# AME: Aligned Manifold Entropy for Robust Vision-Language Distillation

arXiv: https://arxiv.org/abs/2508.08644 · HTML: https://mlsanity.com/paper/2508.08644/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in MLLM training and visual instruction tuning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 49 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [MLLM training and visual instruction tuning](https://mlsanity.com/mllm/mllm-training-and-visual-instruction-tuning/)
- Knowledge distillation / [Multimodal distillation](https://mlsanity.com/distill/multimodal-distillation/)

## Builds on (most cited first, 28 of 28)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks](https://mlsanity.com/paper/1908.02265/) (2019)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [LXMERT: Learning Cross-Modality Encoder Representations from Transformers](https://mlsanity.com/paper/1908.07490/) (2019)
- [CLIP-Adapter: Better Vision-Language Models with Feature Adapters](https://mlsanity.com/paper/2110.04544/) (2021)
- [Learning Robust Global Representations by Penalizing Local Predictive Power](https://mlsanity.com/paper/1905.13549/) (2019)
- [Open-vocabulary Object Detection via Vision and Language Knowledge Distillation](https://mlsanity.com/paper/2104.13921/) (2021)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [DenseCLIP: Language-Guided Dense Prediction with Context-Aware Prompting](https://mlsanity.com/paper/2112.01518/) (2021)
- [Image Segmentation Using Text and Image Prompts](https://mlsanity.com/paper/2112.10003/) (2021)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [Deep Modular Co-Attention Networks for Visual Question Answering](https://mlsanity.com/paper/1906.10770/) (2019)
- [Bilinear Attention Networks](https://mlsanity.com/paper/1805.07932/) (2018)
- [Self-regulating Prompts: Foundational Model Adaptation without Forgetting](https://mlsanity.com/paper/2307.06948/) (2023)
- [Knowledge distillation: A good teacher is patient and consistent](https://mlsanity.com/paper/2106.05237/) (2021)
- [Towards Understanding Knowledge Distillation](https://mlsanity.com/paper/2105.13093/) (2021)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [PromptDet: Towards Open-vocabulary Detection using Uncurated Images](https://mlsanity.com/paper/2203.16513/) (2022)
- [Knowledge Adaptation for Efficient Semantic Segmentation](https://mlsanity.com/paper/1903.04688/) (2019)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [Unpaired Multi-modal Segmentation via Knowledge Distillation](https://mlsanity.com/paper/2001.03111/) (2020)
- [Improving Zero-Shot Generalization for CLIP with Synthesized Prompts](https://mlsanity.com/paper/2307.07397/) (2023)
- [CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet](https://mlsanity.com/paper/2212.06138/) (2022)
- [Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation](https://mlsanity.com/paper/2407.03056/) (2024)
- [Knowledge Distillation with Feature Maps for Image Classification](https://mlsanity.com/paper/1812.00660/) (2018)

## Built on by (most cited first, 2 of 2)

- [When Modalities Conflict: How Unimodal Reasoning Uncertainty Governs Preference Dynamics in MLLMs](https://mlsanity.com/paper/2511.02243/) (2025)
- [ViPER: Empowering the Self-Evolution of Visual Perception Abilities in Vision-Language Model](https://mlsanity.com/paper/2510.24285/) (2025)

## Abstract (arXiv)

Knowledge distillation is a long-established technique for knowledge transfer, and has regained attention in the context of the recent emergence of large vision-language models (VLMs). However, vision-language knowledge distillation often requires sufficient training data to achieve robust generalization on amples with ambiguous or boundary-adjacent representations, which are associated with high predictive uncertainty. Critically, collecting such large-scale, task-specific data for training is often impractical in real-world scenarios. To address this major challenge arising from the entanglement of uncertainty and cross-modal feature representation, we propose Aligned Manifold Entropy for Robust Vision-Language Distillation (AME), aiming to achieve robust generalization under real-world conditions. AME applies entropy minimization over a reconfigured shared manifold, where multi-modal data (i.e., image and text) are bridged through a pair of projection functions, conducive to structural compression for cross-modal feature representations. This enables robust knowledge distillation under low-data regimes, while requiring no architectural modifications to the backbone. As a result, it can serve as a plug-and-play module compatible with a wide range of vision-language distillation frameworks. Notably, our theoretical analysis reveals that integrating knowledge distillation with entropy minimization over the shared manifold leads to a tighter generalization error bound. Extensive experiments across diverse distillation architectures and training settings demonstrate that AME consistently facilitates robust knowledge distillation, resulting in superior generalization performance across a wide spectrum of downstream tasks.