Diagnosing the Sources of Compositional Failure in Vision-Language Models: A Controlled Analysis

arXiv:2609.31456 · cs.CV · Submitted 2026-09-25 · Read on arXiv

cs.CV

Submitted: 2026-09-25

Updated: 2026-09-25

Terminology

• Benchmark — 20× in this paper · explained in 2 episodes
• Perplexity — 20× in this paper · explained in 3 episodes
• Grounding — 11× in this paper · explained in 3 episodes
• Accuracy — 8× in this paper · explained in 1 episode
• Embeddings — 3× in this paper · explained in 2 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Alignment — 2× in this paper · explained in 1 episode
• Compositional Generalization — 2× in this paper · explained in 4 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Vision-Language Models (VLMs) — 2× in this paper · explained in 6 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Semantic Understanding — 1× in this paper · explained in 2 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• Vision-Language Models Do Not Understand Negation
• Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models
• Teaching Structured Vision&Language Concepts to Vision&Language Models
• Probing Image-Language Transformers for Verb Understanding
• Compositionality decomposed: how do neural networks generalise?
• ComCLIP: Training-Free Compositional Image and Text Matching
• CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning
• The Hard Positive Truth about Vision-Language Compositionality
• Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations
• Grounded Language-Image Pre-training
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• CREPE: Can Vision-Language Foundation Models Reason Compositionally?
• Kosmos-2: Grounding Multimodal Large Language Models to the World
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
• A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks
• Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding
• A Contrastive Compositional Benchmark for Text-to-Image Synthesis: A Study with Unified Text-to-Image Fidelity Metrics

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models