# Bounded-Compute Multimodal Regression for Product-Rating Prediction

arXiv: https://arxiv.org/abs/2605.27737 · HTML: https://mlsanity.com/paper/2605.27737/

## Key facts

- Cited by 1 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 25 of its 29 references that are in the map.
- First posted on arXiv 26 May 2026.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [MiniCPM-V: A GPT-4V Level MLLM on Your Phone](https://mlsanity.com/paper/2408.01800/) (2024)
- [DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding](https://mlsanity.com/paper/2412.10302/) (2024)
- [8-bit Optimizers via Block-wise Quantization](https://mlsanity.com/paper/2110.02861/) (2021)
- [What matters when building vision-language models?](https://mlsanity.com/paper/2405.02246/) (2024)
- [SmolVLM: Redefining small and efficient multimodal models](https://mlsanity.com/paper/2504.05299/) (2025)
- [PaliGemma 2: A Family of Versatile VLMs for Transfer](https://mlsanity.com/paper/2412.03555/) (2024)
- [MobileVLM V2: Faster and Stronger Baseline for Vision Language Model](https://mlsanity.com/paper/2402.03766/) (2024)
- [Building and better understanding vision-language models: insights and future directions](https://mlsanity.com/paper/2408.12637/) (2024)
- [VBPR: Visual Bayesian Personalized Ranking from Implicit Feedback](https://mlsanity.com/paper/1510.01784/) (2015)
- [MobileVLM : A Fast, Strong and Open Vision Language Assistant for Mobile Devices](https://mlsanity.com/paper/2312.16886/) (2023)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception](https://mlsanity.com/paper/2401.08276/) (2024)
- [Multimodal Recommender Systems: A Survey](https://mlsanity.com/paper/2302.03883/) (2023)
- [SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning](https://mlsanity.com/paper/2209.05040/) (2022)
- [VQualA 2025 Challenge on Engagement Prediction for Short Videos: Methods and Results](https://mlsanity.com/paper/2509.02969/) (2025)
- [Delving Deep into Engagement Prediction of Short Videos](https://mlsanity.com/paper/2410.00289/) (2024)
- [Engagement Prediction of Short Videos with Large Multimodal Models](https://mlsanity.com/paper/2508.02516/) (2025)

## Built on by (most cited first, 1 of 1)

- [AdaKerNet: Neural Kernel Decoding for Task-Adaptive Prediction with Multimodal Large Models](https://mlsanity.com/paper/2609.36368/) (2026)

## Abstract (arXiv)

Vision-language models (VLMs) are increasingly attractive for multimodal quality assessment, but their default reliance on autoregressive text generation and dynamic visual processing is poorly matched to scalar regression under strict latency budgets. We present a bounded-compute adaptation of SmolVLM2-256M-Video-Instruct for product-rating prediction in the LoViF 2026 Efficient VLM challenge. Motivated by recent multimodal engagement-prediction results showing that feature-based regression can outperform token-based score generation, we replace the language-modeling head with a lightweight two-layer MLP fed by pooled decoder states, and we enforce deterministic inputs through fixed 384x384 images and truncated metadata. Across controlled ablations, static global image processing slightly outperforms dynamic tiling, and scaling from 100K to 16M training examples substantially improves validation correlation. Under the official held-out evaluation, our 228M-parameter model achieves 0.39 PLCC and 0.40 CES, providing a strong and reproducible baseline for resource-constrained multimodal regression.