arXiv:2609.24276v1 Announce Type: new Abstract: Hyperbolic vision-language models (VLMs) represent image and text features in a geometry naturally suited to hierarchy, but their adaptation to downstr...
arXiv:2609.24564v1 Announce Type: new Abstract: CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encode...
arXiv:2606. 04434v1 Announce Type: cross Abstract: Multimodal In-Context Learning (ICL) has emerged as a practical inference paradigm for Multimodal Large Language Models, where a small set of interleaved image-text In-Context Demonstrations (ICDs) conditions the model to solve new tasks.
Contrastive Language-Image Pre-training (CLIP) has been shown to have limitations in its fine-grained dense feature representation, due to its pre-training focusing on matching the whole image to a text description. Considering the large data and computational burden in pre-training a vision-language model from scratch, a series of works aim to enhance the fine-grained ability of CLIP through a fine-tuning scheme.
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:2603. 22042v3 Announce Type: replace-cross Abstract: While Vision-Language Models (VLMs) have achieved remarkable performance, their Euclidean embeddings remain limited in capturing hierarchical relationships such as part-to-whole or parent-child structures, and often face challenges in multi-object compositional scenarios.
arXiv:2607. 23913v1 Announce Type: new Abstract: Modern vision-language models (VLMs) increasingly rely on dynamic or high-resolution visual encoding, producing thousands of visual tokens that substantially increase downstream language-model inference cost.
The paper investigates how the modality gap— the separation between image and text representations in contrastive vision‑language models—affects different downstream tasks. By showing that a single dominant direction accounts for most of the image‑text mean separation, the authors explain why reducing or removing this gap can improve zero‑shot classification, degrade retrieval, or restore performance depending on the task. The study provides a geometric framework that clarifies when and why gap interventions should be applied in vision‑language systems.
arXiv:2511. 16107v3 Announce Type: replace-cross Abstract: Visual in-context learning (VICL) solves visual tasks by conditioning on a few input-output demonstrations without any model training.
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved...
The paper introduces Lens, a training‑free framework that aligns multimodal representations with the semantic perspective required by downstream tasks. Lens uses a task‑specific readout phrase to anchor the perspective and then aggregates token states after the full input, ensuring the extracted representation reflects task‑conditioned evidence integration rather than generic salient content. The method achieves a Precision@1 of 63.9 across 36 MMEB datasets, outperforming the nearest training‑free baseline by 10.2 points.
arXiv:2606.23843v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve strong cross-modal alignment but remain brittle to negation, often relying on shallow word associations rathe...