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

Magnitude-Phase Dual-Path Speech Enhancement Network based on Self-Supervised Embedding and Perceptual Contrast Stretch Boosting di Mattursun, Alimjan, Wang, Liejun, Yu, Yinfeng, Ma, Chunyang

Sommario: “... starts by applying the perceptual contrast stretching (PCS) algorithm to enhance the magnitude-phase...”
Testo

HarmonySeg: Tubular Structure Segmentation with Deep-Shallow Feature Fusion and Growth-Suppression Balanced Loss di Huang, Yi, Zhang, Ke, Liu, Wei, Wang, Yuanyuan, Patel, Vishal M., Lu, Le, Han, Xu, Jin, Dakai, Yan, Ke

Sommario: “... exist in algorithm design when faced with diverse sizes, complex topologies, and (often) incomplete data...”
Testo

Full-Diversity Construction-D Lattices: Design and Decoding Perspective on Block-Fading Channels di Sadeghi, Maryam, Khodaiemehr, Hassan, Feng, Chen

Sommario: “... this, we develop an efficient decoding algorithm designed specifically for full-diversity Construction-D...”
Testo

Locate 3D: Real-World Object Localization via Self-Supervised Learning in 3D di Arnaud, Sergio, McVay, Paul, Martin, Ada, Majumdar, Arjun, Jatavallabhula, Krishna Murthy, Thomas, Phillip, Partsey, Ruslan, Dugas, Daniel, Gejji, Abha, Sax, Alexander, Berges, Vincent-Pierre, Henaff, Mikael, Jain, Ayush, Cao, Ang, Prasad, Ishita, Kalakrishnan, Mrinal, Rabbat, Michael, Ballas, Nicolas, Assran, Mido, Maksymets, Oleksandr, Rajeswaran, Aravind, Meier, Franziska

Sommario: “... and AR devices. Key to our approach is 3D-JEPA, a novel self-supervised learning (SSL) algorithm...”
Testo

Gone With the Bits: Revealing Racial Bias in Low-Rate Neural Compression for Facial Images di Qiu, Tian, Nichani, Arjun, Tadayontahmasebi, Rasta, Jeong, Haewon

Sommario: “... in neural compression algorithms by analyzing nine popular models and their variants. Through...”
Testo

Trellis Waveform Shaping for Sidelobe Reduction in Integrated Sensing and Communications: A Duality with PAPR Mitigation di Pu, Henglin, Li, Husheng, Han, Zhu, Poor, H. Vincent

Sommario: “... the PAPR. In this paper, inspired by PAPR reduction algorithms in OFDM, we employ trellis shaping in OFDM...”
Testo

Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors di Fang, Hao, Kong, Jiawei, Zhuang, Tianqu, Qiu, Yixiang, Gao, Kuofeng, Chen, Bin, Xia, Shu-Tao, Wang, Yaowei, Zhang, Min

Sommario: “... reduces when faced with advanced detection algorithms. To address this, we propose \textbf{Co}ntrastive...”
Testo

Toward Fully Neuromorphic Receivers for Ultra-Power Efficient Communications di Katsaros, George N., Nikitopoulos, Konstantinos

Sommario: “... efforts mainly focused on mapping isolated communication algorithms onto spiking networks, often...”
Testo

Multi-Spectral Gaussian Splatting with Neural Color Representation di Meyer, Lukas, Grün, Josef, Weiherer, Maximilian, Egger, Bernhard, Stamminger, Marc, Franke, Linus

Sommario: “... red, without any algorithmic changes. Unlike existing 3DGS-based frameworks that treat each modality...”
Testo

Onboard Mission Replanning for Adaptive Cooperative Multi-Robot Systems di Kwan, Elim, Qureshi, Rehman, Fletcher, Liam, Laganier, Colin, Nockles, Victoria, Walters, Richard

Sommario: “... communication links to centralised compute. Fast, on-board replanning algorithms are therefore needed to enhance...”
Testo

The complete weight distribution of a family of irreducible cyclic codes of dimension two di Vega, Gerardo, Hernández, Félix

Sommario: “... of linear codes are also important due to their efficient encoding and decoding algorithms. Because...”
Testo

TAG-WM: Tamper-Aware Generative Image Watermarking via Diffusion Inversion Sensitivity di Chen, Yuzhuo, Ma, Zehua, Fang, Han, Zhang, Weiming, Yu, Nenghai

Sommario: “.... The proposed method comprises four key modules: a dual-mark joint sampling (DMJS) algorithm for embedding...”
Testo

Weakly Supervised Intracranial Aneurysm Detection and Segmentation in MR angiography via Multi-task UNet with Vesselness Prior di Rainville, Erin, Rasoulian, Amirhossein, Rivaz, Hassan, Xiao, Yiming

Sommario: “... with voxel-wise expert annotations pose challenges for developing deep learning algorithms to address...”
Testo

Do GNN-based QEC Decoders Require Classical Knowledge? Evaluating the Efficacy of Knowledge Distillation from MWPM di Ikeda, Ryota

Sommario: “...The performance of decoders in Quantum Error Correction (QEC) is key to realizing practical quantum...”
Testo

Llasa+: Free Lunch for Accelerated and Streaming Llama-Based Speech Synthesis di Tian, Wenjie, Zhu, Xinfa, Xie, Hanke, Ye, Zhen, Xue, Wei, Xie, Lei

Sommario: “... caused by inaccurate MTP, we design a novel verification algorithm that leverages the frozen backbone...”
Testo

Towards Generalizable Learning Models for EEG-Based Identification of Pain Perception di Rezzouk, Mathis, Gagnon, Fabrice, Champagne, Alyson, Roy, Mathieu, Albouy, Philippe, Coll, Michel-Pierre, Subakan, Cem

Sommario: “... resilient, underscoring their potential for subject-invariant EEG decoding. Even though performance...”
Testo

Correctness-Guaranteed Code Generation via Constrained Decoding di Li, Lingxiao, Rahili, Salar, Zhao, Yiwei

Sommario: “... correctness for runtime-critical components. We present a constrained decoding algorithm for generating...”
Testo

CoCoA: Confidence and Context-Aware Adaptive Decoding for Resolving Knowledge Conflicts in Large Language Models di Khandelwal, Anant, Gupta, Manish, Agrawal, Puneet

Sommario: “... parametric memory and external context. Existing contrastive decoding methods tuned specifically to handle...”
Testo

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models di Wang, Yilin, Wang, Heng, Bai, Yuyang, Luo, Minnan

Sommario: “... parametric knowledge contradicts knowledge provided in the context. Previous works studied tuning, decoding...”
Testo

Controllable Generation of Implied Volatility Surfaces with Variational Autoencoders di Wang, Jing, Liu, Shuaiqiang, Vuik, Cornelis

Sommario: “... are quantified via regression at an anchor point and incorporated into the decoder to steer generation. Numerical...”
Testo