SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
Tim Brooks, Aleksander Holynski, and Alexei A Efros
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
representative citing papers
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
Introduces TRACE-Edit dataset and evaluation protocol demonstrating semantic degradation of structural variables during VLM-to-DiT alignment in flow-matching video editors.
An MLLM agent that profiles, routes, and reformulates image-editing queries into better-conditioned multi-step operations consistently improves existing editors on hard cases.
DS-IEQA jointly learns evaluation criteria via feedback-driven prompt optimization and continuous score modeling via token-decoupled distance regression, ranking 4th in the 2026 NTIRE X-AIGC Quality Assessment Track 2 without extra training data.
VDE Bench is a new bilingual (Chinese-English) dense-document image editing benchmark with 674 samples and an OCR-based evaluation framework showing automated metrics correlate with human judgment.
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
PaintBench provides a scalable deterministic benchmark for precise visual editing operations, revealing that even the best of 11 models achieves only 17.1% mIoU and that scores correlate strongly with applied data visualization editing performance.
citing papers explorer
-
SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing
SpeechEditBench provides seven atomic editing tasks, compositional multi-operation instructions, and an anchor-based protocol yielding target success, preservation success, and joint success metrics; evaluations show no model excels across dimensions and compositional editing is especially difficult
-
UniEditBench: A Unified and Cost-Effective Benchmark for Image and Video Editing via Distilled MLLMs
UniEditBench unifies image and video editing evaluation with a nine-plus-eight operation taxonomy and cost-effective 4B/8B distilled MLLM evaluators that align with human judgments.
-
What Semantics Survive the Connector? Diagnosing VLM-to-DiT Alignment in Video Editing
Introduces TRACE-Edit dataset and evaluation protocol demonstrating semantic degradation of structural variables during VLM-to-DiT alignment in flow-matching video editors.
-
Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions
An MLLM agent that profiles, routes, and reformulates image-editing queries into better-conditioned multi-step operations consistently improves existing editors on hard cases.
-
Redefining Quality Criteria and Distance-Aware Score Modeling for Image Editing Assessment
DS-IEQA jointly learns evaluation criteria via feedback-driven prompt optimization and continuous score modeling via token-decoupled distance regression, ranking 4th in the 2026 NTIRE X-AIGC Quality Assessment Track 2 without extra training data.
-
VDE Bench: Evaluating The Capability of Image Editing Models to Modify Visual Documents
VDE Bench is a new bilingual (Chinese-English) dense-document image editing benchmark with 674 samples and an OCR-based evaluation framework showing automated metrics correlate with human judgment.
-
ImgEdit: A Unified Image Editing Dataset and Benchmark
ImgEdit supplies 1.2 million curated edit pairs and a three-part benchmark that let a VLM-based model outperform prior open-source editors on adherence, quality, and detail preservation.
-
PaintBench: Deterministic Evaluation of Precise Visual Editing
PaintBench provides a scalable deterministic benchmark for precise visual editing operations, revealing that even the best of 11 models achieves only 17.1% mIoU and that scores correlate strongly with applied data visualization editing performance.