TECH·yesterdayBYD AI Team Revealed for the First Time, Harbin Institute of Technology Robot Genes Stand Out, Large Model Debuts as SOTA - 36Kr36氪
PAPER·yesterdayMage-VL: An Efficient Codec-Native Streaming Multimodal Foundation ModelHugging Face Papers
PAPER·2 days agoUltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language ModelsHugging Face Papers
PAPER·2 days agoSalient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question AnsweringarXiv
TECH·2 days agoKimi K3 Officially Open-Sourced: Moonshot AI Releases 2.8 Trillion Parameter Model Weights, Technical Report, and Three Infrastructure TechnologiesPandaily
PAPER·2 days agoTowards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided AssessmentarXiv
PAPER·2 days agoJarvisHub: An Open Harness for Canvas-Native Multimodal Creative AgentsHugging Face Papers
