HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models

• URL: http://arxiv.org/abs/2606.23843v1
• Date: Mon, 22 Jun 2026 18:25:37 GMT
• Title: HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models
• Abstract summary: This work introduces HANCLIP (Hyperbolic + Angular + Negation), a family of vision-language models that explicitly restructures the embedding space to encode "what an image is not" alongside "what it is"<n>HANCLIP is trained on a compact set of 20,000 image-text quadruplets and combines a hyperbolic formulation, which models hierarchical semantic relations and asymmetries, with an angular triplet objective that drives systematic separation between negated descriptions and their corresponding positives.<n>Experiments show that HANCLIP delivers consistent gains on the negation-focused NegBench benchmark, while maintaining competitive or improved performance on standard classification
• Score: 3.4657033095341845
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision-Language Models (VLMs) are typically pre-trained on large-scale image-text datasets to capture semantic correspondences between visual content and natural language. However, they remain surprisingly brittle to negation: models often rely on shallow word co-occurrence and are easily distracted by misleading or irrelevant textual cues, even when their overall retrieval or classification performance is strong. Moreover, directly finetuning on negation data can interfere with previously acquired knowledge, causing noticeable degradation on standard vision-language benchmarks. To tackle these issues, this work introduces HANCLIP (Hyperbolic + Angular + Negation), a family of VLMs that explicitly restructures the embedding space to encode "what an image is not" alongside "what it is." HANCLIP is trained on a compact set of 20,000 image-text quadruplets and combines a hyperbolic formulation, which models hierarchical semantic relations and asymmetries, with an angular triplet objective that drives systematic separation between negated descriptions and their corresponding positives. This geometry-aware design strengthens negation sensitivity while preserving the global structure of pretrained representations, rather than overwriting them. Extensive experiments across multiple vision-language tasks show that HANCLIP delivers consistent gains on the negation-focused NegBench benchmark, while maintaining competitive or improved performance on standard classification and image-text retrieval benchmarks. The framework is model-agnostic and can be plugged into CLIP, LongCLIP, SmartCLIP, and HiMo-CLIP without large-scale retraining, demonstrating that a carefully designed geometric objective can substantially extend the reasoning capabilities of existing VLMs using only modest additional data.

Related papers

• Weave of Formal Thought [51.56484100374058]
  We introduce Weave of Formal Thought (WoFT), a paradigm uniting rigorous syntactic validation with learned structural representations.<n>We present a latent-variable fine-tuning method training the language model to interleave non-terminal grammar symbols directly into generation.<n>For Python, fine-tuning StarCoder2-3B with our RWS objective reduces per-token cross-entropy by 14.3% relative to a text-only SFT baseline.
  arXiv  Detail & Related papers  (2026-06-24T15:58:11Z)
• Not Just What's There: Enabling CLIP to Comprehend Negated Visual Descriptions Without Fine-tuning [23.10421006625293]
  Vision-Language Models (VLMs) like CLIP struggle to understand negation.<n>Existing methods refine negation understanding via fine-tuning CLIP's text encoder, risking overfitting.<n>We propose CLIPGlasses, a plug-and-play framework that enhances CLIP's ability to comprehend negated visual descriptions.
  arXiv  Detail & Related papers  (2026-02-24T15:55:39Z)
• VITRIX-CLIPIN: Enhancing Fine-Grained Visual Understanding in CLIP via Instruction Editing Data and Long Captions [16.90061119174727]
  We present CLIP-IN, a novel framework that bolsters CLIP's fine-grained perception through two core innovations.<n> Firstly, we leverage instruction-editing datasets, originally designed for image manipulation, as a unique source of hard negative image-text pairs.<n> Secondly, CLIP-IN incorporates long captions, utilizing rotary positional encodings to capture rich semantic context often missed by standard CLIP.
  arXiv  Detail & Related papers  (2025-08-04T11:57:10Z)
• TNG-CLIP:Training-Time Negation Data Generation for Negation Awareness of CLIP [27.33315565500182]
  We introduce a training-time negation data generation pipeline for vision-language models (VLMs)<n>We propose the first benchmark, Neg-TtoI, for evaluating text-to-image generation models on prompts containing negation.<n>We show that our proposed method, TNG-CLIP, achieves SOTA performance on diverse negation benchmarks of image-to-text matching, text-to-image retrieval, and image generation.
  arXiv  Detail & Related papers  (2025-05-24T00:02:48Z)
• TULIP: Towards Unified Language-Image Pretraining [60.99500935831526]
  We introduce T, an open-source, drop-in replacement for existing CLIP-like models.<n>Our method leverages generative data augmentation, enhanced image-image and text-text contrastive learning, and image/text reconstruction regularization to learn fine-grained visual features.<n>Our approach, scaling to over 1B parameters, outperforms existing state-of-the-art (SOTA) models across benchmarks.
  arXiv  Detail & Related papers  (2025-03-19T17:58:57Z)
• Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP [57.33324843049638]
  We introduce data generation pipelines that employ a large language model (LLM) and a multimodal LLM to produce negation-inclusive captions.<n>Fine-tuning CLIP with data generated from our pipelines, we develop NegationCLIP, which enhances negation awareness while preserving the generality.<n>Experiments on various CLIP architectures validate the effectiveness of our data generation pipelines in enhancing CLIP's ability to perceive negation accurately.
  arXiv  Detail & Related papers  (2025-01-19T01:17:05Z)
• VladVA: Discriminative Fine-tuning of LVLMs [67.14293827774827]
  Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning.<n>We propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs.
  arXiv  Detail & Related papers  (2024-12-05T17:54:27Z)
• Learn "No" to Say "Yes" Better: Improving Vision-Language Models via Negations [43.484570564890866]
  Existing vision-language models (VLMs) treat text descriptions as a unit, confusing individual concepts in a prompt. We present CC-Neg, a dataset containing 228,246 images, true captions and their corresponding negated captions. Using CC-Neg along with modifications to the contrastive loss of CLIP, our proposed CoN-CLIP framework, has an improved understanding of negations.
  arXiv  Detail & Related papers  (2024-03-29T17:33:42Z)
• Towards Realistic Zero-Shot Classification via Self Structural Semantic Alignment [53.2701026843921]
  Large-scale pre-trained Vision Language Models (VLMs) have proven effective for zero-shot classification. In this paper, we aim at a more challenging setting, Realistic Zero-Shot Classification, which assumes no annotation but instead a broad vocabulary. We propose the Self Structural Semantic Alignment (S3A) framework, which extracts structural semantic information from unlabeled data while simultaneously self-learning.
  arXiv  Detail & Related papers  (2023-08-24T17:56:46Z)
• Non-Contrastive Learning Meets Language-Image Pre-Training [145.6671909437841]
  We study the validity of non-contrastive language-image pre-training (nCLIP) We introduce xCLIP, a multi-tasking framework combining CLIP and nCLIP, and show that nCLIP aids CLIP in enhancing feature semantics.
  arXiv  Detail & Related papers  (2022-10-17T17:57:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.