# CARINOX: Inference-time Scaling with Category-Aware Reward-based Initial Noise Optimization and Exploration

arXiv: https://arxiv.org/abs/2509.17458 · HTML: https://mlsanity.com/paper/2509.17458/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion reasoning and test-time scaling, one of 17 directions in LLM reasoning.
- Builds on 24 of its 82 references that are in the map.
- First posted on arXiv 22 Sep 2025.

## Placed in

- LLM reasoning / [Diffusion reasoning and test-time scaling](https://mlsanity.com/lr/diffusion-reasoning-and-test-time-scaling/)
- Diffusion models / [Image generation, text-to-image and editing](https://mlsanity.com/diffusion/image-generation-text-to-image-and-editing/)

## Builds on (most cited first, 24 of 24)

- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Adding Conditional Control to Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.05543/) (2023)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models](https://mlsanity.com/paper/2112.10741/) (2021)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2302.08453/) (2023)
- [Diffusion Model-Based Image Editing: A Survey](https://mlsanity.com/paper/2402.17525/) (2024)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [D-Flow: Differentiating through Flows for Controlled Generation](https://mlsanity.com/paper/2402.14017/) (2024)
- [Benchmarking Spatial Relationships in Text-to-Image Generation](https://mlsanity.com/paper/2212.10015/) (2022)
- [Test-time Alignment of Diffusion Models without Reward Over-optimization](https://mlsanity.com/paper/2501.05803/) (2025)
- [Divide & Bind Your Attention for Improved Generative Semantic Nursing](https://mlsanity.com/paper/2307.10864/) (2023)
- [CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching](https://mlsanity.com/paper/2404.03653/) (2024)
- [Make It Count: Text-to-Image Generation with an Accurate Number of Objects](https://mlsanity.com/paper/2406.10210/) (2024)
- [If at First You Don't Succeed, Try, Try Again: Faithful Diffusion-based Text-to-Image Generation by Selection](https://mlsanity.com/paper/2305.13308/) (2023)
- [Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing](https://mlsanity.com/paper/2503.19385/) (2025)
- [All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds](https://mlsanity.com/paper/2411.18810/) (2024)
- [Counting Guidance for High Fidelity Text-to-Image Synthesis](https://mlsanity.com/paper/2306.17567/) (2023)
- [VersaT2I: Improving Text-to-Image Models with Versatile Reward](https://mlsanity.com/paper/2403.18493/) (2024)
- [Psi-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models](https://mlsanity.com/paper/2506.01320/) (2025)
- [ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation](https://mlsanity.com/paper/2503.22194/) (2025)
- [Seek for Incantations: Towards Accurate Text-to-Image Diffusion Synthesis through Prompt Engineering](https://mlsanity.com/paper/2401.06345/) (2024)
- [Detection-Driven Object Count Optimization for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2408.11721/) (2024)
- [OIL-AD: An Anomaly Detection Framework for Sequential Decision Sequences](https://mlsanity.com/paper/2402.04567/) (2024)

## Built on by (most cited first, 2 of 2)

- [Erasure or Erosion? Evaluating Compositional Degradation in Unlearned Text-To-Image Diffusion Models](https://mlsanity.com/paper/2604.04575/) (2026)
- [Weeding Out Bad Seeds: Initial-Noise-Robust Unlearning for Text-to-Image Diffusion Models](https://mlsanity.com/paper/2609.37537/) (2026)

## Abstract (arXiv)

Text-to-image diffusion models, such as Stable Diffusion, can produce high-quality and diverse images but often fail to achieve compositional alignment, particularly when prompts describe complex object relationships, attributes, or spatial arrangements. Recent inference-time approaches address this by optimizing or exploring the initial noise under the guidance of reward functions that score text-image alignment without requiring model fine-tuning. While promising, each strategy has intrinsic limitations when used alone: optimization can stall due to poor initialization or unfavorable search trajectories, whereas exploration may require a prohibitively large number of samples to locate a satisfactory output. Our analysis further shows that neither single reward metrics nor ad-hoc combinations reliably capture all aspects of compositionality, leading to weak or inconsistent guidance. To overcome these challenges, we present Category-Aware Reward-based Initial Noise Optimization and EXploration (CARINOX), a unified framework that combines noise optimization and exploration with a principled reward selection procedure grounded in correlation with human judgments. Evaluations on two complementary benchmarks covering diverse compositional challenges show that CARINOX raises average alignment scores by approximately 19% on both T2I-CompBench++ and HRS, consistently outperforming state-of-the-art optimization and exploration-based methods across all major categories, while preserving image quality and diversity. The project page is available at https://amirkasaei.com/carinox/.