When Modality Gap Reduction Fails: Prediction-Level Hubness in CLIP

arXiv:2609.01103 · cs.CL, cs.CV · Submitted 2026-09-01 · Read on arXiv

cs.CL, cs.CV

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Accuracy — 118× in this paper · explained in 1 episode
• Modality Gap — 68× in this paper · explained in 4 episodes
• Embeddings — 21× in this paper · explained in 2 episodes
• Alignment — 20× in this paper · explained in 1 episode
• Cosine Similarity — 6× in this paper · explained in 3 episodes
• Representation Learning — 6× in this paper · explained in 2 episodes
• Ablation — 4× in this paper · explained in 1 episode
• Contrastive Learning — 4× in this paper · explained in 5 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 7 episodes
• Instruction Tuning — 2× in this paper · explained in 2 episodes
• Multimodal Learning — 2× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Cross-domain Similarity Local Scaling — 1× in this paper
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Parsimony — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Zero-Shot Transfer — 1× in this paper · explained in 3 episodes

Sources

• Improving zero-shot learning by mitigating the hubness problem
• It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap
• NeighborRetr: Balancing Hub Centrality in Cross-Modal Retrieval
• When Embedding Models Meet: Procrustes Bounds and Applications
• Fill the Gap: Quantifying and Reducing the Modality Gap in Image-Text Representation Learning

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering