Chat-UniVi [CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Chat-UniVi/Chat-UniVi Video-Text-to-Text • Updated Oct 22, 2024 • 106 • 17 Chat-UniVi/Chat-UniVi-7B-v1.5 Video-Text-to-Text • Updated Dec 7, 2024 • 9 • 2 Chat-UniVi/Chat-UniVi-13B Video-Text-to-Text • Updated Dec 7, 2024 • 51 • 9 Chat-UniVi/Chat-UniVi-7B-v1.5-Stage-1 Text Generation • Updated May 28, 2024 • 13
MoE++ [ICLR 2025 Oral🔥] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Chat-UniVi/MoE-Plus-Plus-7B Text Generation • Updated Dec 7, 2024 • 88 • 5 MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Paper • 2410.07348 • Published Oct 9, 2024 • 1
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Paper • 2410.07348 • Published Oct 9, 2024 • 1
MoH MoH: Multi-Head Attention as Mixture-of-Head Attention Chat-UniVi/MoH-LLaMA3-8B Text Generation • Updated Dec 7, 2024 • 28 • 3 Chat-UniVi/MoH-DiT-XL-90 Updated Oct 17, 2024 • 3 Chat-UniVi/MoH-ViT-B-75 Updated Oct 17, 2024 Chat-UniVi/MoH-ViT-B-50 Updated Oct 17, 2024
Chat-UniVi [CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding Chat-UniVi/Chat-UniVi Video-Text-to-Text • Updated Oct 22, 2024 • 106 • 17 Chat-UniVi/Chat-UniVi-7B-v1.5 Video-Text-to-Text • Updated Dec 7, 2024 • 9 • 2 Chat-UniVi/Chat-UniVi-13B Video-Text-to-Text • Updated Dec 7, 2024 • 51 • 9 Chat-UniVi/Chat-UniVi-7B-v1.5-Stage-1 Text Generation • Updated May 28, 2024 • 13
MoH MoH: Multi-Head Attention as Mixture-of-Head Attention Chat-UniVi/MoH-LLaMA3-8B Text Generation • Updated Dec 7, 2024 • 28 • 3 Chat-UniVi/MoH-DiT-XL-90 Updated Oct 17, 2024 • 3 Chat-UniVi/MoH-ViT-B-75 Updated Oct 17, 2024 Chat-UniVi/MoH-ViT-B-50 Updated Oct 17, 2024
MoE++ [ICLR 2025 Oral🔥] MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Chat-UniVi/MoE-Plus-Plus-7B Text Generation • Updated Dec 7, 2024 • 88 • 5 MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Paper • 2410.07348 • Published Oct 9, 2024 • 1
MoE++: Accelerating Mixture-of-Experts Methods with Zero-Computation Experts Paper • 2410.07348 • Published Oct 9, 2024 • 1
