arXiv:2606. 31421v1 Announce Type: cross Abstract: Single-stage video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached.
arXiv:2607. 14711v1 Announce Type: cross Abstract: We present for video understanding (classification) a split space-time attention model, VideoSEMA, consisting of a scalable and efficient Mamba-like attention (SEMA) block in space and a softmax temporal attention in time.
arXiv:2606. 12300v1 Announce Type: cross Abstract: Temporal grounding--returning the interval $[t_s, t_e]$ for a natural-language query over a video--is the language interface to long-form video, yet has been studied on short videos; the dynamics of hour-scale natural-language grounding remain underexplored.
arXiv:2606. 10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly understood.
arXiv:2606. 09056v1 Announce Type: cross Abstract: Video generative models have become increasingly powerful, but long-range consistency remains challenging to achieve because even a few dozen frames require impractically long transformer sequence lengths.
arXiv:2606. 26348v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) can process diverse inputs, e.
Long-video understanding remains challenging for multimodal large language models, because temporally extended videos often contain thousands of frames and are therefore expensive to process exhaustively. Existing methods usually construct compact visual inputs from long videos under a limited visual budget.
arXiv:2607. 18367v1 Announce Type: new Abstract: Unlike conventional video game development, which relies on labor-intensive pipelines for asset production, animation, physics, and programming, video world models generate interactive environments from user inputs instantly.
Ring Forcing is an autoregressive video diffusion framework that enhances long‑term memory by enforcing retrieval from distant history through a ring‑structured training strategy. It introduces a compression and timestep composition method to extend effective historical span to minutes, and a sparse RoPE mechanism for scalable memory adaptation. Experiments show that Ring Forcing outperforms state‑of‑the‑art models in minutes‑long coherence and object permanence.
arXiv:2606. 10183v1 Announce Type: cross Abstract: Modern Diffusion Transformers for video generation provide limited control over the progression of time and the editing of temporal dynamics.
arXiv:2604. 10024v2 Announce Type: replace-cross Abstract: Long video summarization presents significant challenges for multimodal large language models (MLLMs), particularly in maintaining temporal fidelity over extended durations and producing summaries that are both semantically and temporally grounded.
arXiv:2510. 12453v3 Announce Type: replace Abstract: Diffusion models excel in noise-to-data generation tasks, providing a mapping from a Gaussian distribution to a more complex data distribution.