Trending Research
MossFormer2: Combining Transformer and RNN-Free Recurrent Network for Enhanced Time-Domain Monaural Speech Separation
modelscope/ClearerVoice-Studio
•
•
Instead of applying the recurrent neural networks (RNNs) that use traditional recurrent connections, we present a recurrent module based on a feedforward sequential memory network (FSMN), which is considered "RNN-free" recurrent network due to the ability to capture recurrent patterns without using recurrent connections.
Ranked #1 on
Speech Separation
on Libri2Mix
Speech Separation
Sound
Audio and Speech Processing
Fish-Speech: Leveraging Large Language Models for Advanced Multilingual Text-to-Speech Synthesis
Text-to-Speech (TTS) systems face ongoing challenges in processing complex linguistic features, handling polyphonic expressions, and producing natural-sounding multilingual speech - capabilities that are crucial for future AI applications.
Sound Audio and Speech Processing
Automated Unit Test Improvement using Large Language Models at Meta
This paper describes Meta's TestGen-LLM tool, which uses LLMs to automatically improve existing human-written tests.
Software Engineering
Better Write Amplification for Streaming Data Processing
Many current applications have to perform data processing in a streaming fashion.
Distributed, Parallel, and Cluster Computing
SuperVINS: A Real-Time Visual-Inertial SLAM Framework for Challenging Imaging Conditions
Therefore, SuperVINS, developed as an enhancement of VINS-Fusion, integrates the deep learning neural network model SuperPoint for feature point extraction and loop closure detection.
Robotics
Deterministic Parallel Fixpoint Computation
The de facto approach for computing the approximation of this fixpoint uses a sequential algorithm based on weak topological order (WTO).
Programming Languages
Empowering Robot Path Planning with Large Language Models: osmAG Map Topology & Hierarchy Comprehension with LLMs
Large Language Models (LLMs) have demonstrated great potential in robotic applications by providing essential general knowledge.
Robotics
Hierarchical Diffusion Policy: manipulation trajectory generation via contact guidance
dexin-wang/hierarchical_diffusion_policy
•
•
This paper proposes Hierarchical Diffusion Policy (HDP), a new imitation learning method of using objective contacts to guide the generation of robot trajectories.
Robotics
Multi-cam Multi-map Visual Inertial Localization: System, Validation and Dataset
To address these issues, we propose a multi-cam multi-map visual inertial localization system, which provides real-time, causal and drift-free position feedback to the robot control loop.
Robotics
SkiffOS: Minimal Cross-compiled Linux for Embedded Containers
Embedded Linux processors are increasingly used for real-time computing tasks such as robotics and Internet of Things (IoT).
Software Engineering Robotics
