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

arXiv: https://arxiv.org/abs/2610.03842 · HTML: https://mlsanity.com/paper/2610.03842/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in VLM benchmarks and visual reasoning, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 2 Oct 2026.

## Placed in

- Multimodal LLMs / vision-language models / [VLM benchmarks and visual reasoning](https://mlsanity.com/mllm/vlm-benchmarks-and-visual-reasoning/)
- 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)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision](https://mlsanity.com/paper/2102.05918/) (2021)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations](https://mlsanity.com/paper/1602.07332/) (2016)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering](https://mlsanity.com/paper/2209.09513/) (2022)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)
- [Towards VQA Models That Can Read](https://mlsanity.com/paper/1904.08920/) (2019)
- [MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models](https://mlsanity.com/paper/2306.13394/) (2023)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [Vision-Language Models for Vision Tasks: A Survey](https://mlsanity.com/paper/2304.00685/) (2023)
- [SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference](https://mlsanity.com/paper/2410.04417/) (2024)
- [IconQA: A New Benchmark for Abstract Diagram Understanding and Visual Language Reasoning](https://mlsanity.com/paper/2110.13214/) (2021)
- [SPViT: Enabling Faster Vision Transformers via Soft Token Pruning](https://mlsanity.com/paper/2112.13890/) (2021)
- [LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation](https://mlsanity.com/paper/2408.15881/) (2024)
- [LLaVA-KD: A Framework of Distilling Multimodal Large Language Models](https://mlsanity.com/paper/2410.16236/) (2024)
- [LLAVADI: What Matters For Multimodal Large Language Models Distillation](https://mlsanity.com/paper/2407.19409/) (2024)
- [Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Model Enhancement](https://mlsanity.com/paper/2412.01282/) (2024)
- [VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization](https://mlsanity.com/paper/2508.05211/) (2025)
- [VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs](https://mlsanity.com/paper/2510.17205/) (2025)
- [CompoDistill: Attention Distillation for Compositional Reasoning in Multimodal LLMs](https://mlsanity.com/paper/2510.12184/) (2025)

## Abstract (arXiv)

Knowledge distillation is crucial for deploying vision-language models on resource-constrained devices. However, existing methods typically impose uniform supervision across visual tokens or rely on static token selection, which confuses task-relevant cues with background noise and degrades cross-modal reasoning. To address this limitation, we propose Key Visual Evidence-guided Knowledge Distillation (KVE-KD), a framework that dynamically focuses feature distillation on task-relevant visual tokens identified by the teacher model. Specifically, KVE-KD appoints the final pre-generation textual token as a unified semantic anchor and identifies the target cross-modal fusion layer by analyzing changes in the anchor representation through iterative visual-token contribution removal. Within this layer, KVE-KD ranks visual tokens via the anchor-conditioned attention distribution and selects the most informative visual tokens as key visual evidence with normalized entropy. The key visual evidence subsequently guides focused visual feature distillation, making the student align closely with the teacher's task-relevant visual representations while suppressing irrelevant background information. Extensive experiments on six benchmarks demonstrate that KVE-KD outperforms state-of-the-art cross-modal distillation methods, with particularly pronounced gains on tasks requiring complex reasoning and fine-grained visual understanding. Importantly, these improvements are achieved without introducing any inference-time overhead. The source code is available at https://github.com/zhangjianbin07/KVE-KD.