Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image Generation
cs.CV, cs.AI, cs.LG
Submitted: 2026-10-07
Updated: 2026-10-07
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Leveraging Verifier-Based Reinforcement Learning in Image Editing
- AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
- Flow-GRPO: Training Flow Matching Models via Online RL
- Evaluation-Verification Reward for Consistent Multi-Reference Image Editing
- PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
- MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
- Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
- Visual Jev: Accurate and Efficient Decisions from Shared Visual Context
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models