# Cycle Consistency as Reward: Learning Image-Text Alignment without Human Preferences

arXiv: https://arxiv.org/abs/2506.02095 · HTML: https://mlsanity.com/paper/2506.02095/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation.
- Builds on 75 of its 107 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Placed in

- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 75)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Visual Instruction Tuning](https://mlsanity.com/paper/2304.08485/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Improved Baselines with Visual Instruction Tuning](https://mlsanity.com/paper/2310.03744/) (2023)
- [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)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning](https://mlsanity.com/paper/2305.06500/) (2023)
- [LLaVA-OneVision: Easy Visual Task Transfer](https://mlsanity.com/paper/2408.03326/) (2024)
- [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)
- [CIDEr: Consensus-based Image Description Evaluation](https://mlsanity.com/paper/1411.5726/) (2014)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [Evaluating Object Hallucination in Large Vision-Language Models](https://mlsanity.com/paper/2305.10355/) (2023)

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

- [Back into Plato's Cave: Examining Cross-modal Representational Convergence at Scale](https://mlsanity.com/paper/2604.18572/) (2026)
- [Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions](https://mlsanity.com/paper/2511.06876/) (2025)
- [SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models](https://mlsanity.com/paper/2602.18993/) (2026)
- [SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards](https://mlsanity.com/paper/2506.07963/) (2025)
- [RealDPO: Real or Not Real, that is the Preference](https://mlsanity.com/paper/2510.14955/) (2025)
- [HEDGE: Hallucination Estimation via Dense Geometric Entropy for VQA with Vision-Language Models](https://mlsanity.com/paper/2511.12693/) (2025)
- [The Telephone Game: Evaluating Semantic Drift in Unified Models](https://mlsanity.com/paper/2509.04438/) (2025)
- [VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation](https://mlsanity.com/paper/2604.02467/) (2026)
- [Building a Precise Video Language with Human-AI Oversight](https://mlsanity.com/paper/2604.21718/) (2026)
- [Bias at the End of the Score](https://mlsanity.com/paper/2604.13305/) (2026)
- [(1D) Ordered Tokens Enable Efficient Test-Time Search](https://mlsanity.com/paper/2604.15453/) (2026)
- [Calibrate What You SHIP: Post-Selection Risk Control for Verifier-Guided Text-to-Image Generation](https://mlsanity.com/paper/2608.21748/) (2026)
- [Graph Alignment via Dual-Pass Spectral Encoding and Latent Space Communication](https://mlsanity.com/paper/2509.09597/) (2025)
- [PreferThinker: Reasoning-based Personalized Image Preference Assessment](https://mlsanity.com/paper/2511.00609/) (2025)
- [Cross-modal Identity Mapping: Minimizing Information Loss in Modality Conversion via Reinforcement Learning](https://mlsanity.com/paper/2603.01696/) (2026)
- [CycleCap: Improving VLMs Captioning Performance via Self-Supervised Cycle Consistency Fine-Tuning](https://mlsanity.com/paper/2603.18282/) (2026)
- [ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models](https://mlsanity.com/paper/2603.19676/) (2026)
- [Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation](https://mlsanity.com/paper/2606.00232/) (2026)
- [BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers Inference](https://mlsanity.com/paper/2608.07572/) (2026)
- [EchoRec: Multi-Item Prediction-Empowered Generative Recommendation via Cycle-Consistent Preference Alignment](https://mlsanity.com/paper/2608.14011/) (2026)
- [Re3Cap: Retrieval-Guided Refinement for Image Captioning Enhancement via Reinforcement Learning](https://mlsanity.com/paper/2608.21305/) (2026)
- [Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint](https://mlsanity.com/paper/2609.19812/) (2026)

## Abstract (arXiv)

Measuring alignment between language and vision is a fundamental challenge, especially as multimodal data becomes increasingly detailed and complex. Existing methods often rely on collecting human or AI preferences, which can be costly and time-intensive. We propose an alternative approach that leverages cycle consistency as a supervisory signal. Given an image and generated text, we map the text back to image space using a text-to-image model and compute the similarity between the original image and its reconstruction. Analogously, for text-to-image generation, we measure the textual similarity between an input caption and its reconstruction through the cycle. We use the cycle consistency score to rank candidates and construct a preference dataset of 866K comparison pairs. The reward model trained on our dataset, CycleReward, outperforms state-of-the-art alignment metrics on detailed captioning, with superior inference-time scalability when used as a verifier for Best-of-N sampling, while maintaining speed and differentiability. Furthermore, performing DPO and Diffusion DPO using our dataset enhances performance across a wide range of vision-language tasks and text-to-image generation. Our dataset, model, and code are publicly released at https://cyclereward.github.io.