Hymba: A Hybrid-head Architecture for Small Language Models Paper • 2411.13676 • Published Nov 20 • 39
Hymba: A Hybrid-head Architecture for Small Language Models Paper • 2411.13676 • Published Nov 20 • 39
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation Paper • 2410.21271 • Published Oct 28 • 6
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics Paper • 2408.17443 • Published Aug 30 • 1
HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics Paper • 2408.17443 • Published Aug 30 • 1
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation Paper • 2410.21271 • Published Oct 28 • 6
EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation Paper • 2410.21271 • Published Oct 28 • 6 • 2
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation Paper • 2406.12849 • Published Jun 18 • 49
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction Paper • 2309.03900 • Published Sep 7, 2023 • 1
SemPLeS: Semantic Prompt Learning for Weakly-Supervised Semantic Segmentation Paper • 2401.11791 • Published Jan 22 • 1
PartDistill: 3D Shape Part Segmentation by Vision-Language Model Distillation Paper • 2312.04016 • Published Dec 7, 2023 • 1
Probabilistic 3D Multi-Object Cooperative Tracking for Autonomous Driving via Differentiable Multi-Sensor Kalman Filter Paper • 2309.14655 • Published Sep 26, 2023 • 1
2D-3D Interlaced Transformer for Point Cloud Segmentation with Scene-Level Supervision Paper • 2310.12817 • Published Oct 19, 2023 • 1
Conditional Modeling Based Automatic Video Summarization Paper • 2311.12159 • Published Nov 20, 2023 • 1