Risultati della ricerca - (decoding OR (endedededededededededededededededededededededededecoding OR decoding)) algorithm

How Much Parallelism Is "Free"? A Principle of Near-Free Parallelism for Parallel Decoding di He, Minghua, Zhang, Lingzhe, Liu, Yuan, Zhou, Xiao, Liu, Aiwei

Sommario: “... single decode forward, but reported speedups conflate algorithmic token utilization with the system cost...”
Testo

Specialising and Analysing Instruction-Tuned and Byte-Level Language Models for Organic Reaction Prediction di Pang, Jiayun, Vulić, Ivan

Sommario: “... of (SMILES-oriented) pretraining, fine-tuning sample efficiency, and decoding algorithms at inference. Our...”
Testo

Efficient MoE Serving in the Memory-Bound Regime: Balance Activated Experts, Not Tokens di Yu, Yanpeng, Ma, Haiyue, Agarwal, Krish, Oswald, Nicolai, Huang, Qijing, Linsenmaier, Hugo, Mei, Chunhui, Zhao, Ritchie, Borkar, Ritika, Rouhani, Bita Darvish, Nellans, David, Krashinsky, Ronny, Khandelwal, Anurag

Sommario: “... processing is memory-bound - a common occurrence in MoE serving, especially in the decode phase. Our analysis...”
Testo

Coding for Gaussian Two-Way Channels: Linear and Learning-Based Approaches di Kim, Junghoon, Kim, Taejoon, Das, Anindya Bijoy, Hosseinalipour, Seyyedali, Love, David J., Brinton, Christopher G.

Sommario: “... reliability. We then propose an efficient algorithm for joint encoder/decoder design. For learning-based...”
Testo

Iterative Neural Rollback Chase-Pyndiah Decoding di Artemasov, Dmitry, Nesterenkov, Oleg, Andreev, Kirill, Rybin, Pavel, Frolov, Alexey

Sommario: “...Iterative decoding is essential in modern communication systems, especially optical communications...”
Testo

Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes di Mi, Xiangjun, Mueller, Frank

Sommario: “...Quantum error correction (QEC) is essential for scalable quantum computing, yet decoding errors via...”
Testo

FairBatching: Fairness-Aware Batch Formation for LLM Inference di Lyu, Hongtao, Liu, Boyue, Wu, Mingyu, Chen, Haibo

Sommario: “... violations. Its fair and dynamic batch formation algorithm breaks away from the decode-prioritizing paradigm...”
Testo

Guess-Verify-Refine: Data-Aware Top-K for Sparse-Attention Decoding on Blackwell via Temporal Correlation di Cheng, Long, Zhao, Ritchie, Liu, Timmy, Li, Mindy, Qiao, Xianjie, Duan, Kefeng, Chen, Yu-Jung, Chen, Xiaoming, Rouhani, Bita Darvish, Yang, June

Sommario: “...Sparse-attention decoders rely on exact Top-K selection to choose the most important key-value...”
Testo

VeriCache: Turning Lossy KV Cache into Lossless LLM Inference di Yao, Jiayi, Shen, Samuel, Du, Kuntai, Feng, Shaoting, Seo, Dongjoo, Zhang, Rui, Huang, Yuyang, Liu, Yuhan, Lu, Shan, Jiang, Junchen

Sommario: “... the high decoding throughput of a range of KV cache compression algorithms. VeriCache uses the compressed...”
Testo

Implementation and Optimization of HQC Decoding on NPU-Integrated Devices di Chau, Vu Minh, Kiet, Nguyen Ngoc, Minh, Pham Quang, Ngoc, Mai Xuan, Anh, Nguyen Duc, Ta, Hoang

Sommario: “...-based key-encapsulation mechanism, providing algorithmic diversity alongside lattice-based post-quantum...”
Testo

Towards Out-of-Distribution Detection in Vocoder Recognition via Latent Feature Reconstruction di Du, Renmingyue, Yao, Jixun, Kong, Qiuqiang, Cao, Yin

Sommario: “... it crucial to develop deepfake algorithm recognition. One significant aspect is out-of-distribution (OOD...”
Testo

Multivariate Decoded Quantum Interferometry for Weighted Optimization di Bu, Kaifeng, Gu, Weichen, Li, Xiang

Sommario: “...Decoded Quantum Interferometry (DQI) is a recently introduced quantum algorithm that reduces...”
Testo

Real-Time Neural Appearance Models di Zeltner, Tizian, Rousselle, Fabrice, Weidlich, Andrea, Clarberg, Petrik, Novák, Jan, Bitterli, Benedikt, Evans, Alex, Davidovič, Tomáš, Kallweit, Simon, Lefohn, Aaron

Sommario: “... reserved for offline use. This is achieved with a combination of algorithmic and system level innovations...”
Testo

Plato: Plan to Efficiently Decode for Large Language Model Inference di Jin, Shuowei, Liu, Xueshen, Wu, Yongji, Zheng, Haizhong, Zhang, Qingzhao, Prakash, Atul, Lentz, Matthew, Zhuo, Danyang, Qian, Feng, Mao, Z. Morley

Sommario: “..., but their inference incurs substantial computational and memory overhead. To improve efficiency, parallel decoding...”
Testo

Density Evolution Analysis of Generalized Low-density Parity-check Codes under a Posteriori Probability Decoder di Chang, Dongxu, Peng, Qingqing, Ma, Zhiming, Wang, Guanghui, Yin, Dawei

Sommario: “... posteriori probability (APP) decoder is analyzed. We explore the concentration, symmetry, and monotonicity...”
Testo

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast di Wu, Wenhao, Shao, Zishan, Cui, Kangning, Kim, Jinhee, Wang, Yixiao, Ye, Hancheng, Zhuo, Danyang, Chen, Yiran

Sommario: “... between prefill and autoregressive decode. We present FlashSVD v1.5, a unified inference runtime...”
Testo

Sequoia: Scalable, Robust, and Hardware-aware Speculative Decoding di Chen, Zhuoming, May, Avner, Svirschevski, Ruslan, Huang, Yuhsun, Ryabinin, Max, Jia, Zhihao, Chen, Beidi

Sommario: “... scalable, robust, and hardware-aware algorithm for speculative decoding. To attain better scalability...”
Testo

Symplectic Lattices and GKP Codes -- Simple Randomized Constructions from Cryptographic Lattices di Blömer, Johannes, Xiao, Yinzi, Raissi, Zahra, Soltan, Stanislaw

Sommario: “... a simple decoding algorithm that, for many parameter choices, experimentally yields decoding results...”
Testo

Optimal Proximity Gap for Folded Reed--Solomon Codes via Subspace Designs di Jeronimo, Fernando Granha, Liu, Lenny, Rajpal, Pranav

Sommario: “... on the Guruswami--Sudan list decoding algorithm for RS codes, which is guaranteed to work in the Johnson bound...”
Testo

Iterative Joint Detection of Kalman Filter and Channel Decoder for Sensor-to-Controller Link in Wireless Networked Control Systems di Piao, Jinnan, Li, Dong, Sun, Yiming, Li, Zhibo, Yang, Ming, Yu, Xueting

Sommario: “...In this letter, we propose an iterative joint detection algorithm of Kalman filter (KF) and channel...”
Testo