# UniPercept: Towards Unified Perceptual-Level Image Understanding across Aesthetics, Quality, Structure, and Texture

arXiv: https://arxiv.org/abs/2512.21675 · HTML: https://mlsanity.com/paper/2512.21675/

## Key facts

- Cited by 22 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 37 of its 59 references that are in the map.
- First posted on arXiv 25 Dec 2025.

## 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, 30 of 37)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [MMBench: Is Your Multi-modal Model an All-around Player?](https://mlsanity.com/paper/2307.06281/) (2023)
- [Describing Textures in the Wild](https://mlsanity.com/paper/1311.3618/) (2013)
- [MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI](https://mlsanity.com/paper/2311.16502/) (2023)
- [InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models](https://mlsanity.com/paper/2504.10479/) (2025)
- [MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts](https://mlsanity.com/paper/2310.02255/) (2023)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Are We on the Right Way for Evaluating Large Vision-Language Models?](https://mlsanity.com/paper/2403.20330/) (2024)
- [Emerging Properties in Unified Multimodal Pretraining](https://mlsanity.com/paper/2505.14683/) (2025)
- [MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark](https://mlsanity.com/paper/2409.02813/) (2024)
- [Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels](https://mlsanity.com/paper/2312.17090/) (2023)
- [OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models](https://mlsanity.com/paper/2305.07895/) (2023)
- [ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment](https://mlsanity.com/paper/2403.05135/) (2024)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset](https://mlsanity.com/paper/2505.09568/) (2025)
- [KonIQ-10k: An ecologically valid database for deep learning of blind image quality assessment](https://mlsanity.com/paper/1910.06180/) (2019)
- [SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformers](https://mlsanity.com/paper/2410.10629/) (2024)
- [Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild](https://mlsanity.com/paper/2401.13627/) (2024)
- [Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision](https://mlsanity.com/paper/2309.14181/) (2023)
- [LLaVA-OneVision-1.5: Fully Open Framework for Democratized Multimodal Training](https://mlsanity.com/paper/2509.23661/) (2025)
- [HPSv3: Towards Wide-Spectrum Human Preference Score](https://mlsanity.com/paper/2508.03789/) (2025)
- [SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer](https://mlsanity.com/paper/2501.18427/) (2025)
- [Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models](https://mlsanity.com/paper/2311.06783/) (2023)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Depicting Beyond Scores: Advancing Image Quality Assessment through Multi-modal Language Models](https://mlsanity.com/paper/2312.08962/) (2023)
- [Q-Insight: Understanding Image Quality via Visual Reinforcement Learning](https://mlsanity.com/paper/2503.22679/) (2025)

## Built on by (most cited first, 22 of 22)

- [GEMS: Agent-Native Multimodal Generation with Memory and Skills](https://mlsanity.com/paper/2603.28088/) (2026)
- [PiD: Fast and High-Resolution Latent Decoding with Pixel Diffusion](https://mlsanity.com/paper/2605.23902/) (2026)
- [ERNIE-Image Technical Report](https://mlsanity.com/paper/2605.25347/) (2026)
- [AIBench: Evaluating Visual-Logical Consistency in Academic Illustration Generation](https://mlsanity.com/paper/2603.28068/) (2026)
- [AesRM: Improving Video Aesthetics with Expert-Level Feedback](https://mlsanity.com/paper/2604.28078/) (2026)
- [SANA-Video 2.0: Hybrid Linear Attention with Attention Residuals for Efficient Video Generation](https://mlsanity.com/paper/2607.21553/) (2026)
- [LucidNFT: LR-Anchored Multi-Reward Preference Optimization for Flow-Based Real-World Super-Resolution](https://mlsanity.com/paper/2603.05947/) (2026)
- [One Model, Two Minds: Task-Conditioned Reasoning for Unified Image Quality and Aesthetic Assessment](https://mlsanity.com/paper/2603.19779/) (2026)
- [Sketch Then Paint: Hierarchical Reinforcement Learning for Diffusion Multi-Modal Large Language Models](https://mlsanity.com/paper/2605.16842/) (2026)
- [Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision](https://mlsanity.com/paper/2609.35718/) (2026)
- [Accelerating Masked Image Generation by Learning Controlled Latent Dynamics](https://mlsanity.com/paper/2602.23996/) (2026)
- [DynT2I-Eval: A Dynamic Evaluation Framework for Text-to-Image Models](https://mlsanity.com/paper/2605.06170/) (2026)
- [PhotoFlow: Agentic 3D Virtual Photography Missions](https://mlsanity.com/paper/2605.23771/) (2026)
- [HiTokSR: A Coarse-to-Fine Tokenizer with Hierarchical Codebooks for High-Fidelity Real-World Image Super-Resolution](https://mlsanity.com/paper/2606.01157/) (2026)
- [ShotCrop3: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions](https://mlsanity.com/paper/2606.05635/) (2026)
- [Beyond Absolute Scores: Relative Edit-induced Difference for Generalizable Image Aesthetic Assessment](https://mlsanity.com/paper/2606.05778/) (2026)
- [COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models](https://mlsanity.com/paper/2606.28696/) (2026)
- [AesCanvas: A Large-Scale Dataset and Benchmark for Aesthetic Critique and Contextual Suitability](https://mlsanity.com/paper/2608.26713/) (2026)
- [DramaChain Bench: An End-to-End Benchmark for Short-Drama Generation](https://mlsanity.com/paper/2609.00646/) (2026)
- [SoL-Refiner: Speed-of-Light One-Step Refinement for High-Resolution Video](https://mlsanity.com/paper/2609.37969/) (2026)
- [PortraitAes: Intent-Conditioned Structured Portrait Aesthetic Assessment](https://mlsanity.com/paper/2610.05010/) (2026)
- [Golden Anchor for Video Generation](https://mlsanity.com/paper/2610.13217/) (2026)

## Abstract (arXiv)

Multimodal large language models (MLLMs) have achieved remarkable progress in visual understanding tasks such as visual grounding, segmentation, and captioning. However, their ability to perceive perceptual-level image features remains limited. In this work, we present UniPercept-Bench, a unified framework for perceptual-level image understanding across three key domains: Aesthetics, Quality, Structure and Texture. We establish a hierarchical definition system and construct large-scale datasets to evaluate perceptual-level image understanding. Based on this foundation, we develop a strong baseline UniPercept trained via Domain-Adaptive Pre-Training and Task-Aligned RL, enabling robust generalization across both Visual Rating (VR) and Visual Question Answering (VQA) tasks. UniPercept outperforms existing MLLMs on perceptual-level image understanding and can serve as a plug-and-play reward model for text-to-image generation. This work defines Perceptual-Level Image Understanding in the era of MLLMs and, through the introduction of a comprehensive benchmark together with a strong baseline, provides a solid foundation for advancing perceptual-level multimodal image understanding.