The field of video generation and identity verification is rapidly advancing, with a focus on improving the quality and consistency of generated videos, as well as developing more effective methods for verifying identities in various scenarios. Recent research has explored the use of novel architectures, such as graph neural networks and diffusion models, to generate high-quality videos and improve identity verification accuracy. Notably, the development of multimodal-guided controllable video generation and macro-from-micro planning for long video generation has shown promising results. Additionally, research on biometric verification in photorealistic talking-head avatar videos has highlighted the potential of facial motion patterns as reliable behavioral biometrics. Overall, the field is moving towards more sophisticated and effective methods for video generation and identity verification. Noteworthy papers include: Learning Personalised Human Internal Cognition from External Expressive Behaviours for Real Personality Recognition, which proposes a novel approach for real personality recognition. Is It Really You? Exploring Biometric Verification Scenarios in Photorealistic Talking-Head Avatar Videos, which introduces a new dataset and proposes a lightweight spatio-temporal Graph Convolutional Network architecture for biometric verification. MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention, which proposes a novel Video Diffusion Model for identity-preserving text-to-video generation. Macro-from-Micro Planning for High-Quality and Parallelized Autoregressive Long Video Generation, which proposes a novel planning-then-populating framework for long video generation. LongVie: Multimodal-Guided Controllable Ultra-Long Video Generation, which proposes an end-to-end autoregressive framework for controllable long video generation. StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization, which proposes an efficient consistent-subject-generation method. Motion is the Choreographer: Learning Latent Pose Dynamics for Seamless Sign Language Generation, which proposes a new paradigm for sign language video generation. IDCNet: Guided Video Diffusion for Metric-Consistent RGBD Scene Generation with Precise Camera Control, which proposes a novel framework for generating RGB-D video sequences under explicit camera trajectory control. 4DVD: Cascaded Dense-view Video Diffusion Model for High-quality 4D Content Generation, which proposes a cascaded video diffusion model for generating 4D content. PoseGen: In-Context LoRA Finetuning for Pose-Controllable Long Human Video Generation, which proposes a novel framework for generating arbitrarily long videos of a specific subject from a single reference image and a driving pose sequence.