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

arXiv:2608.25575 · cs.CV, cs.AI · Submitted 2026-08-26 · Read on arXiv

cs.CV, cs.AI

Submitted: 2026-08-26

Updated: 2026-08-26

Comments: EMNLP 2026 Main Conference

Code: https://github.com/LijieFan/LaCLIP

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Distillation — 52× in this paper · explained in 2 episodes
• Benchmark — 22× in this paper · explained in 2 episodes
• Accuracy — 9× in this paper · explained in 1 episode
• Alignment — 8× in this paper · explained in 1 episode
• Transformer — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Embeddings — 4× in this paper · explained in 2 episodes
• Feature Extraction — 4× in this paper · explained in 2 episodes
• Generative Model — 4× in this paper · explained in 2 episodes
• Multimodal Large Language Model — 4× in this paper
• Foundation Model — 3× in this paper · explained in 3 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Generative Models — 3× in this paper · explained in 2 episodes
• Loss Function — 3× in this paper · explained in 2 episodes
• Ablation Studies — 2× in this paper · explained in 1 episode
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Downstream Tasks — 2× in this paper · explained in 2 episodes
• Knowledge Distillation — 2× in this paper · explained in 11 episodes
• Unified Framework — 2× in this paper · explained in 5 episodes
• AdamW Optimizer — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Contrastive Learning — 1× in this paper · explained in 5 episodes
• Data Augmentation — 1× in this paper · explained in 7 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalizability — 1× in this paper · explained in 6 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Qwen3-VL Technical Report
• Microsoft COCO Captions: Data Collection and Evaluation Server
• ComKD-CLIP: Comprehensive Knowledge Distillation for Contrastive Language-Image Pre-traning Model
• The Llama 3 Herd of Models
• Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and Ranking
• VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks
• Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigm
• What's "up" with vision-language models? Investigating their struggle with spatial reasoning
• VLM2Vec-V2: Advancing Multimodal Embedding for Videos, Images, and Visual Documents
• Image Retrieval from Contextual Descriptions
• Modeling Caption Diversity in Contrastive Vision-Language Pretraining
• Preserving Multi-Modal Capabilities of Pre-trained VLMs for Improving Vision-Linguistic Compositionality
• VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena
• InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency
• Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association
• LLAVADI: What Matters For Multimodal Large Language Models Distillation
• A Survey on Knowledge Distillation of Large Language Models
• Qwen3 Technical Report
• When and why vision-language models behave like bags-of-words, and what to do about it?
• VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models