Copertina

HoliSafe: Holistic Safety Benchmarking and Modeling for Vision-Language Model

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Lee, Youngwan, Kim, Kangsan, Park, Kwanyong, Jung, Ilcahe, Jang, Soojin, Lee, Seanie, Lee, Yong-Ju, Hwang, Sung Ju
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computer Vision and Pattern Recognition Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

MultihopSpatial: Multi-hop Compositional Spatial Reasoning Benchmark for Vision-Language Model
di: Lee, Youngwan, et al.
Pubblicazione: (2026)

KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
di: Lee, Youngwan, et al.
Pubblicazione: (2023)

VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understanding
di: Kim, Kangsan, et al.
Pubblicazione: (2024)

Visualizing the loss landscape of Self-supervised Vision Transformer
di: Lee, Youngwan, et al.
Pubblicazione: (2024)

MA-EgoQA: Question Answering over Egocentric Videos from Multiple Embodied Agents
di: Kim, Kangsan, et al.
Pubblicazione: (2026)

EVEREST: Efficient Masked Video Autoencoder by Removing Redundant Spatiotemporal Tokens
di: Hwang, Sunil, et al.
Pubblicazione: (2022)

SafeRoute: Adaptive Model Selection for Efficient and Accurate Safety Guardrails in Large Language Models
di: Lee, Seanie, et al.
Pubblicazione: (2025)

Concept-skill Transferability-based Data Selection for Large Vision-Language Models
di: Lee, Jaewoo, et al.
Pubblicazione: (2024)

SIA: Enhancing Safety via Intent Awareness for Vision-Language Models
di: Na, Youngjin, et al.
Pubblicazione: (2025)

Simple yet Effective Semi-supervised Knowledge Distillation from Vision-Language Models via Dual-Head Optimization
di: Kang, Seongjae, et al.
Pubblicazione: (2025)

FedRand: Enhancing Privacy in Federated Learning with Randomized LoRA Subparameter Updates
di: Park, Sangwoo, et al.
Pubblicazione: (2025)

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
di: An, Sohyun, et al.
Pubblicazione: (2023)

Talk in Pieces, See in Whole: Disentangling and Hierarchical Aggregating Representations for Language-based Object Detection
di: An, Sojung, et al.
Pubblicazione: (2025)

Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
di: Jang, Sangwon, et al.
Pubblicazione: (2024)

A Training-free Sub-quadratic Cost Transformer Model Serving Framework With Hierarchically Pruned Attention
di: Lee, Heejun, et al.
Pubblicazione: (2024)

VideoRAG: Retrieval-Augmented Generation over Video Corpus
di: Jeong, Soyeong, et al.
Pubblicazione: (2025)

WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
di: Yeo, Woongyeong, et al.
Pubblicazione: (2025)

Drug Discovery with Dynamic Goal-aware Fragments
di: Lee, Seul, et al.
Pubblicazione: (2023)

THINKSAFE: Self-Generated Safety Alignment for Reasoning Models
di: Lee, Seanie, et al.
Pubblicazione: (2026)

It Takes Two: Complementary Self-Distillation for Contextual Integrity in LLMs
di: Park, Sangwoo, et al.
Pubblicazione: (2026)

Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
di: Kim, Suji, et al.
Pubblicazione: (2026)

SpectraDINO: Bridging the Spectral Gap in Vision Foundation Models via Lightweight Adapters
di: Nalcakan, Yagiz, et al.
Pubblicazione: (2026)

Are Vision-Language Models Safe in the Wild? A Meme-Based Benchmark Study
di: Lee, DongGeon, et al.
Pubblicazione: (2025)

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
di: Lee, Hyomin, et al.
Pubblicazione: (2026)

Pix2Next: Leveraging Vision Foundation Models for RGB to NIR Image Translation
di: Jin, Youngwan, et al.
Pubblicazione: (2024)

UniversalRAG: Retrieval-Augmented Generation over Corpora of Diverse Modalities and Granularities
di: Yeo, Woongyeong, et al.
Pubblicazione: (2025)

Distilling LLM Agent into Small Models with Retrieval and Code Tools
di: Kang, Minki, et al.
Pubblicazione: (2025)

How Does Vision-Language Adaptation Impact the Safety of Vision Language Models?
di: Lee, Seongyun, et al.
Pubblicazione: (2024)

Set-based Meta-Interpolation for Few-Task Meta-Learning
di: Lee, Seanie, et al.
Pubblicazione: (2022)

Training-Free Exponential Context Extension via Cascading KV Cache
di: Willette, Jeffrey, et al.
Pubblicazione: (2024)

Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models
di: Jang, Sangwon, et al.
Pubblicazione: (2025)

PCoreSet: Effective Active Learning through Knowledge Distillation from Vision-Language Models
di: Kang, Seongjae, et al.
Pubblicazione: (2025)

Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection
di: Park, Kwanyong, et al.
Pubblicazione: (2024)

HarmAug: Effective Data Augmentation for Knowledge Distillation of Safety Guard Models
di: Lee, Seanie, et al.
Pubblicazione: (2024)

PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation
di: Hwang, Injoon, et al.
Pubblicazione: (2024)

BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptation
di: Lee, Daeun, et al.
Pubblicazione: (2024)

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model
di: Kim, Dongki, et al.
Pubblicazione: (2025)

Holistic Unlearning Benchmark: A Multi-Faceted Evaluation for Text-to-Image Diffusion Model Unlearning
di: Moon, Saemi, et al.
Pubblicazione: (2024)

V-Agent: An Interactive Video Search System Using Vision-Language Models
di: Park, SunYoung, et al.
Pubblicazione: (2025)

Self-Supervised Dataset Distillation for Transfer Learning
di: Lee, Dong Bok, et al.
Pubblicazione: (2023)