TECH·11 hours agoMiniMax Releases Open-Source Full-Modal Model H3: Video Editing Ranks No. 1 Globally With Pricing Cut to One-Third of CompetitorsPandaily
PAPER·13 hours agoSee2Think: Do Multimodal Models Really Use Intermediate Visual States?Hugging Face Papers
TECH·22 hours agoThinking Machines debuts Inkling Small open source AI model nearing performance of predecessor at about 1/4 sizeVentureBeat
PAPER·5 days agoDICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language ModelsarXiv
PAPER·5 days agoPerceptionBench: Evaluating Atomic Visual Perception in Multimodal Large Language ModelsHugging Face Papers
