Imagen de Portada

The Instinctive Bias: Spurious Images lead to Illusion in MLLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Han, Tianyang, Lian, Qing, Pan, Rui, Pi, Renjie, Zhang, Jipeng, Diao, Shizhe, Lin, Yong, Zhang, Tong
Formato:	Preprint
Publicado:	2024
Materias:	Computer Vision and Pattern Recognition Computation and Language Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Strengthening Multimodal Large Language Model with Bootstrapped Preference Optimization
por: Pi, Renjie, et al.
Publicado: (2024)

MLLM-Protector: Ensuring MLLM's Safety without Hurting Performance
por: Pi, Renjie, et al.
Publicado: (2024)

Image Textualization: An Automatic Framework for Creating Accurate and Detailed Image Descriptions
por: Pi, Renjie, et al.
Publicado: (2024)

LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
por: Pan, Rui, et al.
Publicado: (2024)

Personalized Visual Instruction Tuning
por: Pi, Renjie, et al.
Publicado: (2024)

Adapt-Pruner: Adaptive Structural Pruning for Efficient Small Language Model Training
por: Pan, Rui, et al.
Publicado: (2025)

VL-GenRM: Enhancing Vision-Language Verification via Vision Experts and Iterative Training
por: Zhang, Jipeng, et al.
Publicado: (2025)

MA-LoT: Model-Collaboration Lean-based Long Chain-of-Thought Reasoning enhances Formal Theorem Proving
por: Wang, Ruida, et al.
Publicado: (2025)

Generalizable Geometric Image Caption Synthesis
por: Xin, Yue, et al.
Publicado: (2025)

Active Prompting with Chain-of-Thought for Large Language Models
por: Diao, Shizhe, et al.
Publicado: (2023)

TAGCOS: Task-agnostic Gradient Clustered Coreset Selection for Instruction Tuning Data
por: Zhang, Jipeng, et al.
Publicado: (2024)

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
por: Wang, Ruida, et al.
Publicado: (2024)

LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models
por: Diao, Shizhe, et al.
Publicado: (2023)

Bridge-Coder: Unlocking LLMs' Potential to Overcome Language Gaps in Low-Resource Code
por: Zhang, Jipeng, et al.
Publicado: (2024)

Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Data
por: Shum, KaShun, et al.
Publicado: (2023)

R-Tuning: Instructing Large Language Models to Say `I Don't Know'
por: Zhang, Hanning, et al.
Publicado: (2023)

The Side Effects of Being Smart: Safety Risks in MLLMs' Multi-Image Reasoning
por: Chen, Renmiao, et al.
Publicado: (2026)

Entropy-Regularized Process Reward Model
por: Zhang, Hanning, et al.
Publicado: (2024)

Can MLLMs Understand the Deep Implication Behind Chinese Images?
por: Zhang, Chenhao, et al.
Publicado: (2024)

Arithmetic Control of LLMs for Diverse User Preferences: Directional Preference Alignment with Multi-Objective Rewards
por: Wang, Haoxiang, et al.
Publicado: (2024)

The Illusion-Illusion: Vision Language Models See Illusions Where There are None
por: Ullman, Tomer
Publicado: (2024)

Unhackable Temporal Rewarding for Scalable Video MLLMs
por: Yu, En, et al.
Publicado: (2025)

IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
por: Shahgir, Haz Sameen, et al.
Publicado: (2024)

MedRCube: A Multidimensional Framework for Fine-Grained and In-Depth Evaluation of MLLMs in Medical Imaging
por: Bao, Zhijie, et al.
Publicado: (2026)

Interpretable and Reliable Detection of AI-Generated Images via Grounded Reasoning in MLLMs
por: Ji, Yikun, et al.
Publicado: (2025)

GRIT: Teaching MLLMs to Think with Images
por: Fan, Yue, et al.
Publicado: (2025)

Linking Perception, Confidence and Accuracy in MLLMs
por: Du, Yuetian, et al.
Publicado: (2026)

Latent Sketchpad: Sketching Visual Thoughts to Elicit Multimodal Reasoning in MLLMs
por: Zhang, Huanyu, et al.
Publicado: (2025)

Tables as Texts or Images: Evaluating the Table Reasoning Ability of LLMs and MLLMs
por: Deng, Naihao, et al.
Publicado: (2024)

FIRST: Teach A Reliable Large Language Model Through Efficient Trustworthy Distillation
por: Shum, KaShun, et al.
Publicado: (2024)

Benchmarking Spurious Bias in Few-Shot Image Classifiers
por: Zheng, Guangtao, et al.
Publicado: (2024)

A Sober Look at the Robustness of CLIPs to Spurious Features
por: Wang, Qizhou, et al.
Publicado: (2024)

Localize-and-Stitch: Efficient Model Merging via Sparse Task Arithmetic
por: He, Yifei, et al.
Publicado: (2024)

p-MoD: Building Mixture-of-Depths MLLMs via Progressive Ratio Decay
por: Zhang, Jun, et al.
Publicado: (2024)

AMBER: An LLM-free Multi-dimensional Benchmark for MLLMs Hallucination Evaluation
por: Wang, Junyang, et al.
Publicado: (2023)

Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs
por: Yeh, Chun-Hsiao, et al.
Publicado: (2025)

Seeing the Poem: Image-Semantic Detection of AI-Generated Modern Chinese Poetry with MLLMs
por: Wang, Shanshan, et al.
Publicado: (2026)

ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialects
por: Zhang, Jipeng, et al.
Publicado: (2025)

CoCA: Regaining Safety-awareness of Multimodal Large Language Models with Constitutional Calibration
por: Gao, Jiahui, et al.
Publicado: (2024)

Exploring the Design Space of Visual Context Representation in Video MLLMs
por: Du, Yifan, et al.
Publicado: (2024)