Boosting Visual Instruction Tuning with Self-Supervised Guidance

• URL: http://arxiv.org/abs/2604.12966v1
• Date: Tue, 14 Apr 2026 16:59:53 GMT
• Title: Boosting Visual Instruction Tuning with Self-Supervised Guidance
• Abstract summary: Multimodal large language models (MLLMs) perform well on many vision-centric tasks but often struggle with vision-centric problems.<n>Recent evidence suggests that this limitation arises from under-utilization of visual information during instruction tuning.<n>We propose a simple and lightweight approach that augments visual instruction tuning with a small number of visually grounded self-supervised tasks.
• Score: 25.75897924846719
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Multimodal large language models (MLLMs) perform well on many vision-language tasks but often struggle with vision-centric problems that require fine-grained visual reasoning. Recent evidence suggests that this limitation arises not from weak visual representations, but from under-utilization of visual information during instruction tuning, where many tasks can be partially solved using language priors alone. We propose a simple and lightweight approach that augments visual instruction tuning with a small number of visually grounded self-supervised tasks expressed as natural language instructions. By reformulating classical self-supervised pretext tasks, such as rotation prediction, color matching, and cross-view correspondence, as image-instruction-response triplets, we introduce supervision that cannot be solved without relying on visual evidence. Our approach requires no human annotations, no architectural modifications, and no additional training stages. Across multiple models, training regimes, and benchmarks, injecting only a small fraction (3-10%) of such visually grounded instructions consistently improves performance on vision-centric evaluations. Our findings highlight instruction tuning with visually grounded SSL tasks as a powerful lever for improving visual reasoning in MLLMs through simple adjustments to the training data distribution. Code available at: https://github.com/sirkosophia/V-GIFT

Related papers

• Latent Implicit Visual Reasoning [59.39913238320798]
  We propose a task-agnostic mechanism that trains LMMs to discover and use visual reasoning tokens without explicit supervision.<n>Our approach outperforms direct fine-tuning and achieves state-of-the-art results on a diverse range of vision-centric tasks.
  arXiv  Detail & Related papers  (2025-12-24T14:59:49Z)
• Visual Jigsaw Post-Training Improves MLLMs [58.29961336087896]
  We introduce Visual Jigsaw, a generic self-supervised post-training framework designed to strengthen visual understanding in large language models (MLLMs)<n>Visual Jigsaw is formulated as a general ordering task: visual inputs are partitioned, shuffled, and the model must reconstruct the visual information by producing the correct permutation in natural language.<n>Extensive experiments demonstrate substantial improvements in fine-grained perception, temporal reasoning, and 3D spatial understanding.
  arXiv  Detail & Related papers  (2025-09-29T17:59:57Z)
• Visual Representation Alignment for Multimodal Large Language Models [38.319869213758686]
  Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks.<n>But they remain limited in vision-centric tasks such as object counting or spatial reasoning.<n>We present VIsual Representation ALignment (VIRAL), a simple yet effective regularization strategy that aligns the internal visual representations of MLLMs with those of pre-trained vision foundation models.
  arXiv  Detail & Related papers  (2025-09-09T17:59:14Z)
• ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs [98.27348724529257]
  We introduce ViCrit (Visual Caption Hallucination Critic), an RL proxy task that trains VLMs to localize a subtle, synthetic visual hallucination injected into paragraphs of human-written image captions.<n>Models trained with the ViCrit Task exhibit substantial gains across a variety of vision-language models benchmarks.
  arXiv  Detail & Related papers  (2025-06-11T19:16:54Z)
• Do we Really Need Visual Instructions? Towards Visual Instruction-Free Fine-tuning for Large Vision-Language Models [127.38740043393527]
  We propose ViFT, a visual instruction-free fine-tuning framework for LVLMs.<n>We only require the text-only instructions and image caption data during training, to separately learn the task-solving and visual perception abilities.<n> Experimental results demonstrate that ViFT can achieve state-of-the-art performance on several visual reasoning and visual instruction following benchmarks.
  arXiv  Detail & Related papers  (2025-02-17T04:38:12Z)
• Looking Beyond Text: Reducing Language bias in Large Vision-Language Models via Multimodal Dual-Attention and Soft-Image Guidance [67.26434607115392]
  Large vision-language models (LVLMs) have achieved impressive results in various vision-language tasks. LVLMs suffer from hallucinations caused by language bias, leading to diminished focus on images and ineffective visual comprehension. We propose LACING to address the language bias of LVLMs with muLtimodal duAl-attention meChanIsm (MDA) aNd soft-image Guidance (IFG)
  arXiv  Detail & Related papers  (2024-11-21T16:33:30Z)
• TWIST & SCOUT: Grounding Multimodal LLM-Experts by Forget-Free Tuning [54.033346088090674]
  We introduce TWIST & SCOUT, a framework that equips pre-trained MLLMs with visual grounding ability.<n>To fine-tune the model effectively, we generate a high-quality synthetic dataset we call SCOUT.<n>This dataset provides rich supervision signals, describing a step-by-step multimodal reasoning process.
  arXiv  Detail & Related papers  (2024-10-14T13:35:47Z)
• What Makes for Good Visual Tokenizers for Large Language Models? [26.488269091290597]
  We investigate proper pre-training methods to build good visual tokenizers, making Large Language Models (LLMs) powerful Multimodal Large Language Models (MLLMs) We discuss different visual tokenizers pre-trained with dominant methods (i.e., DeiT, CLIP, MAE, DINO) We obtain a new MLLM equipped with a tailored Good Visual Tokenizer (GVT), which exhibits strong visual comprehension capability at multiple scales.
  arXiv  Detail & Related papers  (2023-05-20T16:11:26Z)

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.