Copertina

Conflict-Aware Additive Guidance for Flow Models under Compositional Rewards

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Yu, Xuehui, Cai, Fucheng, Wang, Meiyi, Fan, Xiaopeng, Soh, Harold
Natura:	Preprint
Pubblicazione:	2026
Soggetti:	Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Robotics
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Subtask-Aware Visual Reward Learning from Segmented Demonstrations
di: Kim, Changyeon, et al.
Pubblicazione: (2025)

Aligning Text-to-Image Diffusion Models with Reward Backpropagation
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2023)

GrndCtrl: Grounding World Models via Self-Supervised Reward Alignment
di: He, Haoyang, et al.
Pubblicazione: (2025)

Video Diffusion Alignment via Reward Gradients
di: Prabhudesai, Mihir, et al.
Pubblicazione: (2024)

FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
di: Zhang, Zihui, et al.
Pubblicazione: (2026)

Virtual Guidance as a Mid-level Representation for Navigation with Augmented Reality
di: Yang, Hsuan-Kung, et al.
Pubblicazione: (2023)

ARM: Advantage Reward Modeling for Long-Horizon Manipulation
di: Mao, Yiming, et al.
Pubblicazione: (2026)

Compositional Generative Modeling: A Single Model is Not All You Need
di: Du, Yilun, et al.
Pubblicazione: (2024)

Aether: Geometric-Aware Unified World Modeling
di: Aether Team, et al.
Pubblicazione: (2025)

A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving
di: Long, Keke, et al.
Pubblicazione: (2025)

Maximizing Alignment with Minimal Feedback: Efficiently Learning Rewards for Visuomotor Robot Policy Alignment
di: Tian, Ran, et al.
Pubblicazione: (2024)

EfficientFlow: Efficient Equivariant Flow Policy Learning for Embodied AI
di: Chang, Jianlei, et al.
Pubblicazione: (2025)

IFG: Internet-Scale Guidance for Functional Grasping Generation
di: Liu, Ray Muxin, et al.
Pubblicazione: (2025)

PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
di: Zhang, Kaidong, et al.
Pubblicazione: (2024)

Flame3D: Zero-shot Compositional Reasoning of 3D Scenes with Agentic Language Models
di: Bharadwaj, Sagar, et al.
Pubblicazione: (2026)

DiMSam: Diffusion Models as Samplers for Task and Motion Planning under Partial Observability
di: Fang, Xiaolin, et al.
Pubblicazione: (2023)

IRL-VLA: Training an Vision-Language-Action Policy via Reward World Model
di: Jiang, Anqing, et al.
Pubblicazione: (2025)

Iterative Refinement Improves Compositional Image Generation
di: Jaiswal, Shantanu, et al.
Pubblicazione: (2026)

WAM-Flow: Parallel Coarse-to-Fine Motion Planning via Discrete Flow Matching for Autonomous Driving
di: Xu, Yifang, et al.
Pubblicazione: (2025)

RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
di: Qin, Yiran, et al.
Pubblicazione: (2025)

ChainFlow-VLA: Causal Flow Planning with Vision-Language Models
di: Wang, Xiyang, et al.
Pubblicazione: (2026)

FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation
di: Zeng, Huajian, et al.
Pubblicazione: (2026)

Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation
di: Ma, Xiao, et al.
Pubblicazione: (2024)

SPA: 3D Spatial-Awareness Enables Effective Embodied Representation
di: Zhu, Haoyi, et al.
Pubblicazione: (2024)

Pixel-level Scene Understanding in One Token: Visual States Need What-is-Where Composition
di: Lee, Seokmin, et al.
Pubblicazione: (2026)

C-SWAP: Explainability-Aware Structured Pruning for Efficient Neural Networks Compression
di: Bauvin, Baptiste, et al.
Pubblicazione: (2025)

Open-Set LiDAR Panoptic Segmentation Guided by Uncertainty-Aware Learning
di: Mohan, Rohit, et al.
Pubblicazione: (2025)

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions
di: Wu, Ruihai, et al.
Pubblicazione: (2023)

FALCON: Future-Aware Learning with Contextual Object-Centric Pretraining for UAV Action Recognition
di: Xian, Ruiqi, et al.
Pubblicazione: (2024)

Single-Frame Point-Pixel Registration via Supervised Cross-Modal Feature Matching
di: Han, Yu, et al.
Pubblicazione: (2025)

Application of Vision-Language Model to Pedestrians Behavior and Scene Understanding in Autonomous Driving
di: Gao, Haoxiang, et al.
Pubblicazione: (2025)

ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
di: Cai, Shaofei, et al.
Pubblicazione: (2025)

Non-rigid Relative Placement through 3D Dense Diffusion
di: Cai, Eric, et al.
Pubblicazione: (2024)

World Simulation with Video Foundation Models for Physical AI
di: NVIDIA, et al.
Pubblicazione: (2025)

Learning Visual Feature-Based World Models via Residual Latent Action
di: Zhang, Xinyu, et al.
Pubblicazione: (2026)

PRIX: Learning to Plan from Raw Pixels for End-to-End Autonomous Driving
di: Wozniak, Maciej K., et al.
Pubblicazione: (2025)

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
di: Gao, Shenyuan, et al.
Pubblicazione: (2026)

CREStE: Scalable Mapless Navigation with Internet Scale Priors and Counterfactual Guidance
di: Zhang, Arthur, et al.
Pubblicazione: (2025)

Image-Goal Navigation Using Refined Feature Guidance and Scene Graph Enhancement
di: Feng, Zhicheng, et al.
Pubblicazione: (2025)

Cosmos World Foundation Model Platform for Physical AI
di: NVIDIA, et al.
Pubblicazione: (2025)