Imagen de Portada

Contamination Detection for VLMs using Multi-Modal Semantic Perturbation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Park, Jaden, Cai, Mu, Yao, Feng, Shang, Jingbo, Lee, Soochahn, Lee, Yong Jae
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples
por: Zhang, Jianrui, et al.
Publicado: (2024)

Reasoning-Augmented Representations for Multimodal Retrieval
por: Zhang, Jianrui, et al.
Publicado: (2026)

Vinoground: Scrutinizing LMMs over Dense Temporal Reasoning with Short Videos
por: Zhang, Jianrui, et al.
Publicado: (2024)

TemporalBench: Benchmarking Fine-grained Temporal Understanding for Multimodal Video Models
por: Cai, Mu, et al.
Publicado: (2024)

VGBench: Evaluating Large Language Models on Vector Graphics Understanding and Generation
por: Zou, Bocheng, et al.
Publicado: (2024)

Unified Spatio-Temporal Token Scoring for Efficient Video VLMs
por: Zhang, Jianrui, et al.
Publicado: (2026)

Matryoshka Multimodal Models
por: Cai, Mu, et al.
Publicado: (2024)

One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
por: Kim, Doyoung, et al.
Publicado: (2023)

Probing Visual Language Priors in VLMs
por: Luo, Tiange, et al.
Publicado: (2024)

Yo'LLaVA: Your Personalized Language and Vision Assistant
por: Nguyen, Thao, et al.
Publicado: (2024)

Active Diffusion Matching: Score-based Iterative Alignment of Cross-Modal Retinal Images
por: Lee, Kanggeon, et al.
Publicado: (2026)

Anomaly Detection with Adaptive and Aggressive Rejection for Contaminated Training Data
por: Lee, Jungi, et al.
Publicado: (2025)

Heavy-tailed Contamination is Easier than Adversarial Contamination
por: Cherapanamjeri, Yeshwanth, et al.
Publicado: (2024)

VLM-SubtleBench: How Far Are VLMs from Human-Level Subtle Comparative Reasoning?
por: Kim, Minkyu, et al.
Publicado: (2026)

Active Learning for Continual Learning: Keeping the Past Alive in the Present
por: Park, Jaehyun, et al.
Publicado: (2025)

Multi-Modal Continual Learning via Cross-Modality Adapters and Representation Alignment with Knowledge Preservation
por: Chee, Evelyn, et al.
Publicado: (2025)

Penalized Empirical Likelihood for Doubly Robust Causal Inference under Contamination in High Dimensions
por: Lee, Byeonghee, et al.
Publicado: (2025)

Multi-Marginal Schrödinger Bridge Matching
por: Park, Byoungwoo, et al.
Publicado: (2025)

Greedy Alignment Principle for Optimizer Selection
por: Lee, Jaerin, et al.
Publicado: (2025)

Auto-regressive transformation for image alignment
por: Lee, Kanggeon, et al.
Publicado: (2025)

MatRes: Zero-Shot Test-Time Model Adaptation for Simultaneous Matching and Restoration
por: Lee, Kanggeon, et al.
Publicado: (2026)

Particle Diffusion Matching: Random Walk Correspondence Search for the Alignment of Standard and Ultra-Widefield Fundus Images
por: Lee, Kanggeon, et al.
Publicado: (2026)

LASER: Lip Landmark Assisted Speaker Detection for Robustness
por: Nguyen, Le Thien Phuc, et al.
Publicado: (2025)

AMPS: Adaptive Modality Preference Steering via Functional Entropy
por: Huang, Zihan, et al.
Publicado: (2026)

GNSP: Gradient Null Space Projection for Preserving Cross-Modal Alignment in VLMs Continual Learning
por: Peng, Tiantian, et al.
Publicado: (2025)

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems
por: Lee, Jongyeong, et al.
Publicado: (2025)

Distributed Information Bottleneck Theory for Multi-Modal Task-Aware Semantic Communication
por: Zhou, Yujie, et al.
Publicado: (2025)

SeMoBridge: Semantic Modality Bridge for Efficient Few-Shot Adaptation of CLIP
por: Timmermann, Christoph, et al.
Publicado: (2025)

MONAQ: Multi-Objective Neural Architecture Querying for Time-Series Analysis on Resource-Constrained Devices
por: Trirat, Patara, et al.
Publicado: (2025)

See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models
por: Nguyen, Le Thien Phuc, et al.
Publicado: (2025)

Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection
por: Wang, Han, et al.
Publicado: (2025)

Robust and Adaptive Spectral Method for Representation Multi-Task Learning with Contamination
por: Huang, Yian, et al.
Publicado: (2025)

Leveraging Large Language Models for Scalable Vector Graphics-Driven Image Understanding
por: Cai, Mu, et al.
Publicado: (2023)

Enhancing Prompt Injection Attacks to LLMs via Poisoning Alignment
por: Shao, Zedian, et al.
Publicado: (2024)

Get Global Guarantees: On the Probabilistic Nature of Perturbation Robustness
por: Mu, Wenchuan, et al.
Publicado: (2025)

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
por: Cai, Mu, et al.
Publicado: (2023)

Quantifying Data Contamination in Psychometric Evaluations of LLMs
por: Han, Jongwook, et al.
Publicado: (2025)

Predictive Prompt Analysis
por: Lee, Jae Yong, et al.
Publicado: (2025)

Low-Complexity Semantic Packet Aggregation for Token Communication via Lookahead Search
por: Lee, Seunghun, et al.
Publicado: (2025)

DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization
por: Park, Yeonhong, et al.
Publicado: (2024)