Výsledky vyhledávání - Theory of computation → Data structures design and analysis

Supply Of Mathematics For Machine Learning, Theory Performance Of Electical Machines, Utilization Of Electrical Energy Traction, Electrical Machine Design, Irrigation Engg Hydraulic Structure, Power System Analysis Stability, Database System Concepts, A F

Získat plný text

DuQTTA: Dual Quantized Tensor-Train Adaptation with Decoupling Magnitude-Direction for Efficient Fine-Tuning of LLMs Autor Dong, Haoyan, Chen, Hai-Bao, Chang, Jingjing, Yang, Yixin, Gao, Ziyang, Ji, Zhigang, Wang, Runsheng, Huang, Ru

“…Recent parameter-efficient fine-tuning (PEFT) techniques have enabled large language models (LLMs) to be efficiently fine-tuned for specific tasks, while…”
Získat plný text

MILLION: MasterIng Long-Context LLM Inference Via Outlier-Immunized KV Product QuaNtization Autor Wang, Zongwu, Xu, Peng, Liu, Fangxin, Hu, Yiwei, Sun, Qingxiao, Li, Gezi, Li, Cheng, Wang, Xuan, Jiang, Li, Guan, Haibing

“… KV cache mechanism alleviates this issue by storing pre-computed data, but introduces memory requirements that scale linearly with context length, hindering efficient LLM deployment…”
Získat plný text

NDSEARCH: Accelerating Graph-Traversal-Based Approximate Nearest Neighbor Search through Near Data Processing Autor Wang, Yitu, Li, Shiyu, Zheng, Qilin, Song, Linghao, Li, Zongwang, Chang, Andrew, Li, Hai lHelenr, Chen, Yiran

“…Approximate nearest neighbor search (ANNS) is a key retrieval technique for vector database and many data center applications, such as person re-identification and recommendation systems…”
Získat plný text

Faster and Stronger Lossless Compression with Optimized Autoregressive Framework Autor Mao, Yu, Li, Jingzong, Cui, Yufei, Xue, Jason Chun

“…Neural AutoRegressive (AR) framework has been applied in general-purpose lossless compression recently to improve compression performance. However, this paper…”
Získat plný text

ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression Autor Liu, Guangda, Li, Chengwei, Zhao, Jieru, Zhang, Chenqi, Guo, Minyi

“…) cache and increased latency due to extensive memory accesses. Recent works have proposed compressing KV cache to approximate computation, but these methods either…”
Získat plný text

SumPA: Efficient Pattern-Centric Graph Mining with Pattern Abstraction Autor Gui, Chuangyi, Liao, Xiaofei, Zheng, Long, Yao, Pengcheng, Wang, Qinggang, Jin, Hai

“…Graph mining aims to explore interesting structural information of a graph. Pattern-centric systems typically transform a generic-purpose graph mining problem…”
Získat plný text

PISA: Efficient Precision-Slice Framework for LLMs with Adaptive Numerical Type Autor Yang, Ning, Wang, Zongwu, Sun, Qingxiao, Lu, Liqiang, Liu, Fangxin

“…Large language models (LLMs) have transformed numerous AI applications, with on-device deployment becoming increasingly important for reducing cloud computing…”
Získat plný text

SNAPPIX: Efficient-Coding-Inspired In-Sensor Compression for Edge Vision Autor Lin, Weikai, Ma, Tianrui, Boloor, Adith, Feng, Yu, Xing, Ruofan, Zhang, Xuan, Zhu, Yuhao

“…Energy-efficient image acquisition on the edge is crucial for enabling remote sensing applications where the sensor node has weak compute capabilities and must transmit data to a remote server/cloud for processing…”
Získat plný text

Easz: An Agile Transformer-based Image Compression Framework for Resource-constrained IoTs Autor Mao, Yu, Li, Jingzong, Wang, Jun, Xu, Hong, Kuo, Tei-Wei, Guan, Nan, Xue, Chun Jason

“…Neural image compression, necessary in various machine-to-machine communication scenarios, suffers from its heavy encode-decode structures and inflexibility in switching between different compression levels…”
Získat plný text

GraphMini: Accelerating Graph Pattern Matching Using Auxiliary Graphs Autor Liu, Juelin, Polisetty, Sandeep, Guan, Hui, Serafini, Marco

“… This paper explores for the first time how to proactively prune graphs to speed up graph pattern matching by leveraging the structure of the query pattern and the input graph…”
Získat plný text

KVO-LLM: Boosting Long-Context Generation Throughput for Batched LLM Inference Autor Li, Zhenyu, Lyu, Dongxu, Wang, Gang, Chen, Yuzhou, Chen, Liyan, Li, Wenjie, Jiang, Jianfei, Sun, Yanan, He, Guanghui

“…With the widespread deployment of long-context large language models (LLMs), efficient and high-quality generation is becoming increasingly important. Modern…”
Získat plný text

Dryadic: Flexible and Fast Graph Pattern Matching at Scale Autor Mawhirter, Daniel, Reinehr, Samuel, Han, Wei, Fields, Noah, Claver, Miles, Holmes, Connor, McClurg, Jedidiah, Liu, Tongping, Wu, Bo

“…Graph pattern matching searches a data graph for all instances of one or more query patterns…”
Získat plný text

Processing-In-Hierarchical-Memory Architecture for Billion-Scale Approximate Nearest Neighbor Search Autor Zhu, Zhenhua, Liu, Jun, Dai, Guohao, Zeng, Shulin, Li, Bing, Yang, Huazhong, Wang, Yu

“… Because of the irregular and large-volume data access, existing CPU-based systems suffer from heavy data movements when dealing with graph-based ANNS algorithms…”
Získat plný text

One Automaton to Rule Them All: Beyond Multiple Regular Expressions Execution Autor Cicolini, Luisa, Carloni, Filippo, Santambrogio, Marco D., Conficconi, Davide

“… analysis in bioinformatics. Yet, due to their intrinsic data-dependence characteristics, REs represent a complex computational kernel, and numerous solutions investigate pattern-matching efficiency in different directions…”
Získat plný text

Seprox: Sequence-based Approximations for Compressing Ultra-Low Precision Deep Neural Networks Autor Parvathy, Aradhana Mohan, Krithivasan, Sarada, Sen, Sanchari, Raghunathan, Anand

“…Compression techniques such as quantization and pruning are indispensable for deploying state-of-the-art Deep Neural Networks (DNNs) on resource-constrained…”
Získat plný text

On The Efficiency of Sparse-Tiled Tensor Graph Processing For Low Memory Usage Autor Cipolletta, Antonio, Calimera, Andrea

“… Even though many data-driven compression pipelines have proven their efficacy, this work shows there is still room for optimization at the intersection with compute-oriented optimizations…”
Získat plný text

ICCAD-2016 CAD contest in Non-exact Projective NPNP Boolean Matching and benchmark suite Autor Chi-An Wu, Chih-Jen Hsu, Kei-Yong Khoo

“… Instead of basic Boolean matching, Non-exact Projective NPNP Boolean Matching allows to match two designs by not only negating and permuting inputs/outputs but also merging them or binding constants to inputs…”
Získat plný text

Late Breaking Results: COPPER: Computation Obfuscation by Producing Permutations for Encoding Randomly Autor Hutto, Kevin, Mooney, Vincent

“… Capable adversaries can intercept a device to recover the data in memory, including results of performed sensitive computations…”
Získat plný text

CUSZ-i: High-Ratio Scientific Lossy Compression on GPUs with Optimized Multi-Level Interpolation Autor Liu, Jinyang, Tian, Jiannan, Wu, Shixun, Di, Sheng, Zhang, Boyuan, Underwood, Robert, Huang, Yafan, Huang, Jiajun, Zhao, Kai, Li, Guanpeng, Tao, Dingwen, Chen, Zizhong, Cappello, Franck

“…Error-bounded lossy compression is a critical technique for significantly reducing scientific data volumes…”
Získat plný text