Trending Research
Textoshop: Interactions Inspired by Drawing Software to Facilitate Text Editing
We explore how interactions inspired by drawing software can help edit text.
Human-Computer Interaction
Formalization of physics index notation in Lean 4
The physics community relies on index notation to effectively manipulate types of tensors.
Logic in Computer Science High Energy Physics - Phenomenology High Energy Physics - Theory
NavRL: Learning Safe Flight in Dynamic Environments
Zhefan-Xu/NavRL
•
•
Safe flight in dynamic environments requires unmanned aerial vehicles (UAVs) to make effective decisions when navigating cluttered spaces with moving obstacles.
Robotics
Stream-K: Work-centric Parallel Decomposition for Dense Matrix-Matrix Multiplication on the GPU
We introduce Stream-K, a work-centric parallelization of matrix multiplication (GEMM) and related computations in dense linear algebra.
Data Structures and Algorithms Distributed, Parallel, and Cluster Computing
AKF-LIO: LiDAR-Inertial Odometry with Gaussian Map by Adaptive Kalman Filter
Existing LiDAR-Inertial Odometry (LIO) systems typically use sensor-specific or environment-dependent measurement covariances during state estimation, leading to laborious parameter tuning and suboptimal performance in challenging conditions (e. g., sensor degeneracy and noisy observations).
Robotics
LCB-net: Long-Context Biasing for Audio-Visual Speech Recognition
alibaba-damo-academy/FunASR
•
•
The growing prevalence of online conferences and courses presents a new challenge in improving automatic speech recognition (ASR) with enriched textual information from video slides.
Sound Multimedia Audio and Speech Processing
HiFi-Codec: Group-residual Vector quantization for High Fidelity Audio Codec
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
A Survey on Trustworthy LLM Agents: Threats and Countermeasures
With the rapid evolution of Large Language Models (LLMs), LLM-based agents and Multi-agent Systems (MAS) have significantly expanded the capabilities of LLM ecosystems.
Multiagent Systems Computers and Society
Cornstarch: Distributed Multimodal Training Must Be Multimodality-Aware
Multimodal large language models (MLLMs) extend the capabilities of large language models (LLMs) by combining heterogeneous model architectures to handle diverse modalities like images and audio.
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
