Abstract: Anomaly detection aims to identify patterns and events that deviate from the norm. However, current methods struggle to achieve high detection accuracy due to data complexity, i.e., ...

Abstract: To address limited transmission rates resulting from the laser’s low repetition frequency in cross-medium communication, this study proposed a specialized position coding cross-medium ...

Previous research has investigated the application of Multimodal Large Language Models (MLLMs) in understanding 3D scenes by interpreting them as videos. These approaches generally depend on ...

[25/07/02] We supported fine-tuning the GLM-4.1V-9B-Thinking model. [25/04/28] We supported fine-tuning the Qwen3 model family. [25/04/21] We supported the Muon optimizer. See examples for usage.

Perception Encoder, PE, is the core vision stack in Meta’s Perception Models project. It is a family of encoders for images, video, and audio that reaches state of the art on many vision and audio ...