Edit-Compass and EditReward-Compass are new unified benchmarks for fine-grained image editing evaluation and realistic reward modeling in reinforcement learning optimization.
Magicbrush: A manually annotated dataset for instruction-guided image editing.Advances in Neural Information Processing Systems, 36:31428–31449
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
baseline 2
background 1
other 1
citation-polarity summary
representative citing papers
Controlla learns identity and attribute factors from multimodal inputs and aligns them with graph priors using graph-constrained optimal transport to enforce consistent attribute trajectories while preserving reference identity.
Pretrained instruction-based image editing models exhibit early foreground-background separability that enables a training-free framework for zero-shot referring image segmentation using a single denoising step.
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.
Emu3.5 is a native multimodal world model pre-trained on over 10 trillion vision-language tokens with next-token prediction, post-trained via reinforcement learning, and accelerated by Discrete Diffusion Adaptation for efficient interleaved generation and world exploration.
Slot-MLLM introduces a slot-attention-based object-centric visual tokenizer with Q-Former encoder, diffusion decoder, and residual vector quantization for improved local visual comprehension and generation in multimodal LLMs.
Using understanding tasks as direct supervision during post-training improves image generation and editing in unified multimodal models.
VAE-LFA suppresses semantic drift in multi-turn DiT image editing by low-pass filtering latent discrepancies and aligning low-frequency components to an EMA of previous rounds in VAE space.
citing papers explorer
-
Auto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria
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.