Efficient Computing

Online Detection of Changes in Moment--Based Projections: When to Retrain Deep Learners or Update Portfolios? JMLR 2026 QuietPrune: Query-Guided Early Token Pruning for Vision-Language Models CVPR 2026 Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability UAI 2026 Saliency-Driven Token Merging for Vision Transformers CVPR 2026 SegMo: Co-Designing Content-Aware Sparsity and Locally-Cohesive Segment Parallelism for Efficient VLM Inference CVPR 2026 Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage ACL 2026 SGI: Structured 2D Gaussians for Efficient and Compact Large Image Representation CVPR 2026 Sparse Checkpointing for Fast and Reliable MoE Training NSDI 2026 Speeding Up the Learning of 3D Gaussians with Much Shorter Gaussian Lists CVPR 2026 SpikeTrack: High-performance and Energy-efficient Event-Based Object Tracking with Spiking Neural Network CVPR 2026 SURF: Signature-Retained Fast Video Generation CVPR 2026 TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model CVPR 2026 Vista-LLM: Decoupled Query-Guided Visual Token Pruning for Efficient Long-Video Large Language Models ACL 2026 5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks CVPR 2025 Accelerate Parallelizable Reasoning via Parallel Decoding within One Sequence EMNLP 2025 Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Interspeech 2025 ActiveGAMER: Active GAussian Mapping through Efficient Rendering CVPR 2025 Adaptive Dual-domain Learning for Underwater Image Enhancement AAAI 2025 Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency CVPR 2025 AIQViT: Architecture-Informed Post-Training Quantization for Vision Transformers AAAI 2025 All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising CVPR 2025 An Effective Training Framework for Light-Weight Automatic Speech Recognition Models Interspeech 2025 APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers CVPR 2025 Assessing the Performance and Efficiency of Mamba ASR in Low-Resource Scenarios Interspeech 2025 AtomNet: Designing Tiny Models from Operators Under Extreme MCU Constraints AAAI 2025