Wei Li

The DeepSeek-V4.1-Flash model, a multimodal Mixture-of-Experts model with 552B backbone parameters and support for contexts of up to one million tokens, is introduced, substantially improving cost efficiency for agentic workloads and pushing the limits of KV cache compression.

MUSE decouples image annotation from question generation, enabling diverse tasks with controllable difficulty while reducing annotation effort, and it is hoped MUSE will serve as a standardized benchmark for advancing multi-modal understanding in situated educational applications.

Experiments show improved depth accuracy and temporal consistency over scale-only calibration, demonstrating how localization geometry can support both pose recovery and dense robot perception.

UniMPA, a Unified Memory-Prediction-Action model that addresses transition ambiguity by modeling the intended future state evolution through a shared action-grounded transition interface, is proposed.

Masking compositional concepts in one modality while leveraging contextual cues from another can dramatically enhance the compositionality of vision-language models.