Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge

• URL: http://arxiv.org/abs/2606.27527v1
• Date: Thu, 25 Jun 2026 20:19:50 GMT
• Title: Large Language Model Teaches Visual Students: Cross-Modality Transfer of Fine-Grained Conceptual Knowledge
• Abstract summary: We propose LaViD--Language-to-Visual Knowledge Distillation--a framework for transferring high-level semantic knowledge from a language-only teacher to a vision-only student model.<n>LaViD elicits conceptual signals from an LLM by prompting it to generate multiple-choice questions (MCQs) that probe semantic distinctions between visual classes.
• Score: 35.00522690300795
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) possess broad conceptual knowledge acquired through large-scale text pretraining, yet their potential to supervise models in other modalities remains underexplored. In this work, we propose LaViD--Language-to-Visual Knowledge Distillation--a simple and effective framework for transferring high-level semantic knowledge from a language-only teacher to a vision-only student model. Instead of relying on paired multimodal data, LaViD elicits conceptual signals from an LLM by prompting it to generate multiple-choice questions (MCQs) that probe semantic distinctions between visual classes. Each class is mapped to a soft label distribution over these MCQs, forming a rich conceptual signature that guides the student through an auxiliary distillation loss. Notably, despite using a language-only teacher without access to image data, LaViD consistently outperforms recent methods like MaKD that distill from vision-language models across multiple fine-grained benchmarks. It also achieves competitive or superior performance compared to state-of-the-art visual distillation methods such as DKD and MLKD, with further gains when combined with logit standardization. On the Waterbirds dataset, LaViD substantially improves worst-group accuracy, demonstrating enhanced robustness to spurious correlations with distillation. Code is available at https://github.com/lliangthomas/lavid.

Related papers

• Unleashing Vision-Language Semantics for Deepfake Video Detection [78.7562836979696]
  Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) exhibit strong generalization capabilities in detecting artifacts across different identities.<n>We propose VLAForge, a novel DFD framework that unleashes the potential of such cross-modal semantics to enhance model's discriminability in deepfake detection.
  arXiv  Detail & Related papers  (2026-03-25T16:05:35Z)
• Conformal Cross-Modal Active Learning [16.42479423972555]
  Active Learning aims to minimize annotation costs by strategically selecting the most informative samples for labeling.<n>We introduce Conformal Cross-Modal Acquisition ( CCMA), a novel AL framework that bridges vision and language modalities through a teacher-student architecture.
  arXiv  Detail & Related papers  (2026-03-24T12:59:47Z)
• Lightweight Model Pre-training via Language Guided Knowledge Distillation [28.693835349747598]
  This paper studies the problem of pre-training for small models, which is essential for many mobile devices. We propose a new method named Language-Guided Distillation (LGD) system, which uses category names of the target downstream task to help refine the knowledge transferred between the teacher and student. Experiment results show that the distilled lightweight model using the proposed LGD method presents state-of-the-art performance and is validated on various downstream tasks, including classification, detection, and segmentation.
  arXiv  Detail & Related papers  (2024-06-17T16:07:19Z)
• Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs [49.88461345825586]
  This paper proposes a new framework to enhance the fine-grained image understanding abilities of MLLMs. We present a new method for constructing the instruction tuning dataset at a low cost by leveraging annotations in existing datasets. We show that our model exhibits a 5.2% accuracy improvement over Qwen-VL and surpasses the accuracy of Kosmos-2 by 24.7%.
  arXiv  Detail & Related papers  (2023-10-01T05:53:15Z)
• Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization [52.935150075484074]
  We introduce a well-designed visual tokenizer to translate the non-linguistic image into a sequence of discrete tokens like a foreign language. The resulting visual tokens encompass high-level semantics worthy of a word and also support dynamic sequence length varying from the image. This unification empowers LaVIT to serve as an impressive generalist interface to understand and generate multi-modal content simultaneously.
  arXiv  Detail & Related papers  (2023-09-09T03:01:38Z)
• ViLTA: Enhancing Vision-Language Pre-training through Textual Augmentation [35.05755930636518]
  We propose ViLTA, comprising of two components to further facilitate the model to learn fine-grained representations among image-text pairs. For Masked Language Modeling (MLM), we propose a cross-distillation method to generate soft labels to enhance the robustness of model. For Image-Text Matching (ITM), we leverage the current language encoder to synthesize hard negatives based on the context of language input.
  arXiv  Detail & Related papers  (2023-08-31T12:46:36Z)
• Distilling Large Vision-Language Model with Out-of-Distribution Generalizability [43.984177729641615]
  This paper investigates the distillation of visual representations in large teacher vision-language models into lightweight student models. We propose several metrics and conduct extensive experiments to investigate their techniques. The results demonstrate significant improvements in zero-shot and few-shot student performance on open-vocabulary out-of-distribution classification.
  arXiv  Detail & Related papers  (2023-07-06T17:05:26Z)
• SgVA-CLIP: Semantic-guided Visual Adapting of Vision-Language Models for Few-shot Image Classification [84.05253637260743]
  We propose a new framework, named Semantic-guided Visual Adapting (SgVA), to extend vision-language pre-trained models. SgVA produces discriminative task-specific visual features by comprehensively using a vision-specific contrastive loss, a cross-modal contrastive loss, and an implicit knowledge distillation. State-of-the-art results on 13 datasets demonstrate that the adapted visual features can well complement the cross-modal features to improve few-shot image classification.
  arXiv  Detail & Related papers  (2022-11-28T14:58:15Z)
• A Simple Long-Tailed Recognition Baseline via Vision-Language Model [92.2866546058082]
  The visual world naturally exhibits a long-tailed distribution of open classes, which poses great challenges to modern visual systems. Recent advances in contrastive visual-language pretraining shed light on a new pathway for visual recognition. We propose BALLAD to leverage contrastive vision-language models for long-tailed recognition.
  arXiv  Detail & Related papers  (2021-11-29T17:49:24Z)
• Align before Fuse: Vision and Language Representation Learning with Momentum Distillation [52.40490994871753]
  We introduce a contrastive loss to representations BEfore Fusing (ALBEF) through cross-modal attention. We propose momentum distillation, a self-training method which learns from pseudo-targets produced by a momentum model. ALBEF achieves state-of-the-art performance on multiple downstream vision-language tasks.
  arXiv  Detail & Related papers  (2021-07-16T00:19:22Z)

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.