)

SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge
by: Yousaf, Adeel, et al.
Published: (2025)

Semi-Supervised Fine-Tuning of Vision Foundation Models with Content-Style Decomposition
by: Drozdova, Mariia, et al.
Published: (2024)

Kernelized Sparse Fine-Tuning with Bi-level Parameter Competition for Vision Models
by: Shen, Shufan, et al.
Published: (2025)

LLARVA: Vision-Action Instruction Tuning Enhances Robot Learning
by: Niu, Dantong, et al.
Published: (2024)

Enhancing Generalization in Vision-Language-Action Models by Preserving Pretrained Representations
by: Grover, Shresth, et al.
Published: (2025)

Fine-Tuning a Large Vision-Language Model for Artwork's Scoring and Critique
by: Zhang, Zhehan, et al.
Published: (2026)

Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark
by: Xin, Yi, et al.
Published: (2024)

Enhancing Parameter-Efficient Fine-Tuning of Vision Transformers through Frequency-Based Adaptation
by: Ly, Son Thai, et al.
Published: (2024)

Benchmarking Vision, Language, & Action Models in Procedurally Generated, Open Ended Action Environments
by: Guruprasad, Pranav, et al.
Published: (2025)

Unified Knowledge Distillation Framework: Fine-Grained Alignment and Geometric Relationship Preservation for Deep Face Recognition
by: Mishra, Durgesh, et al.
Published: (2025)

Language Integration in Fine-Tuning Multimodal Large Language Models for Image-Based Regression
by: Jennings, Roy H., et al.
Published: (2025)

Pixels Versus Priors: Controlling Knowledge Priors in Vision-Language Models through Visual Counterfacts
by: Golovanevsky, Michal, et al.
Published: (2025)

On the Robustness Tradeoff in Fine-Tuning
by: Li, Kunyang, et al.
Published: (2025)

Continual Learning with Vision-Language Models via Semantic-Geometry Preservation
by: He, Chiyuan, et al.
Published: (2026)

Understanding the Fine-Grained Knowledge Capabilities of Vision-Language Models
by: Ghosh, Dhruba, et al.
Published: (2026)

Gradient-based Fine-Tuning through Pre-trained Model Regularization
by: Liu, Xuanbo, et al.
Published: (2025)

HyperFlow: Gradient-Free Emulation of Few-Shot Fine-Tuning
by: Kim, Donggyun, et al.
Published: (2025)

Towards Compatible Fine-tuning for Vision-Language Model Updates
by: Wang, Zhengbo, et al.
Published: (2024)

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
by: Tang, Zihao, et al.
Published: (2024)

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
by: Mannes, Mahmoud
Published: (2026)

Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
by: Yanuka, Moran, et al.
Published: (2024)

Model-agnostic Adversarial Attack and Defense for Vision-Language-Action Models
by: Xu, Haochuan, et al.
Published: (2025)

EaqVLA: Encoding-aligned Quantization for Vision-Language-Action Models
by: Jiang, Feng, et al.
Published: (2025)

VCM: Vision Concept Modeling Based on Implicit Contrastive Learning with Vision-Language Instruction Fine-Tuning
by: Luo, Run, et al.
Published: (2025)

Directional Gradient Projection for Robust Fine-Tuning of Foundation Models
by: Huang, Chengyue, et al.
Published: (2025)

Tactile Modality Fusion for Vision-Language-Action Models
by: Morissette, Charlotte, et al.
Published: (2026)

ReMem: Mutual Information-Aware Fine-tuning of Pretrained Vision Transformers for Effective Knowledge Distillation
by: Dong, Chengyu, et al.
Published: (2025)