OpenSAL360: Open-Source Crowdsourcing Platform for Omnidirectional Video Saliency Collection
为解决全景视频显著性数据收集成本高、复杂度大的问题，提出OpenSAL360平台，利用普通屏幕和鼠标通过众包方式低成本收集数据。
0 citationsRead paper
Selected work
Representative Papers
Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching
This work addresses the sharp performance degradation of conventional models in subseasonal (up to 30-day) global weather forecasting, a challenge rooted in atmospheric chaos. To overcome this limitation, the authors propose Marchuk, a generative latent-space autoregressive model based on flow matching. By replacing Rotary Position Embedding (RoPE) with trainable positional embeddings and extending the temporal context window, Marchuk substantially enhances its capacity to model long-range temporal dependencies. Remarkably, with only 276 million parameters—far fewer than the 1.6 billion in comparable models—it achieves forecasting accuracy on par with LaDCast over the full 30-day horizon while offering significantly faster inference. The code and model weights have been publicly released.
0 citationsRead paper
Recent publications
Latest Papers
OpenSAL360: Open-Source Crowdsourcing Platform for Omnidirectional Video Saliency Collection
为解决全景视频显著性数据收集成本高、复杂度大的问题，提出OpenSAL360平台，利用普通屏幕和鼠标通过众包方式低成本收集数据。
0 citationsRead paper
Marchuk: Efficient Global Weather Forecasting from Mid-Range to Sub-Seasonal Scales via Flow Matching
This work addresses the sharp performance degradation of conventional models in subseasonal (up to 30-day) global weather forecasting, a challenge rooted in atmospheric chaos. To overcome this limitation, the authors propose Marchuk, a generative latent-space autoregressive model based on flow matching. By replacing Rotary Position Embedding (RoPE) with trainable positional embeddings and extending the temporal context window, Marchuk substantially enhances its capacity to model long-range temporal dependencies. Remarkably, with only 276 million parameters—far fewer than the 1.6 billion in comparable models—it achieves forecasting accuracy on par with LaDCast over the full 30-day horizon while offering significantly faster inference. The code and model weights have been publicly released.
0 citationsRead paper