Efficient Computing

Nixie: Efficient, Transparent Temporal Multiplexing for Consumer GPUs OSDI 2026 NuWa: Deriving Lightweight Class-Specific Vision Transformers for Edge Devices CVPR 2026 OCP: Outlier-Centric Probing for Dynamic Structured Pruning of LLMs ACL 2026 OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data CVPR 2026 Online Detection of Changes in Moment--Based Projections: When to Retrain Deep Learners or Update Portfolios? JMLR 2026 OS-Fed: One Snapshot Is All You Need CVPR 2026 ParallelVLM: Lossless Video-LLM Acceleration with Visual Alignment Aware Parallel Speculative Decoding CVPR 2026 Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited Model Capacity CVPR 2026 PDTrim: Targeted Pruning for Prefill-Decode Disaggregation in Inference ACL 2026 Peek2: Regex-free Byte-level Byte-Pair Encoding Pretokenizer for LLM Inference on Edge Devices ACL 2026 Phantora: Maximizing Code Reuse in Simulation-based Machine Learning System Performance Estimation NSDI 2026 PHOTON: Hierarchical Autoregressive Modeling for Lightspeed and Memory-Efficient Language Generation ACL 2026 Polymorphic Universal Transformer ACL 2026 PoseAdapt: Sustainable Human Pose Estimation via Continual Learning Benchmarks and Toolkit WACV 2026 Prime Once, then Reprogram Locally: An Efficient Alternative to Black-Box Service Model Adaptation CVPR 2026 PRISM: Video Dataset Condensation with Progressive Refinement and Insertion for Sparse Motion CVPR 2026 Profiling-Free Mixed-Precision Quantization for MoE LLMs via Fuzzy Rule Interpolation ACL 2026 qTPU: Hybrid Tensor Networks for Quantum-Classical Acceleration OSDI 2026 Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization CVPR 2026 Question Tells You Where the Answer Is: Intention-aware Long-Context KV Cache Compression ACL 2026 QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer CVPR 2026 RADAR: Risk-Aware Distilled Adaptive Routing for Efficient Short-Form Video Platform Ecosystem Governance ACL 2026 Read As Human: Compressing Context via Parallelizable Close Reading and Skimming ACL 2026 REAL: REtrieval-reAsoning and Logic-constructed Attention Behaviors for Long-Context KV Cache Compression ACL 2026 Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses CVPR 2026