Copertina

Attention Misses Visual Risk: Risk-Adaptive Steering for Multimodal Safety Alignment

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Park, Jonghyun, Seo, Minhyuk, Yeo, Chaewon, Choi, Jonghyun
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
di: Seo, Minhyuk, et al.
Pubblicazione: (2024)

OASIS: Online Sample Selection for Continual Visual Instruction Tuning
di: Lee, Minjae, et al.
Pubblicazione: (2025)

TTA-DAME: Test-Time Adaptation with Domain Augmentation and Model Ensemble for Dynamic Driving Conditions
di: Jeon, Dongjae, et al.
Pubblicazione: (2025)

Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
di: Kim, Taeheon, et al.
Pubblicazione: (2025)

Tuning Large Multimodal Models for Videos using Reinforcement Learning from AI Feedback
di: Ahn, Daechul, et al.
Pubblicazione: (2024)

GenOL: Generating Diverse Examples for Name-only Online Learning
di: Seo, Minhyuk, et al.
Pubblicazione: (2024)

DialNav: Multi-turn Dialog Navigation with a Remote Guide
di: Han, Leekyeung, et al.
Pubblicazione: (2025)

ISR-DPO: Aligning Large Multimodal Models for Videos by Iterative Self-Retrospective DPO
di: Ahn, Daechul, et al.
Pubblicazione: (2024)

Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
di: Park, Jonghyun, et al.
Pubblicazione: (2024)

SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization
di: Ahn, Young Jin, et al.
Pubblicazione: (2024)

FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers
di: Park, Jonghyun, et al.
Pubblicazione: (2025)

TRACE: Your Diffusion Model is Secretly an Instance Edge Detector
di: Jo, Sanghyun, et al.
Pubblicazione: (2025)

Learning Equi-angular Representations for Online Continual Learning
di: Seo, Minhyuk, et al.
Pubblicazione: (2024)

DBMSolver: A Training-free Diffusion Bridge Sampler for High-Quality Image-to-Image Translation
di: Venugopal, Sankarshana, et al.
Pubblicazione: (2026)

See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis
di: Park, Jaehyun, et al.
Pubblicazione: (2026)

One-Shot Structure-Aware Stylized Image Synthesis
di: Cho, Hansam, et al.
Pubblicazione: (2024)

MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
di: Choi, Kanghyun, et al.
Pubblicazione: (2024)

DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
di: Liu, Jianyu, et al.
Pubblicazione: (2025)

What Happens When: Learning Temporal Orders of Events in Videos
di: Ahn, Daechul, et al.
Pubblicazione: (2025)

Efficient Diffusion-Driven Corruption Editor for Test-Time Adaptation
di: Oh, Yeongtak, et al.
Pubblicazione: (2024)

Long-Tailed Recognition on Binary Networks by Calibrating A Pre-trained Model
di: Kim, Jihun, et al.
Pubblicazione: (2024)

STAG: Structural Test-time Alignment of Gradients for Online Adaptation
di: Shin, Juhyeon, et al.
Pubblicazione: (2024)

Tiled Prompts: Overcoming Prompt Misguidance in Image and Video Super-Resolution
di: Kim, Bryan Sangwoo, et al.
Pubblicazione: (2026)

Attentive Fine-Grained Structured Sparsity for Image Restoration
di: Oh, Junghun, et al.
Pubblicazione: (2022)

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
di: Jeon, Jinsung, et al.
Pubblicazione: (2024)

Online Generic Event Boundary Detection
di: Jung, Hyungrok, et al.
Pubblicazione: (2025)

FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing
di: Kim, Jeongsol, et al.
Pubblicazione: (2025)

MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation Models
di: Lee, Minsoo, et al.
Pubblicazione: (2026)

SEAL: Semantic-aware Single-image Sticker Personalization with a Large-scale Sticker-tag Dataset
di: Roh, Changhyun, et al.
Pubblicazione: (2026)

Accelerating Video Inverse Problem Solvers with Autoregressive Diffusion Models
di: Kwon, Taesung, et al.
Pubblicazione: (2026)

HyGE-Occ: Hybrid View-Transformation with 3D Gaussian and Edge Priors for 3D Panoptic Occupancy Prediction
di: Kim, Jong Wook, et al.
Pubblicazione: (2025)

Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
di: Yoon, Taehoon, et al.
Pubblicazione: (2025)

CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models
di: Kwon, Minkyung, et al.
Pubblicazione: (2025)

MatLat: Material Latent Space for PBR Texture Generation
di: Yeo, Kyeongmin, et al.
Pubblicazione: (2025)

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
di: Kim, Jaihoon, et al.
Pubblicazione: (2024)

Guided Slot Attention for Unsupervised Video Object Segmentation
di: Lee, Minhyeok, et al.
Pubblicazione: (2023)

StochSync: Stochastic Diffusion Synchronization for Image Generation in Arbitrary Spaces
di: Yeo, Kyeongmin, et al.
Pubblicazione: (2025)

CountSteer: Steering Attention for Object Counting in Diffusion Models
di: Boo, Hyemin, et al.
Pubblicazione: (2025)

Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
di: Lee, Jonghyun, et al.
Pubblicazione: (2024)

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation
di: Min, Yunhong, et al.
Pubblicazione: (2025)