# Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling

Page: https://stenobird.com/podcast/daily-paper-cast-7079649/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling
Text version: https://stenobird.com/podcast/daily-paper-cast-7079649/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling.md
Podcast: [Daily Paper Cast](https://stenobird.com/podcast/daily-paper-cast-7079649)
Published: 2026-05-15T04:59:29+00:00
Episode link: https://share.transistor.fm/s/46539574
Audio file: https://media.transistor.fm/46539574/aaa65c3b.mp3
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/edit-compass-editreward-compass-a-unified-benchmark-for-image-editing-and-reward-modeling
Duration seconds: 1418

## Resource

🤗 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.

## Actions

- request_transcript: `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.
- read_markdown: `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.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.