Imagen de Portada

OmniAlpha: Aligning Transparency-Aware Generation via Multi-Task Unified Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Yu, Hao, Wang, Jinglin, Zhan, Jiabo, Chen, Rui, Wang, Zile, Zhang, Huaisong, Li, Hongyu, Chen, Xinrui, Wei, Yongxian, Yuan, Chun
Formato:	Preprint
Publicado:	2025
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

AlphaVAE: Unified End-to-End RGBA Image Reconstruction and Generation with Alpha-Aware Representation Learning
por: Wang, Zile, et al.
Publicado: (2025)

Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
por: Wei, Yongxian, et al.
Publicado: (2025)

Prune&Comp: Free Lunch for Layer-Pruned LLMs via Iterative Pruning with Magnitude Compensation
por: Chen, Xinrui, et al.
Publicado: (2025)

OmniGen: Unified Image Generation
por: Xiao, Shitao, et al.
Publicado: (2024)

AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
por: Zhang, Yi, et al.
Publicado: (2025)

Align the GAP: Prior-based Unified Multi-Task Remote Physiological Measurement Framework For Domain Generalization and Personalization
por: Wang, Jiyao, et al.
Publicado: (2025)

Task-Specific Zero-shot Quantization-Aware Training for Object Detection
por: Li, Changhao, et al.
Publicado: (2025)

OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
por: Yan, Qianqi, et al.
Publicado: (2026)

Whoever Started the Interference Should End It: Guiding Data-Free Model Merging via Task Vectors
por: Cheng, Runxi, et al.
Publicado: (2025)

Task-Distributionally Robust Data-Free Meta-Learning
por: Hu, Zixuan, et al.
Publicado: (2023)

DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning
por: Wei, Yujie, et al.
Publicado: (2026)

Why can a hydrophilic polyelectrolyte precipitate and redissolve below the critical micelle concentration of an oppositely-charged surfactant ?
por: Yong, Huaisong
Publicado: (2024)

Omni-Effects: Unified and Spatially-Controllable Visual Effects Generation
por: Mao, Fangyuan, et al.
Publicado: (2025)

OmniGen: Unified Multimodal Sensor Generation for Autonomous Driving
por: Tang, Tao, et al.
Publicado: (2025)

InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue
por: Tong, Wenwen, et al.
Publicado: (2025)

Task Groupings Regularization: Data-Free Meta-Learning with Heterogeneous Pre-trained Models
por: Wei, Yongxian, et al.
Publicado: (2024)

DreamOmni: Unified Image Generation and Editing
por: Xia, Bin, et al.
Publicado: (2024)

Omni-Video: Democratizing Unified Video Understanding and Generation
por: Tan, Zhiyu, et al.
Publicado: (2025)

OmniTracker: Unifying Object Tracking by Tracking-with-Detection
por: Wang, Junke, et al.
Publicado: (2023)

OmniGen2: Towards Instruction-Aligned Multimodal Generation
por: Wu, Chenyuan, et al.
Publicado: (2025)

PosterOmni: Generalized Artistic Poster Creation via Task Distillation and Unified Reward Feedback
por: Chen, Sixiang, et al.
Publicado: (2026)

Ming-Omni: A Unified Multimodal Model for Perception and Generation
por: AI, Inclusion, et al.
Publicado: (2025)

Learning to Pose Problems: Reasoning-Driven and Solver-Adaptive Data Synthesis
por: Wei, Yongxian, et al.
Publicado: (2025)

UmniBench: Unified Understand and Generation Model Oriented Omni-dimensional Benchmark
por: Liu, Kai, et al.
Publicado: (2025)

OmniCamera: A Unified Framework for Multi-task Video Generation with Arbitrary Camera Control
por: Wang, Yukun, et al.
Publicado: (2026)

UniCompress: Token Compression for Unified Vision-Language Understanding and Generation
por: Wang, Ziyao, et al.
Publicado: (2026)

Interference-Aware Multi-Task Unlearning
por: Huang, Ying-Hua, et al.
Publicado: (2026)

OmniCam: Unified Multimodal Video Generation via Camera Control
por: Yang, Xiaoda, et al.
Publicado: (2025)

Task Aware Dreamer for Task Generalization in Reinforcement Learning
por: Ying, Chengyang, et al.
Publicado: (2023)

Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement Learning
por: Chen, Jingxiang, et al.
Publicado: (2026)

ChronusOmni: Improving Time Awareness of Omni Large Language Models
por: Chen, Yijing, et al.
Publicado: (2025)

Robust and Highly Stretchable UV‐Curable Rubber/Polyurethane‐Based Resins Reinforced with Photocurable Cellulose Acetate
por: Bin Yang, et al.
Publicado: (2025)

AR-Omni: A Unified Autoregressive Model for Any-to-Any Generation
por: Cheng, Dongjie, et al.
Publicado: (2026)

Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete Diffusion
por: Lu, Yizhuo, et al.
Publicado: (2026)

OmniGenBench: A Benchmark for Omnipotent Multimodal Generation across 50+ Tasks
por: Wang, Jiayu, et al.
Publicado: (2025)

OmniVDiff: Omni Controllable Video Diffusion for Generation and Understanding
por: Xi, Dianbing, et al.
Publicado: (2025)

Modality Unified Attack for Omni-Modality Person Re-Identification
por: Bian, Yuan, et al.
Publicado: (2025)

Omni-Video 2: Scaling MLLM-Conditioned Diffusion for Unified Video Generation and Editing
por: Yang, Hao, et al.
Publicado: (2026)

OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
por: Zhu, Boyu, et al.
Publicado: (2025)

OmniSVG: A Unified Scalable Vector Graphics Generation Model
por: Yang, Yiying, et al.
Publicado: (2025)