Research map / Vision-language and multimodal / Multimodal LLMs
V-LUMEN: Visual Lookup Memory for Embedding Scaling in Vision-Language Models
Miso Choi, Daekeun Kim, Eunji Kim, Jungbeom Lee
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's full text. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes V-LUMEN, an extension of embedding scaling to vision-language models using visual lookup memory, based on the abstract only.
Problem
Existing embedding scaling methods target discrete text tokens; it is unclear whether such mechanisms extend to vision-language models whose visual representations differ from text tokens.
Approach
Extends embedding scaling from text tokens to visual representations in vision-language models via a visual lookup memory, increasing model capacity at the embedding level rather than by expanding transformer depth or width. Details beyond the abstract are not available.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| attach V-Lumen visual lookup memory to a frozen backbone | Qwen3-VL-2B-Instruct (frozen) · five reasoning benchmarks (avg) | accuracy: 2.18 -> 19.97 | Improved |
| add V-Lumen without any in-domain adaptation | Qwen3-VL-2B (frozen) · TextVQA, OCR-VQA, VizWiz-VQA (zero-shot) | accuracy: TextVQA 11.00 -> 37.17; OCR-VQA 13.80 -> 47.67; VizWiz 2.00 -> 9.97 | Improved |
| move part of LoRA capacity into V-Lumen at matched total budget (ablation) | LoRA adapter on Qwen3-VL-2B · five reasoning benchmarks (avg) | accuracy: 22.76 -> 23.33 | No clear effect |
| move part of MoE capacity into V-Lumen at matched total budget (ablation) | MoE adapter on Qwen3-VL-2B · five reasoning benchmarks (avg) | accuracy: 19.03 -> 19.10 | No clear effect |
| add V-Lumen on top of identical LoRA(0.5) adapter (rank-matched) (ablation) | LoRA(0.5) on Qwen3-VL-2B · five reasoning benchmarks (avg) | accuracy: 23.79 -> 23.33 | No clear effect |
| add V-Lumen to LoRA at matched budget (ablation) | LoRA adapter · MMMU-Pro | accuracy: 26.50 -> 29.20 | Improved |
| add V-Lumen to LoRA at matched budget (ablation) | LoRA adapter · VisRes | accuracy: 22.03 -> 21.70 | Hurt |
| add V-Lumen to MoE at matched budget (ablation) | MoE adapter · MMMU-Pro | accuracy: 20.10 -> 19.00 | Hurt |
| grow memory table from 16,384 to 655,360 rows per cell (ablation) | V-Lumen lookup · lookup latency (one fusion layer) | lookup total (ms): 11.22 -> 11.23 | No clear effect |
| add more memory rows (ablation) | V-Lumen · accuracy | accuracy | No clear effect |
| widen retrieved memory vectors (ablation) | V-Lumen · accuracy | accuracy | Improved |
| add V-Lumen memory to adapter, probed with logit lens | MoE (VisRes) and LoRA (MMMU-Pro) · final-layer top-1 accuracy | top-1 accuracy: VisRes 0.236 -> 0.251; MMMU-Pro 0.277 -> 0.289 | Mixed |
Closest papers by meaning
- Bridging Vision and Language Spaces with Assignment Prediction (ICLR 2024 · similarity 0.90)
- Towards General Continuous Memory for Vision-Language Models (NeurIPS 2025 · similarity 0.90)
- VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models (CVPR 2026 · similarity 0.89)
- VISion On Request: Enhanced VLLM efficiency with sparse, dynamically selected, vision-language interactions (CVPR 2026 · similarity 0.89)
- VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks (ICLR 2025 · similarity 0.89)
- Large Vision-Language Models Get Lost in Attention (ICML 2026 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
