Trending Research
Improving the Performance of K-Means for Color Quantization
Color quantization is an important operation with many applications in graphics and image processing.
Graphics I.4.1
Is Your Wallet Snitching On You? An Analysis on the Privacy Implications of Web3
In this paper, we analyze the privacy implications that Web3 technologies such as decentralized applications and wallets have on users.
Cryptography and Security
CED: Consistent ensemble distillation for audio tagging
richermans/ced
•
•
Augmentation and knowledge distillation (KD) are well-established techniques employed in audio classification tasks, aimed at enhancing performance and reducing model sizes on the widely recognized Audioset (AS) benchmark.
Sound Audio and Speech Processing
Boosting Studies of Multi-Agent Reinforcement Learning on Google Research Football Environment: the Past, Present, and Future
jidiai/GRF_MARL
•
•
Even though Google Research Football (GRF) was initially benchmarked and studied as a single-agent environment in its original paper, recent years have witnessed an increasing focus on its multi-agent nature by researchers utilizing it as a testbed for Multi-Agent Reinforcement Learning (MARL).
Multiagent Systems
FC-Planner: A Skeleton-guided Planning Framework for Fast Aerial Coverage of Complex 3D Scenes
Based on SSD, a hierarchical planner effectively divides the large planning problem into independent sub-problems, enabling parallel planning for each subspace.
Robotics
RTLCoder: Outperforming GPT-3.5 in Design RTL Generation with Our Open-Source Dataset and Lightweight Solution
The automatic generation of RTL code (e. g., Verilog) using natural language instructions and large language models (LLMs) has attracted significant research interest recently.
Programming Languages Hardware Architecture
NeuPIMs: NPU-PIM Heterogeneous Acceleration for Batched LLM Inferencing
In batched processing, QKV generation and feed-forward networks involve compute-intensive matrix-matrix multiplications (GEMM), while multi-head attention requires bandwidth-heavy matrix-vector multiplications (GEMV).
Hardware Architecture
How Far Can We Go with Practical Function-Level Program Repair?
ghabix/srepair
•
•
Inspired by our findings, we propose an LLM-based function-level APR technique, namely SRepair, which adopts a dual-LLM framework to leverage the power of the auxiliary repair-relevant information for advancing the repair performance.
Software Engineering
InspectorRAGet: An Introspection Platform for RAG Evaluation
Large Language Models (LLM) have become a popular approach for implementing Retrieval Augmented Generation (RAG) systems, and a significant amount of effort has been spent on building good models and metrics.
Software Engineering Human-Computer Interaction
A Holistic Approach to Reactive Mobile Manipulation
We present the design and implementation of a taskable reactive mobile manipulation system.
Robotics
