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.
hub Mixed citations
VisionReward: Fine-Grained Multi-Dimensional Human Preference Learning for Image and Video Generation
Mixed citation behavior. Most common role is background (45%).
25
Pith papers citing it
Background
45% of classified citations
abstract
Visual generative models have achieved remarkable progress in synthesizing photorealistic images and videos, yet aligning their outputs with human preferences across critical dimensions remains a persistent challenge. Though reinforcement learning from human feedback offers promise for preference alignment, existing reward models for visual generation face limitations, including black-box scoring without interpretability and potentially resultant unexpected biases. We present VisionReward, a general framework for learning human visual preferences in both image and video generation. Specifically, we employ a hierarchical visual assessment framework to capture fine-grained human preferences, and leverages linear weighting to enable interpretable preference learning. Furthermore, we propose a multi-dimensional consistent strategy when using VisionReward as a reward model during preference optimization for visual generation. Experiments show that VisionReward can significantly outperform existing image and video reward models on both machine metrics and human evaluation. Notably, VisionReward surpasses VideoScore by 17.2% in preference prediction accuracy, and text-to-video models with VisionReward achieve a 31.6% higher pairwise win rate compared to the same models using VideoScore. All code and datasets are provided at https://github.com/THUDM/VisionReward.
hub tools
citation-role summary
background 5
baseline 3
method 2
dataset 1
citation-polarity summary
representative citing papers
OTCA improves GRPO training for visual generation by estimating step importance in trajectories and adaptively weighting multiple reward objectives.
A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
DSH-Bench is a benchmark for subject-driven T2I generation that uses hierarchical taxonomy sampling, difficulty/scenario classification, and a new SICS metric showing 9.4% higher human correlation than prior measures.
LocalDPO aligns text-to-video diffusion models with human preferences at the spatio-temporal region level by automatically generating localized preference pairs from corrupted real videos and applying a region-aware DPO loss.
UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.
Skill-aligned annotation improves inter-annotator agreement and evaluation stability in text-to-image generation compared to uniform annotation baselines.
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
DreamShot uses video diffusion priors and a role-attention consistency loss to produce coherent, personalized storyboards with better character and scene continuity than text-to-image methods.
Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.
UniWorld-V2 applies policy optimization via DiffusionNFT and MLLM logit feedback with group filtering to reach state-of-the-art scores of 4.49 on ImgEdit and 7.83 on GEdit-Bench while remaining model-agnostic.
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training.
citing papers explorer
-
RewardHarness: Self-Evolving Agentic Post-Training
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.
-
Learning to Credit the Right Steps: Objective-aware Process Optimization for Visual Generation
OTCA improves GRPO training for visual generation by estimating step importance in trajectories and adaptively weighting multiple reward objectives.
-
Speculative Decoding for Autoregressive Video Generation
A training-free speculative decoding method for block-based autoregressive video diffusion uses a quality router on worst-frame ImageReward scores to accept drafter proposals, achieving up to 2.09x speedup at 95.7% quality retention.
-
DSH-Bench: A Difficulty- and Scenario-Aware Benchmark with Hierarchical Subject Taxonomy for Subject-Driven Text-to-Image Generation
DSH-Bench is a benchmark for subject-driven T2I generation that uses hierarchical taxonomy sampling, difficulty/scenario classification, and a new SICS metric showing 9.4% higher human correlation than prior measures.
-
Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion Models
LocalDPO aligns text-to-video diffusion models with human preferences at the spatio-temporal region level by automatically generating localized preference pairs from corrupted real videos and applying a region-aware DPO loss.
-
Unified Reward Model for Multimodal Understanding and Generation
UnifiedReward is the first unified reward model that jointly assesses multimodal understanding and generation to provide better preference signals for aligning vision models via DPO.
-
PhyMotion: Structured 3D Motion Reward for Physics-Grounded Human Video Generation
PhyMotion scores generated human videos by grounding recovered 3D poses in a physics simulator across kinematic, contact, and dynamic axes, yielding stronger human correlation and larger RL post-training gains than prior 2D rewards.
-
Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation
Skill-aligned annotation improves inter-annotator agreement and evaluation stability in text-to-image generation compared to uniform annotation baselines.
-
How Far Are Video Models from True Multimodal Reasoning?
Current video models succeed on basic understanding but achieve under 25% success on logically grounded generation and near 0% on interactive generation, exposing gaps in multimodal reasoning.
-
DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior
DreamShot uses video diffusion priors and a role-attention consistency loss to produce coherent, personalized storyboards with better character and scene continuity than text-to-image methods.
-
Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation
Causal Forcing uses an autoregressive teacher for ODE initialization in diffusion distillation to close the causal attention gap and deliver better real-time video generation than Self Forcing.
-
Reward Forcing: Efficient Streaming Video Generation with Rewarded Distribution Matching Distillation
Reward Forcing combines EMA-Sink tokens and Rewarded Distribution Matching Distillation to deliver state-of-the-art streaming video generation at 23.1 FPS without copying initial frames.
-
Seeing What Matters: Visual Preference Policy Optimization for Visual Generation
ViPO enhances GRPO for visual generation by creating spatially and temporally aware advantage maps from pretrained vision models to focus optimization on perceptually important regions.
-
Uniworld-V2: Reinforce Image Editing with Diffusion Negative-aware Finetuning and MLLM Implicit Feedback
UniWorld-V2 applies policy optimization via DiffusionNFT and MLLM logit feedback with group filtering to reach state-of-the-art scores of 4.49 on ImgEdit and 7.83 on GEdit-Bench while remaining model-agnostic.
-
Self-Forcing++: Towards Minute-Scale High-Quality Video Generation
Self-Forcing++ scales autoregressive video diffusion to over 4 minutes by using self-generated segments for guidance, reducing error accumulation and outperforming baselines in fidelity and consistency.
-
Listener-Rewarded Thinking in VLMs for Image Preferences
Listener-augmented GRPO uses an independent frozen VLM to provide dense confidence scores on reasoning traces, yielding 67.4% accuracy on ImageReward, up to +6% OOD gains on 1.2M-vote human data, and fewer reasoning contradictions.
-
DanceGRPO: Unleashing GRPO on Visual Generation
DanceGRPO applies GRPO to visual generation tasks to achieve stable policy optimization across diffusion models, rectified flows, multiple tasks, and diverse reward models, outperforming prior RL methods.
-
Improving Video Generation with Human Feedback
A human preference dataset and VideoReward model enable Flow-DPO and Flow-NRG to produce smoother, better-aligned videos from text prompts in flow-based generators.
-
Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling
Visual generation models are evolving from passive renderers to interactive agentic world modelers, but current systems lack spatial reasoning, temporal consistency, and causal understanding, with evaluations overemphasizing perceptual quality.
-
Reward-Aware Trajectory Shaping for Few-step Visual Generation
RATS lets few-step visual generators surpass multi-step teachers by shaping trajectories with reward-based adaptive guidance instead of strict imitation.
-
Anthropogenic Regional Adaptation in Multimodal Vision-Language Model
Anthropogenic Regional Adaptation with GG-EZ improves cultural relevance in multimodal vision-language models for Southeast Asia by 5-15% while retaining over 98% of global performance.
-
Reward-Forcing: Autoregressive Video Generation with Reward Feedback
Reward-Forcing guides autoregressive video generation with reward feedback to achieve performance comparable to teacher-dependent methods on benchmarks like VBench without relying on distillation.
-
PSR: Scaling Multi-Subject Personalized Image Generation with Pairwise Subject-Consistency Rewards
A data-generation pipeline plus pairwise subject-consistency rewards in RL improve consistency and prompt adherence for multi-subject personalized image generation.
-
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Z-Image is an efficient 6B-parameter foundation model for image generation that rivals larger commercial systems in photorealism and bilingual text rendering through a new single-stream diffusion transformer and streamlined training.
- CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating