Related papers: OneLive: Dynamically Unified Generative Framework …
We propose UniDFlow, a unified discrete flow-matching framework for multimodal understanding, generation, and editing. It decouples understanding and generation via task-specific low-rank adapters, avoiding objective interference and…
Understanding continuous video streams plays a fundamental role in real-time applications including embodied AI and autonomous driving. Unlike offline video understanding, streaming video understanding requires the ability to process video…
Flow-matching models have enabled high-quality text-to-speech synthesis, but their iterative sampling process during inference incurs substantial computational cost. Although distillation is widely used to reduce the number of inference…
Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch,…
Creating AI systems that can interact with environments over long periods, similar to human cognition, has been a longstanding research goal. Recent advancements in multimodal large language models (MLLMs) have made significant strides in…
Gesture recognition in resource-constrained scenarios faces significant challenges in achieving high accuracy and low latency. The streaming gesture recognition framework, Duo Streamers, proposed in this paper, addresses these challenges…
Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we…
With the rise of diffusion models, audio-video generation has been revolutionized. However, most existing methods rely on separate modules for each modality, with limited exploration of unified generative architectures. In addition, many…
Modeling long horizon marked event sequences is a fundamental challenge in many real-world applications, including healthcare, finance, and user behavior modeling. Existing neural temporal point process models are typically autoregressive,…
Live video streaming has become a mainstay as a standard communication solution for several enterprises worldwide. To efficiently stream high-quality live video content to a large amount of offices, companies employ distributed video…
With the prevalence of social networks on online platforms, social recommendation has become a vital technique for enhancing personalized recommendations. The effectiveness of social recommendations largely relies on the social homophily…
The dynamic environment in the real world calls for the adaptive techniques for information filtering, namely to provide real-time responses to the changes of system data. Where many incremental algorithms are designed for this purpose,…
The manuscript introduces a method to select a random sample from a stream by deciding on each sampling unit immediately after observing it. The process could be applied to unequal as well as equal probability sampling. The implementation…
Decision-making is a cognitively intensive task that requires synthesizing relevant information from multiple unstructured sources, weighing competing factors, and incorporating subjective user preferences. Existing methods, including large…
Several overlay-based live multimedia streaming platforms have been proposed in the recent peer-to-peer streaming literature. In most of the cases, the overlay neighbors are chosen randomly for robustness of the overlay. However, this…
Streaming platforms, like Netflix and YouTube, strive to offer high streaming quality (SQ), in terms of bitrate, delays, etc., to their users. Meanwhile, a significant share of content consumption of these platforms is heavily influenced by…
In domains where users tend to develop long-term preferences that do not change too frequently, the stability of recommendations is an important factor of the perceived quality of a recommender system. In such cases, unstable…
The recent success of large language models (LLMs) has renewed interest in whether recommender systems can achieve similar scaling benefits. Conventional recommenders, dominated by massive embedding tables, tend to plateau as embedding…
Transformer-based generative models have achieved remarkable success across domains with various scaling law manifestations. However, our extensive experiments reveal persistent challenges when applying Transformer to recommendation…
One of the most used approaches for providing recommendations in various online environments such as e-commerce is collaborative filtering. Although, this is a simple method for recommending items or services, accuracy and quality problems…