arXiv Machine Learning

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.

arXiv AI

Jun 16

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.

By Shubhang Bhatnagar, Dheeraj Baiju, Narendra Ahuja

llms rag efficiency multimodal benchmarks

arXiv AI

Jul 8

CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space

arXiv:2604. 11539v2 Announce Type: replace-cross Abstract: Human perception of visual similarity is inherently adaptive and subjective, depending on the users' interests and focus.

By Sohwi Lim, Lee Hyoseok, Jungjoon Park, Tae-Hyun Oh

llms rag multimodal

Hugging Face Trending Papers

Jul 6

DiCE-CIR: Direct Composition Learning for Efficient Zero-Shot Composed Image Retrieval

Zero-shot composed image retrieval (ZS-CIR) aims to retrieve a target image from a multimodal query consisting of a reference image and an edit text describing the desired modification. Recent ZS-CIR studies have relied on projection-based methods that map a reference image into pseudo-word tokens in the text embedding space.

llms rag multimodal benchmarks safety

arXiv Machine Learning

Aug 3

FORGE: Frame Orthogonality in Relevance Geometry for Long-Form Video Understanding

arXiv:2607. 25266v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible.

By Ghazal Kaviani, Ghassan AlRegib

llms rag nlp multimodal

arXiv AI

Jul 7

Text as Partial Constraint: Core-Residual Alignment for Robust Vision-Language Learning

arXiv:2607. 03143v1 Announce Type: cross Abstract: Vision-language alignment powers open-vocabulary recognition, retrieval, and LVLM grounding, yet natural captions are often underspecified, making similarity brittle and overly confident under paraphrase and omitted details.

By Chengzhen Yu, Canran Xiao, Siyuan Ma, Yang Liu

multimodal safety

arXiv AI

Jul 1

Thinking Before Retrieving: Robust Zero-Shot Composed Image Retrieval via Strategic Planning and Self-Criticism

arXiv:2606. 31222v1 Announce Type: new Abstract: Composed image retrieval requires identifying a target image from a gallery by integrating a reference image with a textual modification instruction.

By Gunho Jung, Jeong-Woo Park, Seon Bin Kim, Seong-Whan Lee

rag

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 AI

Aug 11

Explaining, Verifying, and Aligning Semantic Hierarchies in Vision-Language Model Embeddings

arXiv:2603. 26798v2 Announce Type: replace-cross Abstract: Vision-language model (VLM) encoders such as CLIP enable strong retrieval and zero-shot classification in a shared image-text embedding space, yet the semantic organization of this space is rarely inspected.

By Gesina Schwalbe, Mert Keser, Moritz Bayerkuhnlein, Edgar Heinert, Annika M\"utze, Marvin Keller, Sparsh Tiwari, Georgii Mikriukov, Diedrich Wolter, Jae Hee Lee, Matthias Rottmann

llms rag multimodal safety

arXiv AI

Jul 7

TORINO: Token Reduction via Interpretable Concept Overlap in Vision-Language Models

arXiv:2607. 04593v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) have demonstrated impressive capabilities across different tasks, but their computational cost is dominated by the large number of visual tokens fed to the language model.

By Riccardo Renzulli, Gabriele Spadaro, Shruthi Gowda, Alaa Eddine Mazouz, Van-Tam Nguyen

llms diffusion fine-tuning efficiency multimodal benchmarks

arXiv AI

Jun 8

TEVI: Text-Conditioned Editing of Visual Representations via Sparse Autoencoders for Improved Vision-Language Alignment

arXiv:2606. 07451v1 Announce Type: cross Abstract: Vision-language models such as CLIP are highly useful for diverse tasks due to their shared image-text embedding space.

By Sweta Mahajan, Sukrut Rao, Jiahao Xie, Alexander Koller, Bernt Schiele

llms rag multimodal benchmarks safety

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 Machine Learning

Jun 2

Reason, Retrieve, Re-rank: A Zero-Shot Reasoning-Aware Framework for Composed Video Retrieval

arXiv:2606. 00910v1 Announce Type: cross Abstract: Composed Video Retrieval (CoVR) seeks the target video that results from applying a free-form textual modification to a reference video.

By Ali Alavi

llms multimodal

Related stories