Search Results for author:
Found 6 papers, 1 papers with code
ICG-MVSNet: Learning Intra-view and Cross-view Relationships for Guidance in Multi-View Stereo
Multi-view Stereo (MVS) aims to estimate depth and reconstruct 3D point clouds from a series of overlapping images.
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system.
Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.
Fine-Grained Embedding Dimension Optimization During Training for Recommender Systems
Huge embedding tables in modern deep learning recommender models (DLRM) require prohibitively large memory during training and inference.
GeoMVSNet: Learning Multi-View Stereo With Geometry Perception
To intensify the full-scene geometry perception of our model, we present the depth distribution similarity loss based on the Gaussian-Mixture Model assumption.
Ranked #2 on
Point Clouds
on Tanks and Temples
Software-Hardware Co-design for Fast and Scalable Training of Deep Learning Recommendation Models
Deep learning recommendation models (DLRMs) are used across many business-critical services at Facebook and are the single largest AI application in terms of infrastructure demand in its data-centers.
