Efficient Computing

GR-Gauge: Cost-efficient Training Configuration By Gauging the Gradient Redundancy CVPR 2026 Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence ACL 2026 Harvesting Sub-Microsecond CXL Memory Stalls with LiteSwitch OSDI 2026 HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference ACL 2026 HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding ACL 2026 HeSS: Head Sensitivity Score for Sparsity Redistribution in VGGT CVPR 2026 HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference ACL 2026 Heterogeneity at Hyperscale: Characterization and Scheduling of Large Production AI Clusters at Alibaba (Operational Systems) OSDI 2026 HeteroSpec: Leveraging Contextual Heterogeneity for Efficient Speculative Decoding ACL 2026 High-Level Semantics and Low-Level Features Fusion for Multi-Scale Object Detection in Dynamic Construction Environments WACV 2026 HuoziIME: An On-Device LLM-Enhanced Input Method for Deep Personalization ACL 2026 Hybrid Token Compression for Vision-Language Models CVPR 2026 IMPACT: Importance-Aware Activation Space Reconstruction ACL 2026 InferenceDynamics: Adaptive LLM Routing through Structured Capability and Knowledge Profiling ACL 2026 InTrain: Intrinsic Trainability for Zero-Cost Neural Architecture Search CVPR 2026 Jakiro: Boosting Speculative Decoding via Decoupled MoE ACL 2026 Kairox: Adaptive GPU-CPU Hybrid LLM Inference via Online Neuron Balancing OSDI 2026 Latent-Condensed Transformer for Efficient Long Context Modeling ACL 2026 LatentGate: Low-Latency Semantic Routing via Frozen-Backbone Probing of Small Language Models ACL 2026 Layer-Wise High-Impact Parameter Ratio Optimization in Post-Training Quantization for Large Language Models ACL 2026 LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning ACL 2026 LazyVAR: Accelerating Visual Autoregressive Models via Scale-wise Token Pruning and Parallel Group Decoding CVPR 2026 LBLLM: Lightweight Binarization of Large Language Models via Three-Stage Distillation ACL 2026 Learning Quantized Continuous Controllers for Integer Hardware L4DC 2026 Learning Shortcut Models for Efficient Recursive Reasoning ACL 2026