CV-Arena is a new 12K-pair benchmark for instruction-guided real-image editing with 16 task types, CogRetriever curation, and Active Elo mixed human-AI evaluation that finds gaps in 21 models and presents CV-Agent.
hub Baseline reference
Editreward: A human- aligned reward model for instruction-guided image editing
Baseline reference. 67% of citing Pith papers use this work as a benchmark or comparison.
14
Pith papers citing it
Baseline
67% of classified citations
hub tools
citation-role summary
baseline 3
background 2
dataset 1
citation-polarity summary
verdicts
UNVERDICTED 14representative citing papers
A planner-orchestrator system learns long-horizon image editing by maximizing outcome-based rewards from a vision-language judge and refining plans from successful trajectories.
Edit-Compass and EditReward-Compass are new unified benchmarks for fine-grained image editing evaluation and realistic reward modeling in reinforcement learning optimization.
RewardHarness self-evolves a tool-and-skill library from 100 preference examples to reach 47.4% accuracy on image-edit evaluation, beating GPT-5, and yields stronger RL-tuned models.
EditRefiner uses a perception-reasoning-action-evaluation agent loop and the EditFHF-15K human feedback dataset to refine text-guided image edits more accurately than prior methods.
Sparkle supplies a large-scale dataset and benchmark for instruction-driven video background replacement, enabling models that generate more natural and temporally consistent new scenes than earlier approaches.
SpatialFlow-GRPO adds region-level reward feedback and spatial alignment to Flow-GRPO-style RL for image editing, reporting gains on GEdit-Bench, ImgEdit-Bench, and a new MultiEditBench.
A multi-teacher distillation framework that packs 50 effect LoRAs and fast sampling into a single adapter while aiming to avoid concept interference.
Auto-Rubric as Reward externalizes VLM preferences into structured rubrics and applies Rubric Policy Optimization to create more reliable binary rewards for multimodal generation, outperforming pairwise models on text-to-image and editing benchmarks.
ReasonEdit uses a new CoT dataset and reinforcement learning to produce interpretable, human-aligned evaluations of text-guided image edits.
DDA-Thinker decouples planning from generation and applies dual-atomic RL with checklist-based rewards to boost reasoning in image editing, yielding competitive results on RISE-Bench and KRIS-Bench.
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.
ConsistencySolver enables high-quality low-step diffusion previews by adapting general linear multistep methods into a lightweight RL-optimized solver, matching multistep DPM-Solver FID with 47% fewer steps and cutting user interaction time by nearly 50%.
Edit-GRPO decouples editing and preservation objectives via region-specific signals in a policy optimization framework to improve locality in image editing tasks.
citing papers explorer
-
DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing
DDA-Thinker decouples planning from generation and applies dual-atomic RL with checklist-based rewards to boost reasoning in image editing, yielding competitive results on RISE-Bench and KRIS-Bench.
-
VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects
VEFX-Bench releases a large human-labeled video editing dataset, a multi-dimensional reward model, and a standardized benchmark that better matches human judgments than generic evaluators.