VLM Distillation

VLM: Vision-Language Model

Overview

Vision-language model distillation studies how to transfer image-and-text understanding from a teacher model to a smaller or more efficient student, often for tasks such as visual question answering, retrieval, video reasoning, and robotics. Methods align teacher and student features, logits, attention, or relationships between visual and text representations; others train on teacher-generated rationales or student-generated responses, sometimes using multiple teachers or privileged visual cues. Work also targets practical constraints such as fewer visual tokens, quantization, and deployment on devices with limited memory or compute. A central challenge is deciding which teacher signals are reliable and grounded in evidence the student can access, since copying a teacher too closely can preserve its errors or encourage shortcuts rather than visual reasoning.

Latest papers

CardsList

133 papers10 papers in the last four weeks, down 70% on the four weeks before. 0.1% of all new papers.

  1. As Student Rollouts Continue, Visual Backdoors Keep Growing

    Nov 17, 2026Zane Fu, Yanzhao Zheng, Jinze Liu +7Backdoor Attacks on VLMsOn-Policy Distillation

  2. Teach with Blinks: Breaking Linguistic Momentum in On-Policy Distillation for Fine-Grained Multimodal Perception

    Nov 12, 2026Tangzheng Lian, Hang Zhang, Guanyu Hu +4VLM DistillationOn-Policy Distillation

  3. Prior-as-Skill: Remember Outside and Read Inside with On-Policy Self-Distillation for Self-Evolving VLM Agents

    Nov 11, 2026Yan Lin, Jingyu Sun, Yifei Qian +6Memory-Augmented VLMsTemporal Reasoning in VLMs

  4. DiFiT: Distribution-Fidelity-guided Visual Token Pruning for Multimodal Large Language Models

    Nov 11, 2026Jingyuan Zhang, Nihao Niu, Xinyang Lv +4Visual Token PruningLVLM Pruning

  5. SD-LoRA: Training-Time Structural Distillation into LoRA for Few-Shot Vision-Language Adaptation

    Nov 4, 2026Mohammed Rahman Sherif Khan Mohammad, Ardhendu Behera, Sandip Pradhan +2Few-Shot VLM AdaptationVLM Adaptation

  6. SurgPace: Complexity-Aware Progressive Distillation for Surgical Multimodal Large Language Models

    Nov 2, 2026Zhicheng He, Xiaohan Xing, Hongqiu Wang +7VLM DistillationMultimodal Large Language Models

  7. RSKD: Grounding Semantic Consistency in Driving VLMs via Distillation

    Oct 26, 2026Chuchu Xie, Yang Zhong, Kangan Qian +3VLM DistillationKnowledge Distillation

  8. Recursive CLIP: Vision-Language Distillation with Looped Transformer Blocks

    Oct 25, 2026Szymon Mazurek, Alberto Presta, Michał ByraVision-Language ModelsRecurrent Transformers

  9. Edit, Don't Imitate: Minimal-Edit On-Policy Distillation for Multimodal Reasoning

    Oct 21, 2026Wen Ye, Ailin Deng, Zirui Wang +8Reasoning for VLMsVision-Language Models

  10. When Evidence Vanishes: Distilling Visual-Evidence Dependency in Medical Vision-Language Models

    Oct 16, 2026Qizhen Lan, Yiling Ma, Ruiqi Chen +8Medical VLMsVisual Evidence Sensitivity in VLMs

  11. Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models

    Oct 15, 2026Yuqi Xiong, Chunyi Peng, Zhipeng Xu +5VLM DistillationRL for VLMs

  12. Do As I Do, Not As I Say: On-Policy Distillation Inherits the Teacher in Vision-Language Models

    Oct 14, 2026Frank F. Yang, Kefei Yan, Yiren Wang +1VLM DistillationOn-Policy Distillation

  13. DVTR-KD: Distilling Vision-Language Models via Intermediate Visual Token Reconstruction

    Oct 13, 2026Haolan Wei, Jiahui Wang, Junli Zha +4VLM DistillationEfficient VLM Inference

  14. VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning

    Oct 10, 2026Jiahe FengVLM DistillationVisually Grounded Reasoning

  15. CV-OPD: Contrastive Vision On-policy Distillation

    Oct 9, 2026Haowei Wang, Hao Lin, Qi Zhu +4contrastive knowledge distillationVLM Distillation

  16. KVE-KD: Key Visual Evidence-Guided Knowledge Distillation for Vision-Language Models

    Oct 2, 2026Jianbin Zhang, Xin Sun, Shanwen Wang +2VLM DistillationCross-Modal Knowledge Distillation

  17. GRAFT: Growing Agglomerative Foundation Models via Continual Teacher Distillation

    Oct 1, 2026Zhenghao Zhao, Chi Zhang, Qingshuang Chen +1Multi-Teacher Knowledge DistillationVision Foundation Models

  18. Where-OPD: Spatially Guided On-Policy Self-Distillation of MLLMs with Synthetic Scenes

    Oct 1, 2026Sophia Sirko-Galouchenko, Monika Wysoczanska, Andrei Bursuc +2VLM DistillationMultimodal Large Language Models

  19. HAWK: Rethinking Multimodal Drafting for Speculative Decoding

    Sep 30, 2026Wenhan Yang, Anirudh Rao, Ashwin ChandraEfficient Multimodal InferenceVLM Distillation

  20. MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language Models

    Sep 30, 2026Yanshu Li, Jiaqian Li, Canran Xiao +3Cross-Modal Knowledge DistillationMultimodal ICL

  21. RS-OPSD: Reliable Privileged On-Policy-Self-Distillation for Ultra-High-Resolution Remote Sensing VQA

    Sep 29, 2026Chengjie Jiang, Yunqi Zhou, Jiafeng Yan +3Remote Sensing Image UnderstandingVisual Question Answering