Spectral Evolution Search: Efficient Inference-Time Scaling for Reward-Aligned Image Generation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ye, Jinyan, Duan, Zhongjie, Li, Zhiwen, Chen, Cen, Chen, Daoyuan, Li, Yaliang, Chen, Yingda
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

VIRAL: Visual In-Context Reasoning via Analogy in Diffusion Transformers
by: Li, Zhiwen, et al.
Published: (2026)

AutoLoRA: Automatic LoRA Retrieval and Fine-Grained Gated Fusion for Text-to-Image Generation
by: Li, Zhiwen, et al.
Published: (2025)

AttriCtrl: Fine-Grained Control of Aesthetic Attribute Intensity in Diffusion Models
by: Chen, Die, et al.
Published: (2025)

ArtAug: Enhancing Text-to-Image Generation through Synthesis-Understanding Interaction
by: Duan, Zhongjie, et al.
Published: (2024)

Comprehensive Evaluation and Analysis for NSFW Concept Erasure in Text-to-Image Diffusion Models
by: Chen, Die, et al.
Published: (2025)

ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning
by: Duan, Zhongjie, et al.
Published: (2024)

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion Models
by: Chen, Die, et al.
Published: (2025)

EliGen: Entity-Level Controlled Image Generation with Regional Attention
by: Zhang, Hong, et al.
Published: (2025)

Growth Inhibitors for Suppressing Inappropriate Image Concepts in Diffusion Models
by: Chen, Die, et al.
Published: (2024)

Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion
by: Duan, Zhongjie, et al.
Published: (2026)

VeriSciQA: An Auto-Verified Dataset for Scientific Visual Question Answering
by: Li, Yuyi, et al.
Published: (2025)

DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?
by: Jiao, Qirui, et al.
Published: (2025)

From Training-Free to Adaptive: Empirical Insights into MLLMs' Understanding of Detection Information
by: Jiao, Qirui, et al.
Published: (2024)

Diffutoon: High-Resolution Editable Toon Shading via Diffusion Models
by: Duan, Zhongjie, et al.
Published: (2024)

MindGYM: What Matters in Question Synthesis for Thinking-Centric Fine-Tuning?
by: Xu, Zhe, et al.
Published: (2025)

Nexus-Gen: Unified Image Understanding, Generation, and Editing via Prefilled Autoregression in Shared Embedding Space
by: Zhang, Hong, et al.
Published: (2025)

Img-Diff: Contrastive Data Synthesis for Multimodal Large Language Models
by: Jiao, Qirui, et al.
Published: (2024)

HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks
by: Zhou, Ting, et al.
Published: (2024)

LatSearch: Latent Reward-Guided Search for Faster Inference-Time Scaling in Video Diffusion
by: Zhao, Zengqun, et al.
Published: (2026)

Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
by: Fan, Mingyuan, et al.
Published: (2023)

A Dense Reward View on Aligning Text-to-Image Diffusion with Preference
by: Yang, Shentao, et al.
Published: (2024)

RewardDance: Reward Scaling in Visual Generation
by: Wu, Jie, et al.
Published: (2025)

The Image as Its Own Reward: Reinforcement Learning with Adversarial Reward for Image Generation
by: Mao, Weijia, et al.
Published: (2025)

SANA 1.5: Efficient Scaling of Training-Time and Inference-Time Compute in Linear Diffusion Transformer
by: Xie, Enze, et al.
Published: (2025)

Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL
by: Wu, Ruitao, et al.
Published: (2025)

Data-Juicer Sandbox: A Feedback-Driven Suite for Multimodal Data-Model Co-development
by: Chen, Daoyuan, et al.
Published: (2024)

Multi-dimensional Visual Prompt Enhanced Image Restoration via Mamba-Transformer Aggregation
by: Jiang, Aiwen, et al.
Published: (2024)

Bidirectional Prototype-Reward co-Evolution for Test-Time Adaptation of Vision-Language Models
by: Qiao, Xiaozhen, et al.
Published: (2025)

SVGThinker: Instruction-Aligned and Reasoning-Driven Text-to-SVG Generation
by: Chen, Hanqi, et al.
Published: (2025)

RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution
by: Song, Yushuai, et al.
Published: (2026)

RubricRL: Simple Generalizable Rewards for Text-to-Image Generation
by: Feng, Xuelu, et al.
Published: (2025)

Geo-Align: Video Generation Alignment via Metric Geometry Reward
by: Li, Zizun, et al.
Published: (2026)

Physics-Aligned Spectral Mamba: Decoupling Semantics and Dynamics for Few-Shot Hyperspectral Target Detection
by: Gong, Luqi, et al.
Published: (2026)

Hyperspectral Image Classification via Efficient Global Spectral Supertoken Clustering
by: Liu, Peifu, et al.
Published: (2026)

Enhancing Spatial Understanding in Image Generation via Reward Modeling
by: Tang, Zhenyu, et al.
Published: (2026)

PoreTrack3D: A Benchmark for Dynamic 3D Gaussian Splatting in Pore-Scale Facial Trajectory Tracking
by: Li, Dong, et al.
Published: (2025)

Security Tensors as a Cross-Modal Bridge: Extending Text-Aligned Safety to Vision in LVLM
by: Li, Shen, et al.
Published: (2025)

The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective
by: Qin, Zhen, et al.
Published: (2024)

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation
by: Fu, Minghao, et al.
Published: (2025)

AlignedGen: Aligning Style Across Generated Images
by: Zhang, Jiexuan, et al.
Published: (2025)