# MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language Representations

arXiv: https://arxiv.org/abs/2608.25575 · HTML: https://mlsanity.com/paper/2608.25575/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Prompt learning and adaptation of CLIP, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 37 of its 54 references that are in the map.
- First posted on arXiv 26 Aug 2026.

## Placed in

- Multimodal LLMs / vision-language models / [Prompt learning and adaptation of CLIP](https://mlsanity.com/mllm/prompt-learning-and-adaptation-of-clip/)

## Builds on (most cited first, 30 of 37)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency](https://mlsanity.com/paper/2508.18265/) (2025)
- [EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classification](https://mlsanity.com/paper/1709.00029/) (2017)
- [Microsoft COCO Captions: Data Collection and Evaluation Server](https://mlsanity.com/paper/1504.00325/) (2015)
- [Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models](https://mlsanity.com/paper/1505.04870/) (2015)
- [Remote Sensing Image Scene Classification: Benchmark and State of the Art](https://mlsanity.com/paper/1703.00121/) (2017)
- [When and why vision-language models behave like bags-of-words, and what to do about it?](https://mlsanity.com/paper/2210.01936/) (2022)
- [Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality](https://mlsanity.com/paper/2204.03162/) (2022)
- [SLIP: Self-supervision meets Language-Image Pre-training](https://mlsanity.com/paper/2112.12750/) (2021)
- [Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm](https://mlsanity.com/paper/2110.05208/) (2021)
- [Challenges in Representation Learning: A report on three machine learning contests](https://mlsanity.com/paper/1307.0414/) (2013)
- [What's "up" with vision-language models? Investigating their struggle with spatial reasoning](https://mlsanity.com/paper/2310.19785/) (2023)
- [SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality](https://mlsanity.com/paper/2306.14610/) (2023)
- [Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking](https://mlsanity.com/paper/2601.04720/) (2026)
- [VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks](https://mlsanity.com/paper/2410.05160/) (2024)
- [Improving CLIP Training with Language Rewrites](https://mlsanity.com/paper/2305.20088/) (2023)
- [CREPE: Can Vision-Language Foundation Models Reason Compositionally?](https://mlsanity.com/paper/2212.07796/) (2022)
- [VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena](https://mlsanity.com/paper/2112.07566/) (2021)
- [VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations](https://mlsanity.com/paper/2207.00221/) (2022)
- [Probing Image-Language Transformers for Verb Understanding](https://mlsanity.com/paper/2106.09141/) (2021)
- [CLIP-KD: An Empirical Study of CLIP Model Distillation](https://mlsanity.com/paper/2307.12732/) (2023)
- [DreamLIP: Language-Image Pre-training with Long Captions](https://mlsanity.com/paper/2403.17007/) (2024)
- [VeCLIP: Improving CLIP Training via Visual-enriched Captions](https://mlsanity.com/paper/2310.07699/) (2023)
- [TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives](https://mlsanity.com/paper/2411.02545/) (2024)
- [UniCLIP: Unified Framework for Contrastive Language-Image Pre-training](https://mlsanity.com/paper/2209.13430/) (2022)
- [Equivariant Similarity for Vision-Language Foundation Models](https://mlsanity.com/paper/2303.14465/) (2023)
- [Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding](https://mlsanity.com/paper/2312.00081/) (2023)

## Abstract (arXiv)

Pretrained vision-language models such as CLIP excel at zero-shot recognition but often fail at compositionality, particularly attribute-object and relational structures. Recent studies mitigate this issue by augmenting training with synthetic hard negatives generated by a cascade of large language models and text-to-image models, which incurs substantial pipeline overhead. We instead propose MLLMCLIP, a heterogeneous distillation framework that transfers multimodal knowledge directly from a generative Multimodal Large Language Model (MLLM) teacher into a discriminative CLIP student, bypassing synthetic data entirely. To bridge the architectural mismatch between the two paradigms, we introduce an attention-based per-layer token selection and a CKA-based distillation loss. Compared to prior CLIP-enhancement methods, MLLMCLIP achieves state-of-the-art compositional accuracy while delivering consistent gains on standard zero-shot classification and image-text retrieval, showing that feature-level distillation strengthens both compositional and general vision-language representation capability.