Trending Research
CAI: An Open, Bug Bounty-Ready Cybersecurity AI
By 2028 most cybersecurity actions will be autonomous, with humans teleoperating.
Cryptography and Security
Muyan-TTS: A Trainable Text-to-Speech Model Optimized for Podcast Scenarios with a $50K Budget
Additionally, there is no publicly available TTS model specifically optimized for podcast scenarios, which are in high demand for voice interaction applications.
Sound Audio and Speech Processing
OCTOPINF: Workload-Aware Inference Serving for Edge Video Analytics
securade/hub
•
•
OCTOPINF tackles the unique challenges of dynamic edge environments through fine-grained resource allocation, adaptive batching, and workload balancing between edge devices and servers.
Distributed, Parallel, and Cluster Computing
One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
We introduce UniRig, a novel, unified framework for automatic skeletal rigging that leverages the power of large autoregressive models and a bone-point cross-attention mechanism to generate both high-quality skeletons and skinning weights.
Graphics
Ground-Optimized 4D Radar-Inertial Odometry via Continuous Velocity Integration using Gaussian Process
This paper presents two novel improvements beyond the existing radar-inertial odometry: ground-optimized noise filtering and continuous velocity preintegration.
Robotics
Think2Drive: Efficient Reinforcement Learning by Thinking in Latent World Model for Quasi-Realistic Autonomous Driving (in CARLA-v2)
As a result, Think2Drive is able to run in an expert-level proficiency in CARLA v2 within 3 days of training on a single A6000 GPU, and to our best knowledge, so far there is no reported success (100\% route completion)on CARLA v2.
Robotics
NEST: Self-supervised Fast Conformer as All-purpose Seasoning to Speech Processing Tasks
NVIDIA/NeMo
•
•
Self-supervised learning has been proved to benefit a wide range of speech processing tasks, such as speech recognition/translation, speaker verification and diarization, etc.
Sound Audio and Speech Processing
Real-Time LiDAR Point Cloud Compression and Transmission for Resource-constrained Robots
In this paper, we propose a novel point cloud compression and transmission framework for resource-constrained robotic applications, called RCPCC.
Robotics
INTELLECT-1 Technical Report
In this report, we introduce INTELLECT-1, the first 10 billion parameter language model collaboratively trained across the globe, demonstrating that large-scale model training is no longer confined to large corporations but can be achieved through a distributed, community-driven approach.
Distributed, Parallel, and Cluster Computing
HiFi-SR: A Unified Generative Transformer-Convolutional Adversarial Network for High-Fidelity Speech Super-Resolution
modelscope/ClearerVoice-Studio
•
•
However, existing SR methods that typically rely on independently trained and concatenated networks may lead to inconsistent representations and poor speech quality, especially in out-of-domain scenarios.
Sound Audio and Speech Processing
