arXiv AI June 16, 2026 By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

Beyond Scalar Distances: Semantic Attribute Gradients from Frozen MLLMs for Visual Embeddings

arXiv:2606. 15134v1 Announce Type: cross Abstract: Vision encoders for retrieval are typically trained with class-label supervision: each training pair reduces to a scalar that uniformly pushes the embedding apart or pulls it together, as if every visual attribute either differed or matched.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Jun 24

Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations

arXiv:2606. 24716v1 Announce Type: cross Abstract: Sparse autoencoders (SAEs) are increasingly used to extract interpretable concepts from vision and vision language models, yet existing evaluation methods largely rely on proxy metrics or qualitative inspection rather than measuring semantic correspondence.

By Jonas Klotz, Cassio F. Dantas, Pallavi Jain, Diego Marcos, Beg\"um Demir

llms rag benchmarks safety

arXiv AI

Jul 28

Controlling Embedding Spaces with Text-Conditioned Transformations

arXiv:2607. 22919v1 Announce Type: cross Abstract: Multimodal embedding spaces in models like CLIP enable powerful capabilities such as semantic similarity retrieval and cross-modal zero-shot classification.

By Joseph Fioresi, Fabian Caba Heilbron, Pankaj Nathani, Mubarak Shah, Kushal Kafle

rag diffusion multimodal benchmarks

arXiv Machine Learning

Jul 21

The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric

arXiv:2607. 18237v1 Announce Type: cross Abstract: Human visual similarity judgments are context-dependent.

By Sheng-Yu Wang, Yotam Nitzan, Aaron Hertzmann, Jun-Yan Zhu, Eli Shechtman, Alexei A. Efros, Richard Zhang

llms fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 28

Similarity Is Not Logic: Factored Inference for Dual-Encoder Vision-Language Models

arXiv:2607. 23052v1 Announce Type: cross Abstract: Dual-encoder vision-language models (VLMs) expose a similarity interface that enables zero-shot retrieval but fails compositional constraints: queries like "umbrella and no person" retrieve images containing both, even when concept detection is reliable.

By Sultan Alshehri, Zhantao Yang, Han Zhang, Marios Savvides

llms rag fine-tuning multimodal

Hugging Face Trending Papers

Aug 4

SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval

Adapting CLIP for zero-shot sketch-based image retrieval (ZS-SBIR) via prompt learning faces a fundamental tension: the model must bridge the sketch-photo domain gap through task-specific adaptation, yet the added flexibility risks overfitting to seen training categories and eroding CLIP's zero-shot generalization. We present SeCo-SBIR, a semantically consistent prompt learning framework that resolves this tension from both sides.

llms multimodal benchmarks

Hugging Face Trending Papers

Aug 11

When Vision Becomes Text: Visual Token Pruning via Cross-Modal Residual Guidance in VLMs

Abundant visual information strengthens vision-language model (VLM) perception, yet massive visual tokens raise inference costs. Existing visual token pruning methods rely on similarity-based guidance, which exploits pairwise text-vision and vision-vision token correlations for compression.

llms efficiency multimodal

Related stories