Towards Subject Consistency over Dynamic Subject Sets in Video Generation

arXiv:2610.01052 · cs.CV · Submitted 2026-10-01 · Read on arXiv

cs.CV

Submitted: 2026-10-01

Updated: 2026-10-01

Terminology

• Consistency — 135× in this paper · explained in 3 episodes
• Subject Consistency — 23× in this paper
• Temporal consistency — 20× in this paper · explained in 2 episodes
• Fine-Tuning — 15× in this paper · explained in 5 episodes
• Regularization — 11× in this paper · explained in 3 episodes
• Benchmark — 9× in this paper · explained in 2 episodes
• Generative Model — 6× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Transformer — 5× in this paper · explained in 2 episodes
• Diffusion Model — 4× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Embeddings — 4× in this paper · explained in 2 episodes
• Generative Models — 4× in this paper · explained in 2 episodes
• World Model — 4× in this paper · explained in 7 episodes
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Adam — 2× in this paper · explained in 2 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• LoRA Adapters — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation study — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Global Endpoint Drift — 1× in this paper
• Global Mean Reference Drift — 1× in this paper
• Global Worst-frame Drift — 1× in this paper
• Local Mean Adjacent Drift — 1× in this paper
• Local Spike Rate — 1× in this paper

Sources

• Video Consistency Distance: Enhancing Temporal Consistency for Image-to-Video Generation via Reward-Based Fine-Tuning
• Qwen3-VL Technical Report
• SkyReels-V2: Infinite-length Film Generative Model
• SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer
• Infinite Worlds with Versatile Interactions
• LTX-Video: Realtime Video Latent Diffusion
• VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models
• WorldJen: An End-to-End Multi-Dimensional Benchmark for Generative Video Models
• HunyuanVideo: A Systematic Framework For Large Video Generative Models
• WorldModelBench: Judging Video Generation Models As World Models
• Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
• LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV
• SAM 2: Segment Anything in Images and Videos
• Proximal Policy Optimization Algorithms
• Seedance 2.0: Advancing Video Generation for World Complexity
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Identity-Preserving Image-to-Video Generation via Reward-Guided Optimization
• Kling-Omni Technical Report
• Wan: Open and Advanced Large-Scale Video Generative Models
• Video models are zero-shot learners and reasoners

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models