- Rotary GPU: Exploring Local Execution Paths for Large Mixture-of-Experts Models Under Limited GPU Memory
2026/05/27 by Myeong Jun Jo, MYEOUNGJUN JO · 7 voices · 1 citation
Computer Science · #Big Data and Digital Economy #Component (thermodynamics) #Distributed and Parallel Computing Systems #Execution model #Key (lock) #Laptop #Parallel Computing and Optimization Techniques #Throughput #Work (physics) #cs.AR #cs.DC #cs.PF
- LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding
2026/05/26 by Shihao Wang, Shilong Liu, Yuanguo Kuang +10 · 1 voice · 2 citations
Computer Science · #Advanced Neural Network Applications #Bottleneck #Coherence (philosophical gambling strategy) #Decoding methods #Domain Adaptation and Few-Shot Learning #Inference #Multimodal Machine Learning Applications #Scalability #Sequential decoding #Throughput #cs.AI #cs.CV #cs.LG #cs.RO
- VeriCache: Turning Lossy KV Cache into Lossless LLM Inference
2026/05/17 by Jiayi Yao, Samuel Shen, Kuntai Du +7 · 1 voice · 1 citation
Computer Science · #Advanced Data Storage Technologies #Cache #Cache algorithms #Cache pollution #Context (archaeology) #Decoding methods #Logic, programming, and type systems #Lossless compression #Overhead (engineering) #Page cache #Parallel Computing and Optimization Techniques #Throughput #cs.AR #cs.LG
- Silicon Showdown: Performance, Efficiency, and Ecosystem Barriers in Consumer-Grade LLM Inference
2026/05/01 by Abdurrahman Javat, Kazakov, Allan, Allan Kazakov · 1 voice
Computer Science · #Advanced Neural Network Applications #Big Data and Digital Economy #Efficient energy use #Inference #Latency (audio) #Parallel Computing and Optimization Techniques #Quantization (signal processing) #Scaling #Throughput #cs.AI #cs.AR #cs.PF
- Computing FFTs at Target Precision Using Lower-Precision FFTs
2026/03/31 by Shota Kawakami, Daisuke Takahashi · 1 voice
Computer Science · #Computation #Convolution (computer science) #Cryptography and Residue Arithmetic #Digital Filter Design and Implementation #Discrete Fourier transform (general) #Fast Fourier transform #Matrix (chemical analysis) #Modulo operation #Numerical Methods and Algorithms #Scheme (mathematics) #Throughput #Upper and lower bounds #cs.MS
- AIRA2: Overcoming Bottlenecks in AI Research Agents
2026/03/27 by Karen Hambardzumyan, Nicolas Baldwin, Edan Toledo +24 · 2 voices
Computer Science · #Advanced Neural Network Applications #Asynchronous communication #Bottleneck #Component (thermodynamics) #Debugging #Generalization #Limiting #Machine Learning and Data Classification #Parallel Computing and Optimization Techniques #Protocol (science) #Queue #Scope (computer science) #Throughput #cs.AI
- Open-source modular field-programmable gate array system for two-photon mesoscope enabling multiarea, multidepth neural activity recording and lifetime imaging
2026/03/03 by Riichiro Hira, Fumiya Imamura, Hiroto Imamura +14 · 1 voice · 1 citation
Engineering · Materials Science · Neuroscience · #Advanced Memory and Neural Computing #Application-specific integrated circuit #Field-programmable gate array #Gate array #Medical imaging #Modular design #Modularity (biology) #Photochromic and Fluorescence Chemistry #Photoreceptor and optogenetics research #Raster scan #Software #Throughput
- Super-LoRa: Enhancing LoRa Throughput via Payload Superposition
2025/04/16 by Salah Abdeljabar, Abdeljabar, Salah, Mohamed‐Slim Alouini +1 · 1 citation
Computer Science · Engineering · #Advanced Wireless Communication Technologies #Age of Information Optimization #Data transmission #FOS: Electrical engineering #IoT Networks and Protocols #Payload (computing) #Robustness (evolution) #Signal Processing (eess.SP) #Superposition principle #Throughput #Transmission (telecommunications) #Transmitter #electronic engineering #information engineering
- APAR: LLMs Can Do Auto-Parallel Auto-Regressive Decoding
2024/01/12 by M. Liu, Liu, Mingdao, Aohan Zeng +9 · 9 citations
Computer Science · #Algorithm #Cache #Computation and Language (cs.CL) #Computer science #Computer security #Decoding methods #FOS: Computer and information sciences #Key (lock) #Latency (audio) #Natural Language Processing Techniques #Parallel computing #Real-time computing #Software deployment #Speech Recognition and Synthesis #Speedup #Telecommunications #Throughput #Topic Modeling #Wireless
- FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU
2023/03/13 by Ying Sheng, Sheng, Ying, Lianmin Zheng +25 · 2 voices · 153 citations
Computer Science · Engineering · Materials Science · #Algorithm #Artificial intelligence #Benchmark (surveying) #Cache #Computation #Computer science #Ferroelectric and Negative Capacitance Devices #Inference #Latency (audio) #Machine Learning in Materials Science #Operating system #Parallel computing #Throughput #Topic Modeling #cs.AI #cs.LG #cs.PF
- A Tightly Coupled Bi-Level Coordination Framework for CAVs at Road Intersections
2023/02/07 by Donglin Li, Tingting Zhang, Li, Donglin +11 · 2 citations
Engineering · #Artificial intelligence #Autonomous Vehicle Technology and Safety #Bottleneck #Computer network #Computer science #Distributed computing #Embedded system #Engineering #FOS: Computer and information sciences #Intersection (aeronautics) #Mathematical optimization #Operations research #Plan (archaeology) #Planner #Resource (disambiguation) #Robotics (cs.RO) #Throughput #Traffic control and management #Trajectory #Transport engineering #Vehicular Ad Hoc Networks (VANETs)
- EdgeMatrix: A Resources Redefined Edge-Cloud System for Prioritized Services
2022/03/20 by Yuanming Ren, Shihao Shen, Ren, Yuanming +10 · 1 citation
Computer Science · #Artificial intelligence #Cloud Computing and Resource Management #Cloud computing #Cluster analysis #Computer network #Computer science #Distributed #Distributed computing #Enhanced Data Rates for GSM Evolution #FOS: Computer and information sciences #IoT and Edge/Fog Computing #Networking and Internet Architecture (cs.NI) #Operating system #Orchestration #Parallel #Resource (disambiguation) #Resource allocation #Service (business) #Shared resource #Software-Defined Networks and 5G #TRACE (psycholinguistics) #Throughput #Wireless #and Cluster Computing (cs.DC) #cs.DC #cs.NI
- SPINN
2020/08/24 by Stefanos Laskaridis, Stylianos I. Venieris, Mario Almeida +3 · 3 citations
Computer Science · Mathematics · #Advanced Neural Network Applications #Age of Information Optimization #Artificial intelligence #Cloud computing #Computation offloading #Computer network #Computer science #Convolutional neural network #Distributed computing #Edge computing #Inference #IoT and Edge/Fog Computing #Latency (audio) #Mobile cloud computing #Mobile device #Operating system #Real-time computing #Server #Throughput #Wireless #cs.CV #cs.DC #cs.LG #stat.ML
- VASPKIT: A User-friendly Interface Facilitating High-throughput Computing and Analysis Using VASP Code
2019/08/31 by Vei Wang, Nan Xu, Jin-Cheng Liu +5 · 142 citations
Earth and Planetary Sciences · Materials Science · Physics and Astronomy · #Advanced Chemical Physics Studies #Code generation #Compiler #Computational science #Computer science #Data structure #Electronic and Structural Properties of Oxides #Executable #Fortran #Graphical user interface #High-pressure geophysics and materials #Interface (matter) #Operating system #Programming language #Python (programming language) #Scripting language #Throughput #User Friendly #User interface #cond-mat.mtrl-sci