Imagen de Portada

UniGen-1.5: Enhancing Image Generation and Editing through Reward Unification in Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tian, Rui, Gao, Mingfei, Gang, Haiming, Lu, Jiasen, Gan, Zhe, Yang, Yinfei, Wu, Zuxuan, Dehghan, Afshin
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation
por: Tian, Rui, et al.
Publicado: (2025)

SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding
por: Xu, Mingze, et al.
Publicado: (2025)

SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models
por: Xu, Mingze, et al.
Publicado: (2024)

UniVG: A Generalist Diffusion Model for Unified Image Generation and Editing
por: Fu, Tsu-Jui, et al.
Publicado: (2025)

GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing
por: Qian, Yusu, et al.
Publicado: (2025)

Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing
por: Qian, Yusu, et al.
Publicado: (2025)

UniGen: Universal Domain Generalization for Sentiment Classification via Zero-shot Dataset Generation
por: Choi, Juhwan, et al.
Publicado: (2024)

UniGen: Unified Modeling of Initial Agent States and Trajectories for Generating Autonomous Driving Scenarios
por: Mahjourian, Reza, et al.
Publicado: (2024)

AToken: A Unified Tokenizer for Vision
por: Lu, Jiasen, et al.
Publicado: (2025)

SO-Bench: A Structural Output Evaluation of Multimodal LLMs
por: Feng, Di, et al.
Publicado: (2025)

MM-Spatial: Exploring 3D Spatial Understanding in Multimodal LLMs
por: Daxberger, Erik, et al.
Publicado: (2025)

Guiding Instruction-based Image Editing via Multimodal Large Language Models
por: Fu, Tsu-Jui, et al.
Publicado: (2023)

Understanding Alignment in Multimodal LLMs: A Comprehensive Study
por: Amirloo, Elmira, et al.
Publicado: (2024)

Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping
por: Lazarow, Justin, et al.
Publicado: (2025)

How Easy is It to Fool Your Multimodal LLMs? An Empirical Analysis on Deceptive Prompts
por: Qian, Yusu, et al.
Publicado: (2024)

UniHuman: A Unified Model for Editing Human Images in the Wild
por: Li, Nannan, et al.
Publicado: (2023)

MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning
por: Zhang, Haotian, et al.
Publicado: (2024)

GenRec: Unifying Video Generation and Recognition with Diffusion Models
por: Weng, Zejia, et al.
Publicado: (2024)

4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities
por: Bachmann, Roman, et al.
Publicado: (2024)

Trust Your Critic: Robust Reward Modeling and Reinforcement Learning for Faithful Image Editing and Generation
por: Zhao, Xiangyu, et al.
Publicado: (2026)

Reward Models in Deep Reinforcement Learning: A Survey
por: Yu, Rui, et al.
Publicado: (2025)

WeEdit: A Dataset, Benchmark and Glyph-Guided Framework for Text-centric Image Editing
por: Zhang, Hui, et al.
Publicado: (2026)

Thinking with Deltas: Incentivizing Reinforcement Learning via Differential Visual Reasoning Policy
por: Gao, Shujian, et al.
Publicado: (2026)

MM-Ego: Towards Building Egocentric Multimodal LLMs for Video QA
por: Ye, Hanrong, et al.
Publicado: (2024)

UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
por: Bai, Chengyu, et al.
Publicado: (2025)

UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics
por: Chen, Xi, et al.
Publicado: (2024)

UniGenBench++: A Unified Semantic Evaluation Benchmark for Text-to-Image Generation
por: Wang, Yibin, et al.
Publicado: (2025)

DrugGen: Advancing Drug Discovery with Large Language Models and Reinforcement Learning Feedback
por: Sheikholeslami, Mahsa, et al.
Publicado: (2024)

UniRef-Image-Edit: Towards Scalable and Consistent Multi-Reference Image Editing
por: Wei, Hongyang, et al.
Publicado: (2026)

MagDiff: Multi-Alignment Diffusion for High-Fidelity Video Generation and Editing
por: Zhao, Haoyu, et al.
Publicado: (2023)

DeepStack: Deeply Stacking Visual Tokens is Surprisingly Simple and Effective for LMMs
por: Meng, Lingchen, et al.
Publicado: (2024)

Gen-Drive: Enhancing Diffusion Generative Driving Policies with Reward Modeling and Reinforcement Learning Fine-tuning
por: Huang, Zhiyu, et al.
Publicado: (2024)

PRISM-Bench: A Benchmark of Puzzle-Based Visual Tasks with CoT Error Detection
por: Qian, Yusu, et al.
Publicado: (2025)

Compressing LLMs: The Truth is Rarely Pure and Never Simple
por: Jaiswal, Ajay, et al.
Publicado: (2023)

GenFlowRL: Shaping Rewards with Generative Object-Centric Flow in Visual Reinforcement Learning
por: Yu, Kelin, et al.
Publicado: (2025)

Seg-R1: Segmentation Can Be Surprisingly Simple with Reinforcement Learning
por: You, Zuyao, et al.
Publicado: (2025)

UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
por: Zhang, Yanran, et al.
Publicado: (2026)

Cubify Anything: Scaling Indoor 3D Object Detection
por: Lazarow, Justin, et al.
Publicado: (2024)

Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities
por: Zhou, Ziwei, et al.
Publicado: (2025)

Autoregressive Video Generation beyond Next Frames Prediction
por: Ren, Sucheng, et al.
Publicado: (2025)