Agentic Planning with Reasoning for Image Styling via Offline RL
cs.LG
Submitted: 2026-03-07
Updated: 2026-11-09
Terminology
Sources
- STaR-GATE: Teaching Language Models to Ask Clarifying Questions
- Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond
- Qwen2.5-VL Technical Report
- Point and Instruct: Enabling Precise Image Editing by Unifying Direct Manipulation and Text Instructions
- Diffusion-SDPO: Safeguarded Direct Preference Optimization for Diffusion Models
- StyleShot: A Snapshot on Any Style
- Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
- DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation
- Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems
- Advantage-Weighted Regression: Simple and Scalable Off-Policy Reinforcement Learning
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- High-Dimensional Continuous Control Using Generalized Advantage Estimation
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Agentic Retoucher for Text-To-Image Generation
- Qwen3 Technical Report
- Diffusion Model Alignment Using Direct Preference Optimization
- Finetuned Language Models Are Zero-Shot Learners
- Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis