MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
Delving into rl for image generation with cot: A study on dpo vs
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
MixGRPO speeds up GRPO for flow-based image generators by restricting SDE sampling and optimization to a sliding window while using ODE elsewhere, cutting training time by up to 71% with better alignment performance.
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
Persona-based Mixture-of-Thought data curation lets a 7B student outperform larger models on humor generation, while DPO and O-GRPO add no gain over SFT.
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathematical reasoning.
Pref-GRPO stabilizes T2I RL training by using pairwise win rates from preference models as rewards instead of normalized pointwise scores, while UniGenBench enables finer-grained model evaluation across themes and criteria.
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consistency among open-source models on the new OmniContext benchmark.
citing papers explorer
-
MICo-150K: A Comprehensive Dataset Advancing Multi-Image Composition
MICo-150K is a new 150K-image dataset with 7 tasks, a De&Re real-image subset, MICo-Bench, and Weighted-Ref-VIEScore metric that improves AI models for generating consistent composites from arbitrary numbers of reference images.
-
MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
MixGRPO speeds up GRPO for flow-based image generators by restricting SDE sampling and optimization to a sliding window while using ODE elsewhere, cutting training time by up to 71% with better alignment performance.
-
Optimizing Visual Generative Models via Distribution-wise Rewards
Distribution-wise rewards with subset-replace strategy and post-hoc merging improve FID-50K on SiT (8.30 to 5.77) and EDM2 (3.74 to 3.52) while preserving diversity.
-
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
VERTIGO post-trains camera trajectory generators with visual preference signals from Unity-rendered previews scored by a cinematically fine-tuned VLM, cutting character off-screen rates from 38% to near zero while improving framing and prompt adherence.
-
HumorGen: Cognitive Synergy for Humor Generation in Large Language Models via Persona-Based Distillation
Persona-based Mixture-of-Thought data curation lets a 7B student outperform larger models on humor generation, while DPO and O-GRPO add no gain over SFT.
-
From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
EG-GRPO improves autoregressive text-to-image models by reallocating RL updates according to token entropy, excluding low-entropy tokens from reward signals while adding entropy bonuses to high-entropy ones, yielding state-of-the-art results on standard benchmarks.
-
MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning
MathVis-Fine proposes a dataset with fine-grained visual annotations and dependency ratings plus a progressive two-stage training paradigm to align visual supervision with sample-specific necessity in multimodal mathematical reasoning.
-
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning
Pref-GRPO stabilizes T2I RL training by using pairwise win rates from preference models as rewards instead of normalized pointwise scores, while UniGenBench enables finer-grained model evaluation across themes and criteria.
-
OmniGen2: Towards Instruction-Aligned Multimodal Generation
OmniGen2 introduces a unified generative model with two distinct decoding pathways and a decoupled image tokenizer that achieves competitive results on text-to-image and editing benchmarks plus state-of-the-art consistency among open-source models on the new OmniContext benchmark.