Problem
Research questions and friction points this paper is trying to address.
Instruction-based image editing
planner-renderer pipeline
final-image rewards
credit assignment
DARS: Dual-Level Credit Assignment RL with Structured Reasoning for Instruction-Based Image Editing
๐ค AI Summary
่ฎบๆๆๅบDARSๆกๆถ๏ผ้่ฟๅๅฑไฟก็จๅ้
ๅ็ปๆๅๆจ็่งฃๅณๅบไบๆไปค็ๅพๅ็ผ่พไธญ่งๅๅจไธๆธฒๆๅจไผๅๆ็ไฝ็้ฎ้ขใ
๐ Abstract
Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan. Training such systems with only final-image rewards is inefficient because a poor edit does not reveal whether additional optimization should place more emphasis on the planner or the renderer, and even planner-dominant cases remain difficult to localize within a free-form reasoning trace. We present DARS, a reinforcement learning framework for dual-level credit assignment in this two-stage setting. Across modules, multi-plan multi-render rollouts estimate between-plan and within-plan reward variability for soft module routing, while rollout mean rewards provide hardness estimates for an adaptive curriculum. Within the planner, a four-field structured reasoning output enables a prefix-gated reward and token-level advantage reweighting, turning outcome-level feedback into localized supervision. Experiments on five benchmarks show that DARS outperforms a Joint~RL baseline with the same backbone, data, reward model, and rollout budget, with the largest gains on reasoning-intensive edits.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Dual-Level Credit Assignment
Structured Reasoning
Multi-Plan Multi-Render Rollouts
Adaptive Curriculum
Prefix-Gated Reward
๐ Similar Papers
No similar papers found.
