Efficient Computing

Reducing Token Redundancy in LVLMs: A Systematic Review of Token Pruning Methods ACL 2026 ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs ACL 2026 Region-Adaptive Sampling for Diffusion Transformers CVPR 2026 Remembrall: Leaning into Memory for Accurate Video Analytics on System-on-Chip GPUs NSDI 2026 Residual Koopman Spectral Profiling for Predicting and Preventing Transformer Training Instability UAI 2026 Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression ACL 2026 Rethinking SNN Online Training and Deployment: Gradient-Coherent Learning via Hybrid-Driven LIF Model CVPR 2026 Rethinking Token Reduction for Large Vision-Language Models CVPR 2026 Reusable Experiences: Latent Routing and Modular Composition in LLMs ACL 2026 Revisiting Multimodal KV Cache Compression: A Frequency-Domain-Guided Outlier-KV-Aware Approach CVPR 2026 River-LLM: Large Language Model Seamless Exit Based on KV Share ACL 2026 RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment ACL 2026 Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection ACL 2026 RRAtention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference ACL 2026 S2O: Early Stopping for Sparse Attention via Online Permutation ACL 2026 Scalable Feature Matching via State Space Modeling and Sparse Correlation CVPR 2026 SCOPE: Boosting LLM Efficiency with Scoped Position Encoding ACL 2026 SCoRe: Salience-Coverage Reduction for Vision Token Pruning in Vision-Language Models CVPR 2026 SCVQ: Sparse-Compensated Vector Quantization for Large Language Models ACL 2026 Seele: A Unified Acceleration Framework for Real-Time Gaussian Splatting on Mobile Devices CVPR 2026 Semantically Comprehensive Token Pruning in LVLMs via Maximizing Concept Coverage ACL 2026 ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production NSDI 2026 Simple Is Better: Multiplication May Be All You Need for LLM Request Scheduling OSDI 2026 Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance CVPR 2026 SJD-PAC: Accelerating Speculative Jacobi Decoding via Proactive Drafting and Adaptive Continuation CVPR 2026