论文解读
UMo: Unified Sparse Motion Modeling for Real-Time Co-Speech Avatars
语音合成 | 5.5/10
高效推理
论文解读
Keep What Audio Cannot Say: Context-Preserving Token Pruning for Omni-LLMs
音视频 | 7.0/10
论文解读
Encoding and Decoding Temporal Signals with Spiking Bandpass Wavelets
音频编码 | 7.0/10
论文解读
Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers
Adaptive Regularization for Sparsity Control in Bregman-Based Optimizers
论文解读
Pro-KLShampoo: Projected KL-Shampoo with Whitening Recovered by Orthogonalization
大语言模型 | 7.5/10
论文解读
保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端
📄 保留高维 XLS-R 特征时单层 KAN 能否以更少参数替代复杂后端 会议论文 ID：conference:icassp:2026:icassp-arnumber:11460320