Efficient Computing

Flexible VAD-PVAD Transition: A Detachable PVAD Module for Dynamic Encoder RNN VAD Interspeech 2025 Focal Plane Visual Feature Generation and Matching on a Pixel Processor Array ICCV 2025 From KAN to GR-KAN: Advancing Speech Enhancement with KAN-Based Methodology Interspeech 2025 GradQ-ViT: Robust and Efficient Gradient Quantization for Vision Transformers AAAI 2025 ImagePiece: Content-aware Re-tokenization for Efficient Image Recognition AAAI 2025 LAqua: Laplacian Pyramids for Aquatic Segmentation (Student Abstract) AAAI 2025 LightL2S: Ultra-Low Complexity Lip-to-Speech Synthesis for Multi-Speaker Scenarios Interspeech 2025 LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025 LSNet: See Large, Focus Small CVPR 2025 MEET: Towards Memory-Efficient Temporal Sparse Deep Neural Networks CVPR 2025 MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025 Motion-adaptive Transformer for Event-based Image Deblurring AAAI 2025 NGPU-LM: GPU-Accelerated N-Gram Language Model for Context-Biasing in Greedy ASR Decoding Interspeech 2025 Online AV-CrossNet: a Causal and Efficient Audiovisual System for Speech Enhancement and Target Speaker Extraction Interspeech 2025 Plug-and-Play Versatile Compressed Video Enhancement CVPR 2025 PolGS: Polarimetric Gaussian Splatting for Fast Reflective Surface Reconstruction ICCV 2025 Principles of Visual Tokens for Efficient Video Understanding ICCV 2025 Q-TempFusion: Quantization-Aware Temporal Multi-Sensor Fusion on Bird's-Eye View Representation WACV 2025 RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone WACV 2025 RefVSR++: Exploiting Reference Inputs for Reference-Based Video Super-Resolution WACV 2025 Rethinking Token Reduction with Parameter-Efficient Fine-Tuning in ViT for Pixel-Level Tasks CVPR 2025 Self-Aligning Depth-Regularized Radiance Fields for Asynchronous RGB-D Sequences WACV 2025 Simultaneous Masked and Unmasked Decoding with Speculative Decoding Masking for Fast ASR without Accuracy Loss Interspeech 2025 Sparse Structure Exploration and Re-optimization for Vision Transformer UAI 2025 SpiralMLP: A Lightweight Vision MLP Architecture WACV 2025