latency optimization

Alloc-MoE: Budget-Aware Expert Activation Allocation for Efficient Mixture-of-Experts Inference ACL 2026 AnyPro: Preference-Preserving Anycast Optimization based on Strategic AS-Path Prepending NSDI 2026 CacheCatalyst: Enhancing Web Caching for the Latency-Constrained Internet NSDI 2026 Hierarchical Policy Optimization for Simultaneous Translation of Unbounded Speech ACL 2026 SLATE: Service Layer Traffic Engineering NSDI 2026 SpecAgent: A Speculative Retrieval and Forecasting Agent for Code Completion ACL 2026 Achieving Wire-Latency Storage Systems by Exploiting Hardware ACKs NSDI 2025 Efficient Direct-Connect Topologies for Collective Communications NSDI 2025 Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025 Efficient Many-Shot In-Context Learning with Dynamic Block-Sparse Attention ACL 2025 eTran: Extensible Kernel Transport with eBPF NSDI 2025 Faster and Better LLMs via Latency-Aware Test-Time Scaling EMNLP 2025 High-level Programming for Application Networks NSDI 2025 Kamino: Efficient VM Allocation at Scale with Latency-Driven Cache-Aware Scheduling OSDI 2025 Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation AAAI 2025 LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025 MDP: Multidimensional Vision Model Pruning with Latency Constraint CVPR 2025 MixLLM: Dynamic Routing in Mixed Large Language Models NAACL 2025 MoDification: Mixture of Depths Made Easy NAACL 2025 Pruning One More Token is Enough: Leveraging Latency-Workload Non-Linearities for Vision Transformers on the Edge WACV 2025 QuantCache: Adaptive Importance-Guided Quantization with Hierarchical Latent and Layer Caching for Video Generation ICCV 2025 RecStream: Graph-aware Stream Management for Concurrent Recommendation Model Online Serving COLING 2025 SimulPL: Aligning Human Preferences in Simultaneous Machine Translation ICLR 2025 Tooth: Toward Optimal Balance of Video QoE and Redundancy Cost by Fine-Grained FEC in Cloud Gaming Streaming NSDI 2025 TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text EMNLP 2025