相关论文: OASIS: On-Demand Hierarchical Event Memory for Str…
Referring Video Object Segmentation (RVOS) aims to segment an object of interest throughout a video based on a language description. The prominent challenge lies in aligning static text with dynamic visual content, particularly when objects…
Video scene detection is the task of dividing videos into temporal semantic chapters. This is an important preliminary step before attempting to analyze heterogeneous video content. Recently, Optimal Sequential Grouping (OSG) was proposed…
To extend the reinforcement learning post-training paradigm to omni-modal models for concurrently bolstering video-audio understanding and collaborative reasoning, we propose OmniJigsaw, a generic self-supervised framework built upon a…
The increasing popularity of real-world recommender systems produces data continuously and rapidly, and it becomes more realistic to study recommender systems under streaming scenarios. Data streams present distinct properties such as…
Sequential recommender systems have become increasingly important in real-world applications that model user behavior sequences to predict their preferences. However, existing sequential recommendation methods predominantly rely on…
While Test-Time Scaling (TTS) offers a promising direction to enhance video generation without the surging costs of training, current test-time video generation methods based on diffusion models suffer from exorbitant candidate exploration…
Proactive streaming video understanding requires Video-LLMs to decide when to respond as a video unfolds, a task where existing methods often fall short due to their implicit, query-agnostic modeling of visual evidence. We introduce…
Replay-based methods have proved their effectiveness on online continual learning by rehearsing past samples from an auxiliary memory. With many efforts made on improving training schemes based on the memory, however, the information…
Retrieval-augmented generation (RAG) has achieved significant success in information retrieval to assist large language models LLMs because it builds an external knowledge database. However, it also has many problems, it consumes a lot of…
Media streaming has been adopted for a variety of applications such as entertainment, visualization, and design. Unlike video/audio streaming where the content is usually consumed sequentially, 3D applications such as gaming require…
Driven by our mission of "uplifting the world with memory," this paper explores the design concept of "memory" that is essential for achieving artificial superintelligence (ASI). Rather than proposing novel methods, we focus on several…
A key need in different disciplines is to perform analytics over fast-paced data streams, similar in nature to the traditional OLAP analytics in relational databases i.e., with filters and aggregates. Storing unbounded streams, however, is…
Estimating the size of the maximum matching is a canonical problem in graph algorithms, and one that has attracted extensive study over a range of different computational models. We present improved streaming algorithms for approximating…
The computational and memory demands of large language models for generative inference present significant challenges for practical deployment. One promising solution targeting offline inference is offloading-based batched inference, which…
In the context of today's high-pressure, aging society, the demand for large-scale emotional models capable of providing empathetic support is more critical than ever. However, existing benchmarks fail to simultaneously achieve ecological…
Recent advances in video generation have revealed an unexpected phenomenon: diffusion-based video models exhibit non-trivial reasoning capabilities. Prior work attributes this to a Chain-of-Frames (CoF) mechanism, where reasoning is assumed…
Streaming process mining deals with the real-time analysis of streaming data. Event streams require algorithms capable of processing data incrementally. To systematically address the complexities of this domain, we propose AVOCADO, a…
Streaming algorithms are generally judged by the quality of their solution, memory footprint, and computational complexity. In this paper, we study the problem of maximizing a monotone submodular function in the streaming setting with a…
Humans can easily distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object. Hence, we aim to make deep learning models…
The temporal segmentation of events is an essential task and a precursor for the automatic recognition of human actions in the video. Several attempts have been made to capture frame-level salient aspects through attention but they lack the…