meta-llama/Llama-3.1-8B-Instruct Text Generation β’ 8B β’ Updated Sep 25, 2024 β’ 8.71M β’ β’ 5.67k
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training Paper β’ 2203.12602 β’ Published Mar 23, 2022 β’ 3
TAPNext: Tracking Any Point (TAP) as Next Token Prediction Paper β’ 2504.05579 β’ Published Apr 8, 2025 β’ 5