arXiv:2610.33798v1 Announce Type: cross Abstract: An image is rarely described only once. Retrieval benchmarks and many collections attach several captions to each picture, yet dual encoders still ju...
CompoSET is a new vision‑language benchmark that tests compositionality by presenting each image‑caption pair with a foil that differs by only a single controlled edit—such as color, count, spatial relation, or object state—while keeping the overall scene largely unchanged. The dataset contains 1,776 instances across 80 scenes, 16 edit types in four semantic categories, and captions at three verbosity levels, with an average of only 8% pixel change between base and foil images. Evaluation of 22 dual‑encoder VLMs shows that all models perform at or below chance on CompoSET, contrasting with their strong performance on prior benchmarks that conflate global image differences with compositional reasoning.
arXiv:2609.23717v1 Announce Type: new Abstract: Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which regi...
arXiv:2607. 28986v1 Announce Type: cross Abstract: Zero-shot image captioning (ZIC) describes images without paired image-caption supervision during captioner training, relying on text-only corpora and frozen pretrained image-text scorers.
The paper introduces Visual Retrieval Heads (VRHs), a small fraction of attention heads in vision‑language models that are causally responsible for grounding text descriptions to image regions. By recasting head‑scoring methods and evaluating across eleven VLMs and five benchmarks, the authors show that masking the top 20 VRHs can drop grounding accuracy by up to 80 percentage points, while random masking has little effect. VRHs generalize across various visual reference tasks, preserve output format while corrupting localization, and transfer causally across models sharing an LLM backbone.
arXiv:2610.34610v1 Announce Type: new Abstract: Vision-language anomaly detectors describe normal and abnormal appearance with text, and their gains are commonly credited to the semantic content of t...
Global vision--language similarities compress an image and a caption into one vector, preserving semantics but not which word corresponds to which region or how those regions are arranged; a model can...
The paper introduces GAVAGAI, a method that adds a referential alignment variable to vision‑language models by solving a small assignment problem via entropic optimal transport. By allowing words to be assigned to a special NOTHING column and enforcing a capacity constraint on regions, the approach improves word‑to‑picture accuracy and localization on the SAYCam infant video corpus. Experiments show that the alignment loss boosts performance over a standard next‑token captioning baseline, especially under high non‑reference rates.
EXPL-FR is a lightweight adapter that aligns a vision‑language model’s image encoder with a frozen face‑recognition (FR) embedding space, enabling the FR model to be explained using semantic attribute prompts without any text training. By mapping 978 attribute prompts across 22 categories into the FR space, the method identifies the most detectable concepts—forming a readable semantic signature that better separates identities than the full vocabulary. The approach is evaluated on four FR backbones and two VLM encoders, providing identity‑level, per‑image, and differential explanations, and demonstrates that prompt‑driven audits can rank FR models by per‑ethnicity error and attribute‑change verification cost without requiring labeled data.
SCOUT is a frozen‑encoder approach for sim‑to‑real text‑based person retrieval that predicts cross‑modal embeddings instead of fine‑tuning cross‑encoders. It uses a trainable predictor to map patch tokens from a frozen video encoder (V‑JEPA) into the embedding space of a frozen text encoder (EmbeddingGemma), guided by a bidirectional InfoNCE objective. The method achieves state‑of‑the‑art results on the AI City Challenge 2026 Track 4, with a full retrieve‑fuse‑rerank pipeline reaching 84.25 mAP@10 and a single frozen model alone scoring 60.63, while training costs are modest (≈95 GPU‑hours).
The paper presents ChatNDE Figure to Caption, an AI system that automates the interpretation of nondestructive evaluation (NDE) images. It combines a Vision‑and‑Language Pretraining (VLP) approach using ResNet50 for visual feature extraction and GPT‑2 for natural‑language captioning, evaluated with BLEU scores. Additionally, a Visual Question Answering (VQA) model is integrated to answer specific queries about the images, enhancing interactivity for field inspectors.
arXiv:2608. 07886v1 Announce Type: cross Abstract: Vision-language grounding connects language to visual content, yet most existing formulations reduce grounding to a unidirectional localization problem: given a prespecified text phrase or category name, identify the corresponding image region.