Related papers: Bridging Modalities, Spanning Time: Structured Mem…

Memory has become an increasingly important component of agentic systems, as these systems are expected to reason over long-term experience. However, prior work has largely focused on unimodal memory, leaving multimodal memory relatively…

Video question answering (VideoQA) is a challenging task that requires integrating spatial, temporal, and semantic information to capture the complex dynamics of video sequences. Although recent advances have introduced various approaches…

Despite recent advances in retrieval-augmented generation (RAG) for video understanding, effectively understanding long-form video content remains underexplored due to the vast scale and high complexity of video data. Current RAG approaches…

This paper aims to improve the performance of video multimodal large language models (MLLM) via long and rich context (LRC) modeling. As a result, we develop a new version of InternVideo2.5 with a focus on enhancing the original MLLMs'…

Long video question answering requires locating sparse, time-scattered visual evidence within highly redundant content. Although current MLLMs perform well on short videos, long videos introduce long-horizon search and verification, which…

Multimodal large language models (MLLMs) have substantially advanced video misinformation detection through unified multimodal reasoning, but they often rely on fixed-depth inference and place excessive trust in internally generated…

Vision-Language Navigation (VLN) agents often struggle with long-horizon reasoning in unseen environments, particularly when facing ambiguous, coarse-grained instructions. While recent advances use knowledge graph to enhance reasoning, the…

Video Question Answering (VQA) inherently relies on multimodal reasoning, integrating visual, temporal, and linguistic cues to achieve a deeper understanding of video content. However, many existing methods rely on feeding frame-level…

Long video understanding (LVU) is challenging because answering real-world queries often depends on sparse, temporally dispersed cues buried in hours of mostly redundant and irrelevant content. While agentic pipelines improve video…

In order for large language models to achieve true conversational continuity and benefit from experiential learning, they need memory. While research has focused on the development of complex memory systems, it remains unclear which types…

Agentic memory systems have become critical for enabling LLM agents to maintain long-term context and retrieve relevant information efficiently. However, existing memory frameworks suffer from a fundamental limitation: they perform…

Existing works on long-term open-domain dialogues focus on evaluating model responses within contexts spanning no more than five chat sessions. Despite advancements in long-context large language models (LLMs) and retrieval augmented…

In long-video understanding, conventional uniform frame sampling often fails to capture key visual evidence, leading to degraded performance and increased hallucinations. To address this, recent agentic thinking-with-videos paradigms have…

Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, depth map, or dense temporal evidence. In such a scenario, uniform fusion induces modality…

Vision agent memory has shown remarkable effectiveness in streaming video understanding. However, storing such memory for videos incurs substantial memory overhead, leading to high costs in both storage and computation. To address this…

This paper is on long-term video understanding where the goal is to recognise human actions over long temporal windows (up to minutes long). In prior work, long temporal context is captured by constructing a long-term memory bank consisting…

The rapid advancements in Large Language Models (LLMs) and their multimodal extensions (MLLMs) have ushered in remarkable progress in video understanding. However, a fundamental challenge persists: effectively processing and comprehending…

The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extractive reasoning, where answers can be explicitly presented within spatiotemporal events. It…

Previous research has studied the task of segmenting cinematic videos into scenes and into narrative acts. However, these studies have overlooked the essential task of multimodal alignment and fusion for effectively and efficiently…

Recently, integrating visual foundation models into large language models (LLMs) to form video understanding systems has attracted widespread attention. Most of the existing models compress diverse semantic information within the whole…