Dlora: Distributed parameter-efficient fine-tuning solution for large language model
To enhance the performance of large language models (LLM) on downstream tasks, one
solution is to fine-tune certain LLM parameters and make it better align with the …
solution is to fine-tune certain LLM parameters and make it better align with the …
UniLCD: Unified Local-Cloud Decision-Making via Reinforcement Learning
K Sengupta, Z Shagguan, S Bharadwaj, S Arora… - arXiv preprint arXiv …, 2024 - arxiv.org
Embodied vision-based real-world systems, such as mobile robots, require a careful
balance between energy consumption, compute latency, and safety constraints to optimize …
balance between energy consumption, compute latency, and safety constraints to optimize …
VALO: A Versatile Anytime Framework for LiDAR-based Object Detection Deep Neural Networks
This work addresses the challenge of adapting dynamic deadline requirements for LiDAR
object detection deep neural networks (DNNs). The computing latency of object detection is …
object detection deep neural networks (DNNs). The computing latency of object detection is …
Genie: Smart ROS-based Caching for Connected Autonomous Robots
Despite the promising future of autonomous robots, several key issues currently remain that
can lead to compromised performance and safety. One such issue is latency, where we find …
can lead to compromised performance and safety. One such issue is latency, where we find …
Visual SLAM with 3D Gaussian Primitives and Depth Priors Enabling Novel View Synthesis
Conventional geometry-based SLAM systems lack dense 3D reconstruction capabilities
since their data association usually relies on feature correspondences. Additionally, learning …
since their data association usually relies on feature correspondences. Additionally, learning …
[PDF][PDF] Unified Local-Cloud Decision-Making via Reinforcement Learning
K Sengupta, Z Shangguan, S Bharadwaj, S Arora… - ecva.net
Embodied vision-based real-world systems, such as mobile robots, require a careful
balance between energy consumption, compute latency, and safety constraints to optimize …
balance between energy consumption, compute latency, and safety constraints to optimize …