# Science-T2I: Addressing Scientific Illusions in Image Synthesis

arXiv: https://arxiv.org/abs/2504.13129 · HTML: https://mlsanity.com/paper/2504.13129/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 50 of its 83 references that are in the map.
- First posted on arXiv 17 Apr 2025.

## Builds on (most cited first, 30 of 50)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation](https://mlsanity.com/paper/2201.12086/) (2022)
- [Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution](https://mlsanity.com/paper/2409.12191/) (2024)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Sigmoid Loss for Language Image Pre-Training](https://mlsanity.com/paper/2303.15343/) (2023)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2304.05977/) (2023)
- [Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation](https://mlsanity.com/paper/2305.01569/) (2023)
- [Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis](https://mlsanity.com/paper/2306.09341/) (2023)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models](https://mlsanity.com/paper/2305.16381/) (2023)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model](https://mlsanity.com/paper/2311.13231/) (2023)

## Built on by (most cited first, 15 of 15)

- [PAI-Bench: A Comprehensive Benchmark For Physical AI](https://mlsanity.com/paper/2512.01989/) (2025)
- [RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark](https://mlsanity.com/paper/2509.24897/) (2025)
- [Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation](https://mlsanity.com/paper/2508.10858/) (2025)
- [MAC: A Live Benchmark for Multimodal Large Language Models in Scientific Understanding](https://mlsanity.com/paper/2508.15802/) (2025)
- [UEval: A Benchmark for Unified Multimodal Generation](https://mlsanity.com/paper/2601.22155/) (2026)
- [Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://mlsanity.com/paper/2512.09924/) (2025)
- [Unveiling Fine-Grained Visual Traces: Evaluating Multimodal Interleaved Reasoning Chains in Multimodal STEM Tasks](https://mlsanity.com/paper/2604.19697/) (2026)
- [Enhancing Spatial Understanding in Image Generation via Reward Modeling](https://mlsanity.com/paper/2602.24233/) (2026)
- [Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights](https://mlsanity.com/paper/2512.01816/) (2025)
- [Align Beyond Prompts: Evaluating World Knowledge Alignment in Text-to-Image Generation](https://mlsanity.com/paper/2505.18730/) (2025)
- [MIRO: MultI-Reward cOnditioned pretraining improves T2I quality and efficiency](https://mlsanity.com/paper/2510.25897/) (2025)
- [Can Unified Generation and Understanding Models Maintain Semantic Equivalence Across Different Output Modalities?](https://mlsanity.com/paper/2602.23711/) (2026)
- [EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis](https://mlsanity.com/paper/2603.20828/) (2026)
- [PortraitCraft: A Benchmark for Portrait Composition Understanding and Generation](https://mlsanity.com/paper/2604.03611/) (2026)
- [SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation](https://mlsanity.com/paper/2606.30124/) (2026)

## Abstract (arXiv)

Current image generation models produce visually compelling but scientifically implausible images, exposing a fundamental gap between visual fidelity and physical realism. In this work, we introduce ScienceT2I, an expert-annotated dataset comprising a training set of over 20k adversarial image pairs and 9k prompts across 16 scientific domains and an isolated test set of 454 challenging prompts. Using this benchmark, we evaluate 18 recent image generation models and find that none scores above 50 out of 100 under implicit scientific prompts, while explicit prompts that directly describe the intended outcome yield scores roughly 35 points higher, confirming that current models can render correct scenes when told what to depict but cannot reason from scientific cues to the correct visual outcome. To address this, we develop SciScore, a reward model fine-tuned from CLIP-H that captures fine-grained scientific phenomena without relying on language-guided inference, surpassing GPT-4o and experienced human evaluators by roughly 5 points. We further propose a two-stage alignment framework combining supervised fine-tuning with masked online fine-tuning to inject scientific knowledge into generative models. Applying this framework to FLUX.1[dev] yields a relative improvement exceeding 50% on SciScore, demonstrating that scientific reasoning in image generation can be substantially improved through targeted data and alignment.