Cover Image

Beyond Accuracy: Benchmarking Cross-Task Consistency in Unified Multimodal Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wang, Weixing, Zekas, Liudvikas, Hackl, Anton, Auga, Constantin Alexander, Shahabinejad, Parisa, Otholt, Jona, Rueda-Toicen, Antonio, de Melo, Gerard
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Šilutės Hugo Šojaus muziejuje saugoma patranka ir artilerijos pabūklų analizė XRF tyrimų duomenimis
by: Liudvikas Vasiliauskas
Published: (2021)

Are We Recognizing the Jaguar or Its Background? A Diagnostic Framework for Jaguar Re-Identification
by: Rueda-Toicen, Antonio, et al.
Published: (2026)

Beyond Connectivity: Higher-Order Network Framework for Capturing Memory-Driven Mobility Dynamics
by: Zhang, Chen, et al.
Published: (2025)

Generic Multimodal Spatially Graph Network for Spatially Embedded Network Representation Learning
by: Fan, Xudong, et al.
Published: (2025)

Traveling Across Languages: Benchmarking Cross-Lingual Consistency in Multimodal LLMs
by: Wang, Hao, et al.
Published: (2025)

Functional instant noodle formulation for emergency conditions: Sensory and stability characteristics
by: Farboud Shahabinejad, et al.
Published: (2024)

Beyond Self-Consistency: Ensemble Reasoning Boosts Consistency and Accuracy of LLMs in Cancer Staging
by: Chang, Chia-Hsuan, et al.
Published: (2024)

CrossMed: A Multimodal Cross-Task Benchmark for Compositional Generalization in Medical Imaging
by: Singh, Pooja, et al.
Published: (2025)

Towards decent work for young refugees and host communities in the digital platform economy in Africa: Kenya, Uganda, Egypt
by: Andreas Hackl
Published: (2021)

Digital refugee livelihoods and decent work: towards inclusion in a fairer digital economy
by: Andreas Hackl
Published: (2021)

Thioether Synthesis via the Nickel‐Catalyzed Electrochemical Cross Electrophile Coupling of Aryl/Alkyl Disulfides and Aryl/Alkyl Halides
by: Jona Queder, et al.
Published: (2025)

UI-CUBE: Enterprise-Grade Computer Use Agent Benchmarking Beyond Task Accuracy to Operational Reliability
by: Cristescu, Horia, et al.
Published: (2025)

Benchmarking Foundation Models for Zero-Shot Biometric Tasks
by: Sony, Redwan, et al.
Published: (2025)

Minimal Algorithmic Information Loss Methods for Dimension Reduction, Feature Selection and Network Sparsification
by: Zenil, Hector, et al.
Published: (2018)

Rethinking Graph-Based Document Classification: Learning Data-Driven Structures Beyond Heuristic Approaches
by: Bugueño, Margarita, et al.
Published: (2025)

Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP
by: Eslami, Sedigheh, et al.
Published: (2024)

Is GPT-4 a reliable rater? Evaluating Consistency in GPT-4 Text Ratings
by: Hackl, Veronika, et al.
Published: (2023)

Typical entanglement in anyon chains: Page curves beyond Lie group symmetries
by: Yauk, Yale, et al.
Published: (2026)

Trained models supporting the article "Integrative profiling of condensation-prone RNAs during early development".
by: Novljan, Jona
Published: (2025)

Transactive Control of Coupled Electric Power and District Heating Networks
by: Maurer, Jona
Published: (2023)

An Invariant for Triple-Point-Free Immersed Spheres
by: Seidel, Jona
Published: (2025)

Non Hilbertian (Lorentzian) Length Spaces
by: Röhrig, Jona
Published: (2024)

QBIT: Quality-Aware Cloud-Based Benchmarking for Robotic Insertion Tasks
by: Schempp, Constantin, et al.
Published: (2025)

A SageMath Package for Analytic Combinatorics in Several Variables: Beyond the Smooth Case
by: Hackl, Benjamin, et al.
Published: (2025)

Beyond Accuracy: Evaluating Visual Grounding In Multimodal Medical Reasoning
by: Zafar, Anas, et al.
Published: (2026)

Consistent Joint Decision-Making with Heterogeneous Learning Models
by: Faghihi, Hossein Rajaby, et al.
Published: (2024)

CommitBench: A Benchmark for Commit Message Generation
by: Schall, Maximilian, et al.
Published: (2024)

Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
by: Min, Marcus J., et al.
Published: (2023)

ConsistCompose: Unified Multimodal Layout Control for Image Composition
by: Shi, Xuanke, et al.
Published: (2025)

Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering
by: Jiang, Kaixuan, et al.
Published: (2025)

Physical Knot Classification Beyond Accuracy: A Benchmark and Diagnostic Study
by: Nie, Shiheng, et al.
Published: (2026)

Looking Beyond Accuracy: A Holistic Benchmark of ECG Foundation Models
by: Filice, Francesca, et al.
Published: (2026)

Cross-Task Benchmarking of CNN Architectures
by: Sherawat, Kamal, et al.
Published: (2026)

FoREST: Frame of Reference Evaluation in Spatial Reasoning Tasks
by: Premsri, Tanawan, et al.
Published: (2025)

UEval: A Benchmark for Unified Multimodal Generation
by: Li, Bo, et al.
Published: (2026)

Cross-Modal Consistency in Multimodal Large Language Models
by: Zhang, Xiang, et al.
Published: (2024)

NeuralSolver: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
by: Esteves, Bernardo, et al.
Published: (2024)

Multimodal Fusion via Self-Consistent Task-Gradient Fields
by: Xiong, Jiayu, et al.
Published: (2024)

Streaming Piano Transcription Based on Consistent Onset and Offset Decoding with Sustain Pedal Detection
by: Wei, Weixing, et al.
Published: (2025)

Zwischen Anstalt und Schule
by: Garz, Jona Tomke
Published: (2022)