Efficient Computing

Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism ACL 2026 Downscaling Intelligence: Exploring Perception and Reasoning Bottlenecks in Small Multimodal Models CVPR 2026 DPAR: Dynamic Patchification for Efficient Autoregressive Visual Generation CVPR 2026 DS-ATGO: Dual-Stage Synergistic Learning via Forward Adaptive Threshold and Backward Gradient Optimization for Spiking Neural Networks AAAI 2026 DSFlash: Comprehensive Panoptic Scene Graph Generation in Realtime CVPR 2026 Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression ACL 2026 DUET-VLM: Dual stage Unified Efficient Token reduction for VLM Training and Inference CVPR 2026 E$^2$-SCI: Elastic Edge-Cloud Speculative Decoding via Credit Inertia CVPR 2026 EarlyTom: Early Token Compression Completes Fast Video Understanding CVPR 2026 ECHO: Efficient KV Cache Offloading with Lossless Prefetching for Serving Native Sparse Attention LLMs OSDI 2026 EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving ACL 2026 EDSD: Entropy-Driven Design for Faster Speculative Decoding ACL 2026 Efficient Encoder-Free Fourier-based 3D Large Multimodal Model CVPR 2026 Efficient Learned Data Compression via Dual-Stream Feature Decoupling ACL 2026 EfficientLLM: Unified Pruning-Aware Pretraining for Auto-Designed Compact Language Models ACL 2026 Efficient Process Reward Modeling via Contrastive Mutual Information ACL 2026 Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices CVPR 2026 Enabling AI Network Cross-Layer Design and Operations with Arcadia: A Simulation Platform at Scale NSDI 2026 EQUIP: EQUivariant preserving In-Place updates for Efficient Token Pruning ACL 2026 EquivPruner: Boosting Efficiency and Quality in LLM-Based Search via Action Pruning ACL 2026 EROICA: Online Performance Troubleshooting for Large-scale Model Training NSDI 2026 EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation CVPR 2026 Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment CVPR 2026 Expert Calibration Lens for Pruning Mixture of Experts ACL 2026 Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction CVPR 2026