Risultati della ricerca - decoding ((Algorithmsics OR (algorithm OR algorithm)) OR (algorithm OR algorithmssics))

Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification di Wang, Jikai, Tian, Zhenxu, Li, Juntao, Xia, Qingrong, Duan, Xinyu, Wang, Zhefeng, Huai, Baoxing, Zhang, Min

Sommario: “... costs. In this paper, we present a training-free alignment-augmented speculative decoding algorithm. We...”
Testo

BDD2Seq: Enabling Scalable Reversible-Circuit Synthesis via Graph-to-Sequence Learning di Miao, Mingkai, Tang, Jianheng, Hu, Guangyu, Zhang, Hongce

Sommario: “... with a Pointer-Network decoder and Diverse Beam Search to predict high-quality orderings. By treating...”
Testo

Kascade: A Practical Sparse Attention Method for Long-Context LLM Inference di Deshmukh, Dhruv, Goyal, Saurabh, Kwatra, Nipun, Ramjee, Ramachandran

Sommario: “... are selected algorithmically, via a dynamic-programming objective that maximizes cross-layer similarity over a...”
Testo

Backpropagation-Free Test-Time Adaptation for Lightweight EEG-Based Brain-Computer Interfaces di Li, Siyang, Ouyang, Jiayi, Cui, Zhenyao, Wang, Ziwei, Jia, Tianwang, Wan, Feng, Wu, Dongrui

Sommario: “... deployment of decoding algorithms for EEG-based BCI. ...”
Testo

CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs di He, Yicheng, Zhao, Zheng, Kaiyu, Zhou, Dai, Bryan, Fu, Jie, Yang, Yonghui

Sommario: “... is to investigate whether the model's neural dynamics encode internally decodable signals that are predictive...”
Testo

CompleteRXN: Toward Completing Open Chemical Reaction Databases di Vogel, Gabriel, Noordsij, Minouk, Pidko, Evgeny, Weber, Jana M.

Sommario: “... baselines, including a novel encoder-decoder reaction completion model with constrained decoding...”
Testo

Manifold Learning by Mixture Models of VAEs for Inverse Problems di Alberti, Giovanni S., Hertrich, Johannes, Santacesaria, Matteo, Sciutto, Silvia

Sommario: “... of variational autoencoders. Here, every encoder-decoder pair represents one chart of a manifold. We propose a...”
Testo

The domain wall color code di Tiurev, Konstantin, Pesah, Arthur, Derks, Peter-Jan H. S., Roffe, Joschka, Eisert, Jens, Kesselring, Markus S., Reiner, Jan-Michael

Sommario: “... restriction decoder based on a matching algorithm. The proposed code is identified as a comparably resource...”
Testo

Toward distortion-aware change detection in realistic scenarios di Zhao, Yitao, Li, Heng-Chao, Liu, Nanqing, Wang, Rui

Sommario: “... systems. Geometric distortion caused by coordinate shifting remains a thorny issue for CD algorithms...”
Testo

EEND-M2F: Masked-attention mask transformers for speaker diarization di Härkönen, Marc, Broughton, Samuel J., Samarakoon, Lahiru

Sommario: “... of transformer decoders, in which irrelevant frames are explicitly masked from the cross attention using...”
Testo

Event-based Asynchronous HDR Imaging by Temporal Incident Light Modulation di Wu, Yuliang, Tan, Ganchao, Chen, Jinze, Zhai, Wei, Cao, Yang, Zha, Zheng-Jun

Sommario: “..., thereby triggering the pixel-independent event streams. The HDR image is subsequently decoded from...”
Testo

Recurrent Drafter for Fast Speculative Decoding in Large Language Models di Cheng, Yunfei, Zhang, Aonan, Zhang, Xuanyu, Wang, Chong, Wang, Yi

Sommario: “...We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves...”
Testo

Adapting to Covariate Shift in Real-time by Encoding Trees with Motion Equations di Foong, Tham Yik, Zhang, Heng, Yuan, Mao Po, Vargas, Danilo Vasconcellos

Sommario: “... Xenovert, an adaptive algorithm that can dynamically adapt to changes in input distribution. It is a...”
Testo

Exploring and Improving Drafts in Blockwise Parallel Decoding di Kim, Taehyeon, Suresh, Ananda Theertha, Papineni, Kishore, Riley, Michael, Kumar, Sanjiv, Benton, Adrian

Sommario: “... hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding...”
Testo

TK-Planes: Tiered K-Planes with High Dimensional Feature Vectors for Dynamic UAV-based Scenes di Maxey, Christopher, Choi, Jaehoon, Lee, Yonghan, Lee, Hyungtae, Manocha, Dinesh, Kwon, Heesung

Sommario: “... Field (NeRF), wherein our algorithm stores a set of tiered feature vectors. The tiered feature vectors...”
Testo

Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient di Li, Yang, Zhao, Feifei, Zhao, Dongcheng, Zeng, Yi

Sommario: “... direct training of SNNs for various applications. The surrogate gradient (SG) algorithm has recently...”
Testo

Open-Source Conversational AI with SpeechBrain 1.0 di Ravanelli, Mirco, Parcollet, Titouan, Moumen, Adel, de Langen, Sylvain, Subakan, Cem, Plantinga, Peter, Wang, Yingzhi, Mousavi, Pooneh, Della Libera, Luca, Ploujnikov, Artem, Paissan, Francesco, Borra, Davide, Zaiem, Salah, Zhao, Zeyu, Zhang, Shucong, Karakasidis, Georgios, Yeh, Sung-Lin, Champion, Pierre, Rouhe, Aku, Braun, Rudolf, Mai, Florian, Zuluaga-Gomez, Juan, Mousavi, Seyed Mahed, Nautsch, Andreas, Nguyen, Ha, Liu, Xuechen, Sagar, Sangeet, Duret, Jarod, Mdhaffar, Salima, Laperriere, Gaelle, Rouvier, Mickael, De Mori, Renato, Esteve, Yannick

Sommario: “... models and the complete "recipes" of code and algorithms required for training them. This paper presents...”
Testo

Menichetti's nonassociative $G$-crossed product algebras and Menichetti codes di Pumpluen, Susanne

Sommario: “... of algebra they display symmetric and cyclic properties which promise efficient decoding algorithms. Well...”
Testo

Joint Beam Scheduling and Resource Allocation for Flexible RSMA-aided Near-Field Communications di Zhou, Jiasi, Zhou, Cong, Mao, Yijie, Tellambura, Chintha

Sommario: “... is proposed to efficiently manage interference, which carefully selects a subset of legacy users to decode...”
Testo

Numerical Pruning for Efficient Autoregressive Models di Shen, Xuan, Song, Zhao, Zhou, Yufa, Chen, Bo, Liu, Jing, Zhang, Ruiyi, Rossi, Ryan A., Tan, Hao, Yu, Tong, Chen, Xiang, Zhou, Yufan, Sun, Tong, Zhao, Pu, Wang, Yanzhi, Gu, Jiuxiang

Sommario: “... on compressing decoder-only transformer-based autoregressive models through structural weight pruning to improve...”
Testo