Episode
Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling
- Podcast
- Daily Paper Cast
- Published
- May 15, 2026
- Duration seconds
- 1418
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/46539574
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 30 | cs.CV Authors: Xuehai Bai, Yang Shi, Yi-Fan Zhang, Xuanyu Zhu, Yuran Wang, Yifan Dai, Xinyu Liu, Yiyan Ji, Xiaoling Gu, Yuanxing Zhang Title: Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling Arxiv: http://arxiv.org/abs/2605.13062v1 Abstract: Recent image editing models have achieved remarkable progress in instruction following, multimodal understanding, and complex visual editing. However, existing benchmarks often fail to faithfully reflect human judgment, especially for strong frontier models, due to limited task difficulty and coarse-grained evaluation protocols. In parallel, reward models have become increasingly important for RL-based image editing optimization, yet existing reward model benchmarks still rely on unrealistic evaluation settings that deviate from practical RL scenarios. These limitations hinder reliable assessment of both image editing models and reward models. To address these challenges, we introduce Edit-Compass and EditReward-Compass, a unified evaluation suite for image editing and reward modeling. Edit-Compass contains 2,388 carefully annotated instances spanning six progressively challenging task categories, covering capabilities such as world knowledge reasoning, visual reasoning, and multi-image editing. Beyond broad task coverage, Edit-Compass adopts a fine-grained multidimensional evaluation framework based on structured reasoning and carefully designed scoring rubrics. In parallel, EditReward-Compass contains 2,251 preference pairs that simulate realistic reward modeling scenarios during RL optimization.