ArtiVidRM: Verifiable Artifact-as-Rubric Reward Modeling for Explicit Quality Articulation in Video Generation
cs.CV
Submitted: 2026-11-05
Updated: 2026-11-05
Sources
- Direct Preference Optimization with an Offset
- Constitutional AI: Harmlessness from AI Feedback
- OmniReasoner: Thinking with Long Audio-Video via Native Tool Use
- DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence
- Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
- Claim-Level Rubric Rewards for Video Caption Reinforcement Learning
- VideoScore: Building Automatic Metrics to Simulate Fine-grained Human Feedback for Video Generation
- VideoScore2: Think before You Score in Generative Video Evaluation
- VBench: Comprehensive Benchmark Suite for Video Generative Models
- Subjective-Aligned Dataset and Metric for Text-to-Video Quality Assessment
- OmniVideoBench: Towards Audio-Visual Understanding Evaluation for Omni MLLMs
- Flow-GRPO: Training Flow Matching Models via Online RL
- Improving Video Generation with Human Feedback
- VideoDPO: Omni-Preference Alignment for Video Diffusion Generation
- EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
- Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models
- Self-Refine: Iterative Refinement with Self-Feedback
- Seedance 2.0: Advancing Video Generation for World Complexity
- Wan: Open and Advanced Large-Scale Video Generative Models
- Kling-Foley: Multimodal Diffusion Transformer for High-Quality Video-to-Audio Generation
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs