Trending Research
Tightly Joining Positioning and Control for Trustworthy Unmanned Aerial Vehicles Based on Factor Graph Optimization in Urban Transportation
Given the fact that the system positioning and control are highly correlated with each other, for example, the system dynamics of the control can largely help with the positioning, this paper proposed a joint positioning and control method (JPCM) based on factor graph optimization (FGO), which combines sensors' measurements and control intention.
Robotics
Robust Multi-Modal Multi-LiDAR-Inertial Odometry and Mapping for Indoor Environments
Next, with pre-integrated IMU data, an undistortion module is applied to the LiDAR point cloud data.
Robotics
OpenAirLink: Reproducible Wireless Channel Emulation using Software Defined Radios
The emulator is implemented using a finite impulse response (FIR) filter.
Networking and Internet Architecture Signal Processing
Prompt-Enhanced Software Vulnerability Detection Using ChatGPT
This paper launches a study on the performance of software vulnerability detection using ChatGPT with different prompt designs.
Software Engineering
Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
coqui-ai/TTS
•
•
Several recent end-to-end text-to-speech (TTS) models enabling single-stage training and parallel sampling have been proposed, but their sample quality does not match that of two-stage TTS systems.
Sound Audio and Speech Processing
DB-GPT: Empowering Database Interactions with Private Large Language Models
Our extensive experiments and user studies confirm that DB-GPT represents a paradigm shift in database interactions, offering a more natural, efficient, and secure way to engage with data repositories.
Databases
HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec
lucidrains/vector-quantize-pytorch
•
•
Despite their usefulness, two challenges persist: (1) training these audio codec models can be difficult due to the lack of publicly available training processes and the need for large-scale data and GPUs; (2) achieving good reconstruction performance requires many codebooks, which increases the burden on generation models.
Sound Audio and Speech Processing
GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
intelligent-machine-learning/glake
•
•
Owing to the prohibitively large overhead (e. g., $10 \times$) of GPUs' native memory allocator, DNN frameworks like PyTorch and TensorFlow adopt a caching allocator that maintains a memory pool with a splitting mechanism for fast memory (de)allocation.
Distributed, Parallel, and Cluster Computing
Manu: A Cloud Native Vector Database Management System
In the past three years, through interaction with our 1200+ industry users, we have sketched a vision for the features that next-generation vector databases should have, which include long-term evolvability, tunable consistency, good elasticity, and high performance.
Databases
Goal-Driven Autonomous Exploration Through Deep Reinforcement Learning
reiniscimurs/DRL-robot-navigation
•
•
We develop a navigation system where this learned policy is integrated into a motion planning stack as the local navigation layer to move the robot between waypoints towards a global goal.
Robotics
