Cover Image

Step-Level Visual Grounding Faithfulness Predicts Out-of-Distribution Generalization in Long-Horizon Vision-Language Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Rahman, Md Ashikur, Rahman, Md Arifur, Samin, Niamul Hassan, Arean, Abdullah Ibne Hanif, Noshin, Juena Ahmed
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language Models
by: Samin, Niamul Hassan, et al.
Published: (2026)

Automatic Vehicle Detection using DETR: A Transformer-Based Approach for Navigating Treacherous Roads
by: Fahad, Istiaq Ahmed, et al.
Published: (2025)

A bibliometric analysis on intended and actual turnover in higher education
by: Md. Siddikur Rahman, et al.
Published: (2024)

Optimization of Lead‐Free Perovskite Solar Cell Architecture Using Machine Learning and Numerical Simulations
by: Md. Arifur Rahman, et al.
Published: (2025)

BanglaMM-Disaster: A Multimodal Transformer-Based Deep Learning Framework for Multiclass Disaster Classification in Bangla
by: Islam, Ariful, et al.
Published: (2025)

Association of HLA gene polymorphisms with Helicobacter pylori related gastric cancer—a systematic review
by: Md Toslim Mahmud, et al.
Published: (2024)

Investigation of Mechanical Properties of Nonwoven Recycled Cotton/PET Fiber‐Reinforced Polyester Hybrid Composites
by: Barshan Dev, et al.
Published: (2024)

Pattern Recognition Tasks with Personalized Federated Learning
by: Rahman, Md. Arifur, et al.
Published: (2026)

Quantifying Robustness to Unmeasured Confounding in Time-Varying Treatment Confounder Settings: An Extension of E-value Approach
by: Sium, Md. Niamul Islam
Published: (2026)

Multiscale Glass Fiber/Epoxy Nanocomposites Incorporated with Graphene and Zinc Oxide Nanoparticles: Enhanced Mechanical Properties
by: Barshan Dev, et al.
Published: (2024)

Eggshell bio‐filler integration in jute/banana fiber‐reinforced epoxy hybrid composites: Fabrication and characterization
by: Barshan Dev, et al.
Published: (2024)

Development and characterization of air jet vortex yarn with novel fiber blends
by: Khurshid Alam, et al.
Published: (2024)

Redefining POI Popularity: Integrating User Preferences and Recency for Enhanced Recommendations
by: Hasan, Alif Al, et al.
Published: (2024)

CANGuard: A Spatio-Temporal CNN-GRU-Attention Hybrid Architecture for Intrusion Detection in In-Vehicle CAN Networks
by: Sajib, Rakib Hossain, et al.
Published: (2026)

Next‐Generation Materials for Multifunctional Applications: Design Progress and Prospects of 2D MXene‐Enabled Hybrid Architectures
by: Md. Rubel Alam, et al.
Published: (2025)

An Integrated Blockchain and IPFS Solution for Secure and Efficient Source Code Repository Hosting using Middleman Approach
by: Haque, Md. Rafid, et al.
Published: (2024)

Relative Positioning Based Code Chunking Method For Rich Context Retrieval In Repository Level Code Completion Task With Code Language Model
by: Rahman, Imranur, et al.
Published: (2025)

Data Driven Based Bridge Damage Identification Using a Statistical Approach Utilizing Vehicle‐Induced Acceleration Responses
by: Md. Niamul Haque, et al.
Published: (2026)

Detection of Distributed Denial of Service Attacks based on Machine Learning Algorithms
by: Rahman, Md. Abdur
Published: (2025)

DMP: CO₂ Emissions Prediction Using Machine Learning
by: Md Khasrur, Rahman
Published: (2025)

Exploring the Convergence of HCI and Evolving Technologies in Information Systems
by: Gupta, Rajan Das, et al.
Published: (2025)

Mind the Gap: Evaluating LLMs for High-Level Malicious Package Detection vs. Fine-Grained Indicator Identification
by: Ryan, Ahmed, et al.
Published: (2026)

Moral Sycophancy in Vision Language Models
by: Rabby, Shadman, et al.
Published: (2026)

PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
by: Rahman, Hanif
Published: (2026)

Script collapse in multilingual ASR: A reference-free metric and 100-pair benchmark
by: Rahman, Hanif
Published: (2026)

Fine-tuning Whisper for Pashto ASR: strategies and scale
by: Rahman, Hanif
Published: (2026)

PashtoTTS-Bench: automated screening for low-resource non-Latin-script text-to-speech
by: Rahman, Hanif
Published: (2026)

Benchmarking Multilingual Speech Models on Pashto: Zero-Shot ASR, Script Failure, and Cross-Domain Evaluation
by: Rahman, Hanif
Published: (2026)

Governance Quality Under Economic Uncertainty: Global Insights
by: S M Woahid Murad, et al.
Published: (2025)

Testbed Evaluation of AI-based Precoding in Distributed MIMO Systems
by: Miao, Tianzheng, et al.
Published: (2025)

Unveiling Malicious Logic: Towards a Statement-Level Taxonomy and Dataset for Securing Python Packages
by: Ryan, Ahmed, et al.
Published: (2025)

Central limit theorem for the global clustering coefficient of random geometric graphs
by: Yuan, Mingao, et al.
Published: (2026)

Two Decades of Bengali Handwritten Digit Recognition: A Survey
by: Rahman, A. B. M. Ashikur, et al.
Published: (2022)

Unveiling architectural and optoelectronic synergies in lead-free perovskite/perovskite/kesterite triple-junction monolithic tandem solar cells
by: Rahman, Md. Faiaad, et al.
Published: (2025)

Educators as Catalysts for Inclusive and Sustainable Development: A Global Review of Teaching Practices and Policy Imperatives
by: Rahman, Md Md Atikur
Published: (2026)

Code Refactoring with LLM: A Comprehensive Evaluation With Few-Shot Settings
by: Tapader, Md. Raihan, et al.
Published: (2025)

Error Understanding in Program Code With LLM-DL for Multi-label Classification
by: Amin, Md Faizul Ibne, et al.
Published: (2026)

Engineering hyper-personalization: Software challenges and brand performance in AI-driven digital marketing management: An empirical study
by: Haider, Raiyan, et al.
Published: (2025)

Investigating the Influence of Language on Sycophantic Behavior of Multilingual LLMs
by: Aldahlawi, Bayan Abdullah, et al.
Published: (2026)

BeHGAN: Bengali Handwritten Word Generation from Plain Text Using Generative Adversarial Networks
by: Islam, Md. Rakibul, et al.
Published: (2025)