脑机接口 / BCI - arXivDaily 专题

2403.15523 2024-10-15 q-bio.NC cs.AI cs.LG cs.SD eess.AS 54%

Towards auditory attention decoding with noise-tagging: A pilot study

H. A. Scheppink, S. Ahmadi, P. Desain, M. Tangermann, J. Thielen

专题命中其他BCI ：brain-computer interface(comments,journal_ref)；分类 q-bio.NC、cs.LG

Comments 6 pages, 2 figures, 9th Graz Brain-Computer Interface Conference 2024

Journal ref 9th Graz Brain-Computer Interface Conference (2024) 337-342

2607.27943 2026-07-31 cs.GR 新提交 50%

Compact Representation of Mipmapped SVBRDFs via Shared Gaussians

通过共享高斯函数实现带多级纹理滤波（mipmapped）的空间变化双向反射分布函数（SVBRDF）的紧凑表示

Fengdi Zhang, Haocheng Ren, Qing Luo, Yaqing Li, Jibing Lou, Hongwei Li

专题命中其他BCI ：neural decoding(abstract)

AI总结该研究提出GTC方法，通过共享2D高斯函数压缩带多级纹理滤波的SVBRDF纹理，相比ASTC实现更高重建质量与更低内存，支持随机访问和非神经解码，适用于实时渲染

2607.21132 2026-07-24 cs.SD 新提交 50%

Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness

研究用于神经编解码器鲁棒性的编解码器内部潜在音频水印

Zi Hu, Houmin Sun, Linxi Li, Yechen Wang, Liwei Jin, Carsten Maple, Ming Li

专题命中其他BCI ：neural decoding(abstract)

AI总结研究神经音频编解码器中用于鲁棒性的水印，将32位消息嵌入连续潜在表示，采用SEANet风格编码器 - 解码器等技术，表征水印载体移动时的权衡，在48kHz语音上提升了EnCodec - 24k比特准确率并降低了PESQ。

Comments 7 pages. Submitted to IEEE Spoken Language Technology Workshop (SLT)

2605.01790 2026-07-07 cs.SD cs.AI 版本更新 50%

Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation

Shao：将声学令牌语言模型扩展至高保真音乐生成

Jiafeng Liu, Yuanliang Dong, Hongjia Liu, Yuqing Cheng, Zhancheng Guo, Huijing Liang, Wenbo Zhan, Yuming Sun, Xiaobing Li, Feng Yu, Maosong Sun

机构 * Central Conservatory of Music（中央音乐学院）； Tsinghua University（清华大学）

专题命中其他BCI ：neural decoding(abstract)

AI总结该研究提出单一声学令牌层级内渐进建模音乐结构与保真度的框架，通过双阶段生成与混合注意力训练，无需异构空间即可实现高质量音乐生成。

2607.03165 2026-07-07 cs.CV 新提交 50%

Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness

用CLIP重新思考大脑解码：对抗鲁棒性的作用

Byeongseo Bok, Futa Waseda, Jun Liu, Isao Echizen

机构 * The Graduate University for Advanced Studies (SOKENDAI)（高等研究院（索邦大学））； National Institute of Informatics（国立情报学研究所）； The University of Tokyo（东京大学）

专题命中其他BCI ：neural decoding(abstract)

AI总结研究用CLIP进行大脑解码时，探讨对抗鲁棒表示能否改善神经解码。通过固定fMRI解码器，在不同任务和数据集上改变目标表示，发现此方法能提升任务性能及特征对齐，表明对抗鲁棒性可作为大脑解码有用标准。

Comments 20 pages, 10 figures

2606.13259 2026-06-12 physics.med-ph 新提交 50%

ffdas: Volumetric ultrasound reconstruction at warp speed

ffdas：超高速体积超声重建

Luuk Verhoef, Pieter Kruizinga

专题命中其他BCI ：brain-computer interface(abstract)

AI总结针对体积超快超声成像的计算瓶颈，提出三种GPU优化策略（对齐内存访问、混合精度存储、利用张量核心），实现128³体素网格千赫兹帧率重建，显著超越现有方法，支持实时术中脑成像和脑机接口。

2606.09922 2026-06-10 cs.IT cs.AI math.IT 新提交 50%

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

生物电信息论：探究人工智能下生物电信号的理论压缩极限

Jiawen Zou, Bo Yan

机构 * College of Computer Science and Artificial Intelligence（计算机科学与人工智能学院）； Shanghai Key Laboratory of Intelligent Information Processing（上海智能信息处理重点实验室）； Fudan University（复旦大学）

专题命中其他BCI ：brain-computer interface(abstract)

AI总结提出生物电压缩的三级层次框架，将压缩极限重构为模型和任务条件量，而非波形的固定属性。

2304.01844 2026-04-24 cs.AI 50%

Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning

Grid-SD2E：一种用于认知学习系统的通用网格反馈

Jingyi Feng, Chenming Zhang

机构 * Institute of Artificial Intelligence, School of Computer Science, Wuhan University（人工智能学院、计算机学院、武汉大学）

专题命中其他BCI ：neural decoding(abstract)

AI总结本文提出Grid-SD2E系统，结合网格模块与贝叶斯推理，构建交互自增强的认知系统，旨在解释人与环境的交互机制。

Comments 21 pages, 8 figures, 8 formulas

Journal ref Cogn Comput 18, 38 (2026)

2604.07855 2026-04-10 cs.AI 50%

Hidden Biases in Conditioning Autoregressive Models

自回归模型中隐藏的偏见

Francois Pachet, Pierre Roy

机构 * LIP6, Sorbonne Université（索邦大学计算机科学实验室LIP6）； Soundtrap

专题命中其他BCI ：neural decoding(abstract)

AI总结研究揭示了自回归模型在条件生成中存在隐藏的推理偏见，证明了精确解码在全局形式约束下计算上是不可行的。

Comments 9 pages

2603.04227 2026-03-05 cs.IR 50%

Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds

面向广告流多目标优化的约束感知生成重排

Chenfei Li, Hantao Zhao, Weixi Yao, Ruiming Huang, Rongrong Lu, Geng Tian, Dongying Kong

专题命中其他BCI ：neural decoding(abstract)

AI总结本文提出一种面向约束的生成重排框架，通过整合序列生成与奖励估计，提升广告流中多目标优化的效率与效果。

Comments 14 pages, 2 figures, 3 tables

2602.17011 2026-02-20 cs.MM 50%

CAFE: Channel-Autoregressive Factorized Encoding for Robust Biosignal Spatial Super-Resolution

CAFE: 通道自回归因子化编码用于鲁棒生物信号空间超分辨率

Hongjun Liu, Leyu Zhou, Zijianghao Yang, Rujun Han, Shitong Duan, Kuanjian Tang, Chao Yao

专题命中其他BCI ：neural decoding(abstract)

AI总结 CAFE通过自回归因子化编码实现生物信号空间超分辨率，利用几何对齐阶段逐步重建布线，提升低密度观测下的鲁棒性与重建性能。

2601.17711 2026-01-27 cs.SD cs.AI eess.AS 50%

CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays

CaSNet：基于压缩-发送网络的多设备语音增强模型用于分布式麦克风阵列

Chengqian Jiang, Jie Zhang, Haoyin Yan

机构 * NERC-SLIP, University of Science and Technology of China (USTC)（NERC-SLIP，中国科学技术大学）

专题命中其他BCI ：neural decoding(abstract)

AI总结 CaSNet是一种用于分布式麦克风阵列的压缩-发送网络，通过特征压缩和神经解码提升语音增强性能，减少带宽和能耗。

Comments this paper has been accept by ICASSP2026

2601.01339 2026-01-06 cs.CV 50%

Achieving Fine-grained Cross-modal Understanding through Brain-inspired Hierarchical Representation Learning

通过脑启发的分层表征学习实现细粒度跨模态理解

Weihang You, Hanqi Jiang, Yi Pan, Junhao Chen, Tianming Liu, Fei Dou

机构 * School of Computing, University of Georgia, Athens, GA, USA（计算学院，佐治亚大学，亚特兰大，GA，USA）

专题命中其他BCI ：neural decoding(abstract)

AI总结 NeuroAlign通过脑启发的分层表征学习，在fMRI-视频对齐中实现细粒度跨模态理解，提升跨模态检索性能。

2508.16642 2025-08-26 cs.CY 50%

AI as IA: The use and abuse of artificial intelligence (AI) for human enhancement through intellectual augmentation (IA)

Alexandre Erler, Vincent C. Müller

专题命中其他BCI ：brain-computer interface(abstract)

Journal ref (2023) in Marcello Ienca and Fabrice Jotterand (eds.), The Routledge Handbook of the Ethics of Human Enhancement (London: Routledge), 187-99

2508.02480 2025-08-05 cs.CV 50%

MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding

Wenwen Zeng, Yonghuang Wu, Yifan Chen, Xuan Xie, Chengqian Zhao, Feiyu Yin, Guoqing Wu, Jinhua Yu

专题命中其他BCI ：brain-computer interface(abstract)

2503.11167 2025-07-17 cs.CV cs.AI 50%

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

Haonan Wang, Qixiang Zhang, Lehan Wang, Xuanqi Huang, Xiaomeng Li

机构 * The Hong Kong University of Science and Technology（香港科技大学）

专题命中其他BCI ：brain-computer interface(abstract)

Comments Accepted by ICCV 2025, camera ready version

2506.14014 2025-06-18 q-bio.QM 50%

Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data

Laurence Freeman, Philip Shamash, Vinam Arora, Caswell Barry, Tiago Branco, Eva Dyer

专题命中其他BCI ：neural decoding(abstract)

2503.15978 2025-03-21 cs.CV 50%

A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli

Pengyu Liu, Guohua Dong, Dan Guo, Kun Li, Fengling Li, Xun Yang, Meng Wang, Xiaomin Ying

专题命中其他BCI ：brain-computer interface(abstract)

Comments 31 pages, 6 figures

2503.06118 2025-03-11 cs.CV 50%

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

Xuanyu Zhang, Jiarui Meng, Zhipei Xu, Shuzhou Yang, Yanmin Wu, Ronggang Wang, Jian Zhang

专题命中其他BCI ：neural decoding(abstract)

Comments Accepted by ICLR 2025

2503.05715 2025-03-11 cs.CY cs.AI 50%

The Butterfly Effect of Technology: How Various Factors accelerate or hinder the Arrival of Technological Singularity

Hooman Shababi

专题命中其他BCI ：brain-computer interface(abstract)

Comments 20 Pages, 0 Figures, 0 Tables

2502.10183 2025-02-17 cs.IT math.IT 50%

Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders

Ahmad Ismail, Raphaël Le Bidan, Elsa Dupraz, Charbel Abdel-Nour

专题命中其他BCI ：neural decoding(abstract)

Comments 7 pages, 8 figures. Accepted for publication at IEEE Int. Conf. on Machine Learning for Communications and Networking (ICMLCN) 2025. Companion datasets are available at https://ai4code.projects.labsticc.fr/software/

2402.16632 2024-10-23 cs.CL 50%

Domain Embeddings for Generating Complex Descriptions of Concepts in Italian Language

Alessandro Maisto

专题命中其他BCI ：neural decoding(abstract)

2409.20428 2024-10-01 cs.CL 50%

Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic Information

Runze Xia, Congchi Yin, Piji Li

专题命中其他BCI ：brain-computer interface(abstract)

Comments Accepted at Main Conference of EMNLP 2024

2409.17541 2024-09-27 cs.AR 50%

Swapping-Centric Neural Recording Systems

Muhammed Ugur, Raghavendra Pradyumna Pothukuchi, Abhishek Bhattacharjee

专题命中其他BCI ：neural interface(abstract)

Journal ref The 15th Annual Non-Volatile Memories Workshop (NVMW), March, 2024

2403.20022 2024-04-01 cs.CV 50%

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

Ruijie Quan, Wenguan Wang, Zhibo Tian, Fan Ma, Yi Yang

专题命中其他BCI ：brain-computer interface(abstract)

Comments Accepted to CVPR 2024

2403.14510 2024-03-22 cs.CE 50%

Universal Differential Equations as a Common Modeling Language for Neuroscience

Ahmed ElGazzar, Marcel van Gerven

专题命中其他BCI ：neural decoding(abstract)

Comments 23 pages, 3 figures

2402.18766 2024-03-06 cs.CL 50%

Advancing Generative AI for Portuguese with Open Decoder Gervásio PT*

Rodrigo Santos, João Silva, Luís Gomes, João Rodrigues, António Branco

专题命中其他BCI ：neural decoding(abstract)

2310.18998 2023-10-31 eess.SY cs.SY 50%

A 0.21-ps FOM Capacitor-Less Analog LDO with Dual-Range Load Current for Biomedical Applications

Yasemin Engur, Mahsa Shoaran

专题命中其他BCI ：neural interface(abstract)

2310.01854 2023-10-04 cs.AI cs.CL 50%

Fine-tuned vs. Prompt-tuned Supervised Representations: Which Better Account for Brain Language Representations?

Jingyuan Sun, Marie-Francine Moens

专题命中其他BCI ：neural decoding(abstract)

Comments IJCAI 2023

2210.06756 2023-03-31 cs.CV cs.AI cs.MM cs.NE 50%

Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features

Changde Du, Kaicheng Fu, Jinpeng Li, Huiguang He

专题命中其他BCI ：neural decoding(abstract)

Comments IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

1. 其他BCI 132 篇

Towards auditory attention decoding with noise-tagging: A pilot study

Compact Representation of Mipmapped SVBRDFs via Shared Gaussians

Investigating Codec-Internal Latent Audio Watermarking for Neural Codec Robustness

Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation

Rethinking Brain Decoding with CLIP: The Role of Adversarial Robustness

ffdas: Volumetric ultrasound reconstruction at warp speed

The Bioelectrical Information Theory: Investigating the theoretical compression limit of bioelectrical signals under artificial intelligence

Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning

Hidden Biases in Conditioning Autoregressive Models

Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds

CAFE: Channel-Autoregressive Factorized Encoding for Robust Biosignal Spatial Super-Resolution

CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays

Achieving Fine-grained Cross-modal Understanding through Brain-inspired Hierarchical Representation Learning

AI as IA: The use and abuse of artificial intelligence (AI) for human enhancement through intellectual augmentation (IA)

MindShot: Multi-Shot Video Reconstruction from fMRI with LLM Decoding

Neurons: Emulating the Human Visual Cortex Improves Fidelity and Interpretability in fMRI-to-Video Reconstruction

Beyond Black Boxes: Enhancing Interpretability of Transformers Trained on Neural Data

A Survey on fMRI-based Brain Decoding for Reconstructing Multimodal Stimuli

SecureGS: Boosting the Security and Fidelity of 3D Gaussian Splatting Steganography

The Butterfly Effect of Technology: How Various Factors accelerate or hinder the Arrival of Technological Singularity

Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders

Domain Embeddings for Generating Complex Descriptions of Concepts in Italian Language

Decoding the Echoes of Vision from fMRI: Memory Disentangling for Past Semantic Information

Swapping-Centric Neural Recording Systems

Psychometry: An Omnifit Model for Image Reconstruction from Human Brain Activity

Universal Differential Equations as a Common Modeling Language for Neuroscience

Advancing Generative AI for Portuguese with Open Decoder Gervásio PT*

A 0.21-ps FOM Capacitor-Less Analog LDO with Dual-Range Load Current for Biomedical Applications

Fine-tuned vs. Prompt-tuned Supervised Representations: Which Better Account for Brain Language Representations?

Decoding Visual Neural Representations by Multimodal Learning of Brain-Visual-Linguistic Features