2024-11-22 15:28:38.AIbase.
Meta's Latest Audio Model SPIRIT LM: Making AI Not Just Talk, But Also Express Emotion!
2024-11-22 14:45:24.AIbase.
Samsung Launches New Gauss 2 AI Model, Expected to Be the Next Galaxy Brain
2024-11-21 14:05:19.AIbase.
AI Unveils Depression! Voice + EEG, Diagnostic Accuracy Reaches 97.53%
2024-11-19 13:51:41.AIbase.
Peking University Team Releases Multimodal Model LLaVA-o1, Inference Capabilities Comparable to GPT-o1!
2024-11-19 09:54:07.AIbase.
Mistral Launches the Most Powerful Open Source Multimodal Model Pixtral Large, Upgrading Le Chat to Directly Call Flux Pro
2024-11-15 08:36:19.AIbase.
iFLYTEK Spark Multimodal Interaction Model Launched, Achieving 'Voice, Vision, and Digital Human Interaction' Integration
2024-11-14 16:16:41.AIbase.
Open Source AI Language Model Ultravox v0.4.1: Making AI Real-Time Conversations Smoother and Smarter
2024-11-06 09:53:34.AIbase.
Chinese Team Releases the World's Largest Open-source Multimodal Dataset, Achieving Record Performance with 2B Parameter Model
2024-11-06 09:29:51.AIbase.
Chinese Team Launches World's Largest Multimodal Dataset 'Infinity-MM' and Cutting-Edge Micro AI Model 'Aquila-VL-2B'
2024-10-28 16:13:01.AIbase.
ZhiYuan Launches Hour-Level Ultra-Long Video Understanding Model Video-XL
2024-10-28 14:42:03.AIbase.
Meta Open Sources Long Video LLM Project LongVU: Filters Duplicate Frames for Efficient and Accurate Understanding of Long Video Content
2024-10-25 11:16:59.AIbase.
Salesforce AI Research Unveils New Multimodal Model BLIP-3-Video: Cost-Effective Video Understanding
2024-10-23 09:40:35.AIbase.
Cohere Launches Multimodal Search Model Embed3, Allowing Text and Image-Based File Retrieval
2024-10-21 14:55:38.AIbase.
Zhiyuan Releases Native Multimodal World Model Emu3: Achieving Text, Image, and Video Understanding and Generation Solely Through Next Token Prediction
2024-10-21 13:52:45.AIbase.
Redefining Multimodal AI! Zhiyuan Releases the Native Multimodal World Model Emu3
2024-10-14 10:56:21.AIbase.
Apple's 'Multimodal Alchemy Furnace' Upgraded Again! MM1.5 Enhances Text Density and Multimodal Understanding
2024-10-11 10:03:00.AIbase.
Rhymes AI Launches First Open Source Multimodal AI Model Aria, Outperforming GPT-4o Mini and Other Leading AI Models
2024-10-10 11:08:05.AIbase.
vivo Launches New Blue Heart Large Model Matrix: Upgraded Language, Voice, Image, and Multimodal Capabilities
2024-10-10 11:03:28.AIbase.
iFlytek: To Release Multimodal Visual Interaction Technology on October 24
2024-10-08 11:18:05.AIbase.