Related papers: TimeTok: Granularity-Controllable Time-Series Gene…

Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In…

Time series synthesis is an important research topic in the field of deep learning, which can be used for data augmentation. Time series data types can be broadly classified into regular or irregular. However, there are no existing…

Score-based generative models (SGMs) have demonstrated unparalleled sampling quality and diversity in numerous fields, such as image generation, voice synthesis, and tabular data synthesis, etc. Inspired by those outstanding results, we…

Industrial-scale recommender systems rely on a cascade pipeline in which the retrieval stage must return a high-recall candidate set from billions of items under tight latency. Existing solutions either (i) suffer from limited…

In real world domains, most graphs naturally exhibit a hierarchical structure. However, data-driven graph generation is yet to effectively capture such structures. To address this, we propose a novel approach that recursively generates…

Simultaneous sequence generation is a pivotal task for real-time scenarios, such as streaming speech recognition, simultaneous machine translation and simultaneous speech translation, where the target sequence is generated while receiving…

Consider learning a generative model for time-series data. The sequential setting poses a unique challenge: Not only should the generator capture the conditional dynamics of (stepwise) transitions, but its open-loop rollouts should also…

Efficient and robust data clustering remains a challenging task in the field of data analysis. Recent efforts have explored the integration of granular-ball (GB) computing with clustering algorithms to address this challenge, yielding…

Generating consistent long videos is a complex challenge: while diffusion-based generative models generate visually impressive short clips, extending them to longer durations often leads to memory bottlenecks and long-term inconsistency. In…

How to best develop foundational models for time series forecasting remains an important open question. Tokenization is a crucial consideration in this effort: what is an effective discrete vocabulary for a real-valued sequential input? To…

Data summarization is the process of generating interpretable and representative subsets from a dataset. Existing time series summarization approaches often search for recurring subsequences using a set of manually devised similarity…

Recently, diffusion probabilistic models have attracted attention in generative time series forecasting due to their remarkable capacity to generate high-fidelity samples. However, the effective utilization of their strong modeling ability…

Inspired by the remarkable success of autoregressive models in language modeling, this paradigm has been widely adopted in visual generation. However, the sequential token-by-token decoding mechanism inherent in traditional autoregressive…

In the medical field, the limited availability of large-scale datasets and labor-intensive annotation processes hinder the performance of deep models. Diffusion-based generative augmentation approaches present a promising solution to this…

Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements…

Due to the difficulty of acquiring extensive real-world data, robot simulation has become crucial for parallel training and sim-to-real transfer, highlighting the importance of scalable simulated robotic tasks. Foundation models have…

Recommendation model performance is intrinsically tied to the quality, volume, and relevance of their training data. To address common challenges like data sparsity and cold start, recent researchs have leveraged data from multiple…

We propose AdapTok, an adaptive temporal causal video tokenizer that can flexibly allocate tokens for different frames based on video content. AdapTok is equipped with a block-wise masking strategy that randomly drops tail tokens of each…

Watch time prediction (WTP) has emerged as a pivotal task in short video recommendation systems, designed to quantify user engagement through continuous interaction modeling. Predicting users' watch times on videos often encounters…

Temporal graph clustering (TGC) is a crucial task in temporal graph learning. Its focus is on node clustering on temporal graphs, and it offers greater flexibility for large-scale graph structures due to the mechanism of temporal graph…