RSIgen: Reciprocal Self-Improvement for Agentic Visual Generation
cs.CV
Submitted: 2026-10-13
Updated: 2026-10-15
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Unify-Agent: A Unified Multimodal Agent for World-Grounded Image Synthesis
- GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation
- Re-Imagen: Retrieval-Augmented Text-to-Image Generator
- Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
- Gen-Searcher: Reinforcing Agentic Search for Image Generation
- UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision
- Turning Internal Gap into Self-Improvement: Promoting the Generation-Understanding Unification in MLLMs
- Mind-Brush: Integrating Agentic Cognitive Search and Reasoning into Image Generation
- GEMS: Agent-Native Multimodal Generation with Memory and Skills
- SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
- T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
- SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models
- Flow Matching for Generative Modeling
- Flow-GRPO: Training Flow Matching Models via Online RL
- UniGRPO: Unified Policy Optimization for Reasoning-Driven Visual Generation
- UniRL: Self-Improving Unified Multimodal Models via Supervised and Reinforcement Learning
- Learning to Generate via Understanding: Understanding-Driven Intrinsic Rewarding for Unified Multimodal Models
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models
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