8 papers
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
MoReFun: Past-Movement Guided Motion Representation Learning for Future Motion Prediction and Understanding
Junyu Shi, Haoting Wu, Zhiyuan Zhang +3
3D human motion prediction aims to generate coherent future motions from observed sequences, yet existing end-to-end regression frameworks often fail to capture complex dynamics an…
EmbryoDiff: A Conditional Diffusion Framework with Multi-Focal Feature Fusion for Fine-Grained Embryo Developmental Stage Recognition
Yong Sun, Zhengjie Zhang, Junyu Shi +3
Identification of fine-grained embryo developmental stages during In Vitro Fertilization (IVF) is crucial for assessing embryo viability. Although recent deep learning methods have…
MoGIC: Boosting Motion Generation via Intention Understanding and Visual Context
Junyu Shi, Yong Sun, Zhiyuan Zhang +4
Existing text-driven motion generation methods often treat synthesis as a bidirectional mapping between language and motion, but remain limited in capturing the causal logic of act…
GenM: Generative Pretrained Multi-path Motion Model for Text Conditional Human Motion Generation
Junyu Shi, Lijiang Liu, Yong Sun +3
Scaling up motion datasets is crucial to enhance motion generation capabilities. However, training on large-scale multi-source datasets introduces data heterogeneity challenges due…
Time-Lapse Video-Based Embryo Grading via Complementary Spatial-Temporal Pattern Mining
Yong Sun, Yipeng Wang, Junyu Shi +5
Artificial intelligence has recently shown promise in automated embryo selection for In-Vitro Fertilization (IVF). However, current approaches either address partial embryo evaluat…