相关论文: StreamForest: Efficient Online Video Understanding…

We introduce Delayed Streams Modeling (DSM), a flexible formulation for streaming, multimodal sequence-to-sequence learning. Sequence-to-sequence generation is often cast in an offline manner, where the model consumes the complete input…

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially…

Despite progress in video large language models (Video-LLMs), research on instructional video understanding, crucial for enhancing access to instructional content, remains insufficient. To address this, we introduce InstructionBench, an…

Database research can help machine learning performance in many ways. One way is to design better data structures. This paper combines the use of incremental computation and sequential and probabilistic filtering to enable "forgetful"…

Machine learning models deployed in real-world settings must operate under evolving data distributions and constrained computational resources. This challenge is particularly acute in non-stationary domains such as energy time series,…

Generative conversational interfaces powered by large language models (LLMs) typically stream output token-by-token at a rate determined by computational budget, often neglecting actual human reading speeds and the cognitive load associated…

Extracting real-time insights from multi-modal data streams from various domains such as healthcare, intelligent transportation, and satellite remote sensing remains a challenge. High computational demands and limited knowledge scope…

Long-video understanding remains a significant challenge for Multimodal Large Language Models (MLLMs) due to inherent token limitations and the complexity of capturing long-term temporal dependencies. Existing methods often fail to capture…

Integrating vision models into large language models (LLMs) has sparked significant interest in creating vision-language foundation models, especially for video understanding. Recent methods often utilize memory banks to handle untrimmed…

Today, massive amounts of streaming data from smart devices need to be analyzed automatically to realize the Internet of Things. The Complex Event Processing (CEP) paradigm promises low-latency pattern detection on event streams. However,…

Streaming process mining deals with the real-time analysis of event streams. A common approach for it is to adopt windowing mechanisms that select event data from a stream for subsequent analysis. However, the size of these windows denotes…

Real-world long video understanding requires models to perform continuous tracking, information integration and memory retention over massive temporal spans within extreme video durations. Mastering this intense cognitive load constitutes…

Large Vision Language Models (LVLMs) exhibit strong Chain-of-Thought (CoT) capabilities, yet most existing paradigms assume full-video availability before inference, a batch-style process misaligned with real-world video streams where…

Multi-modal Large language models (MLLMs) show remarkable ability in video understanding. Nevertheless, understanding long videos remains challenging as the models can only process a finite number of frames in a single inference,…

Recent advancements in Chain of Thought (COT) generation have significantly improved the reasoning capabilities of Large Language Models (LLMs), with reinforcement learning (RL) emerging as an effective post-training approach. Multimodal…

Nowadays with a growing number of online controlling systems in the organization and also a high demand of monitoring and stats facilities that uses data streams to log and control their subsystems, data stream mining becomes more and more…

Video understanding with multimodal large language models (MLLMs) remains challenging due to the long token sequences of videos, which contain extensive temporal dependencies and redundant frames. Existing approaches typically treat MLLMs…

Some of the most relevant document schemas used online, such as XML and JSON, have a nested format. In the last decade, the task of extracting data from nested documents over streams has become especially relevant. We focus on the streaming…

Machine unlearning aims to remove knowledge of the specific training data in a well-trained model. Currently, machine unlearning methods typically handle all forgetting data in a single batch, removing the corresponding knowledge all at…

Streaming Speech-to-Text Translation (StreamST) requires producing translations concurrently with incoming speech, imposing strict latency constraints and demanding models that balance partial-information decision-making with high…