Variational Autoencoders (VAEs) form the foundation of modern video generation models. In particular, discrete latent VAEs with vector quantization have gained prominence for their superior perceptual sharpness, ability to model long-range dynamics, and efficient adaptation to downstream tasks. However, existing discrete VAEs face two key limitations: (i) a lack of frequency-domain modeling to enhance global spatiotemporal understanding, and (ii) fixed-resolution quantization schemes, preventing effective modeling of coarse-to-fine spatiotemporal hierarchies essential for video generation. To address these limitations, we propose a Pyramidal Vector Quantized Variational Autoencoder (PVQ-VAE) for videos. PVQ-VAE’s encoder–decoder leverages Fast Fourier Transform and Discrete Wavelet Transform to capture global semantics and multi-scale local details jointly. We introduce Pyramidal Vector Quantization (PVQ), a hierarchical quantization scheme that discretizes features at multiple resolutions to better capture multi-scale information. To further boost fidelity, we introduce a cross-modal contrastive loss guided by a pretrained high-resolution image VAE. PVQ-VAE achieves state-of-the-art performance on WebVid-val, COCO-val, and MCL-JCV, reconstructing videos with high perceptual quality at up to 32× spatial and 16× temporal compression. Project page of PVQ-VAE.

Learning the preferences of new users and items with limited interaction history is a major challenge in recommender systems, known as the cold-start recommendation problem. Meta-learning methods, particularly those based on MAML, show strong potential by learning generalized initializations across randomly sampled tasks. In the context of cold-start recommendation, a task represents a new user or item and their associated interactions. These initializations enable rapid adaptation to new users or items for effective preference learning. However, these methods often struggle with personalization due to two key limitations: 1) the generalized initialization is learned under the assumption of a uniform task distribution, and 2) the inability to capture user or item-specific rating tendencies. To address these limitations, we propose Dynamic Task-Adaptive Meta Optimization (DTAMO). DTAMO learns initializations on dynamic tasks, which are clusters of similar users based on its profile attributes and interaction patterns. This helps to capture both personalized and shared user preferences. We design a Cross-Attention Transformer-based autoencoder to discover these user clusters and introduce a Task-Adaptive Meta Optimizer (TAMO) that performs attention-weighted gradient aggregation within each dynamic task. This enables TAMO to efficiently capture both shared and personalized preferences in a single optimization step. To better model user and item-specific rating behaviors, DTAMO incorporates lightweight rating-distribution-aware representations, which capture rating tendencies of user or items with minimal computational cost. We integrate ordinal regression into the meta-learning framework to further enhance the personalization by aligning the model’s learning objective with the ordinal structure of rating data. Extensive experiments on three public datasets demonstrate that DTAMO consistently outperforms state-of-the-art methods in both accuracy and scalability.

With the emergence of online social platforms enabling users to share their opinions with others, there has been a critical need for developing a recommendation system incorporating users’ social connections to learn their preferences. Social relations between users offer potential information about users’ preferences, which alleviates the data sparsity issue and boosts recommendation performance. Several efforts have been made to develop an efficient social recommendation system. Nevertheless, existing approaches have two significant drawbacks: First, they haven’t efficiently explored the complex correlations between the diverse influence of neighbours on users’ item preferences. Second, contemporary systems rely on the unidirectional context of items and fail to embrace bidirectional contexts and long range dependencies while predicting the next user-item interaction. To address the above issues, we propose a novel framework for Social Recommendation called Multi-View Bert Network (MVBN). This model incorporated Bidirectional Encoder Representations from Transformer(BERT) with Multi-Task learning to learn bidirectional context-aware user and item embeddings with neighbourhood sampling. Neighbourhood Sampling technique samples the most influential neighbours for all the items, and our proposed Sequence Header correlates sampled neighbours with users. The main objective of our model is to predict the next item that a user would interact with based on its interaction behaviour. Experiments on three real-world datasets demonstrate that the proposed MVBN model outperforms the state-of-the-art recommendation methods consistently and significantly. Finally, an extensive ablation study is carried out to validate the importance of each component in the system.

In the real world, when we seek our friends’ opinions on various items or events, we request verbal social recommendations. It has been observed that we often turn to our friends for recommendations on a daily basis. The emergence of online social platforms has enabled users to share their opinion with their social connections. Therefore, we should consider users’ social connections to enhance online recommendation performance. The social recommendation aims to fuse social links with user-item interactions to offer more relevant recommendations. Several efforts have been made to develop an effective social recommendation system. However, there are two significant limitations to current methods: First, they haven’t thoroughly explored the intricate relationships between the diverse influences of neighbours on users’ preferences. Second, existing models are vulnerable to overfitting due to the relatively low number of user-item interaction records in the interaction space. For the aforementioned problems, this paper offers a novel framework called CR-SoRec, an effective recommendation model based on BERT and consistency regularization. This model incorporates Bidirectional Encoder Representations from Transformer(BERT) to learn bidirectional context-aware user and item embeddings with neighbourhood sampling. The neighbourhood Sampling technique samples the most influential neighbours for all the users/ items. Further, to effectively use the available user-item interaction data and social ties, we leverage diverse perspectives via consistency regularization to harness the underlying information. The main objective of our model is to predict the next item that a user would interact with based on its interaction behaviour and social connections. Experimental results show that our model defines a new state-of-the-art on various datasets and outperforms previous work by a significant margin. Extensive experiments are also conducted to analyze the proposed method.