Efficient Computing

Smarter, not Bigger: Fine-Tuned RAG-Enhanced LLMs for Automotive Hardware-in-the-Loop Testing ACL 2026 Soft Modality-Guided Expert Specialization in MoE-VLMs CVPR 2026 Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs ACL 2026 Sparse Checkpointing for Fast and Reliable MoE Training NSDI 2026 Sparse-LaViDa: Sparse Multimodal Discrete Diffusion Language Models CVPR 2026 SpecCache: Speculative KV Cache Reuse for Efficient RAG Serving ACL 2026 Speculative End-Turn Detector for Efficient Speech Chatbot Assistant ACL 2026 SpikeTrack: A Spike-driven Framework for Efficient Visual Tracking CVPR 2026 SSM-Aware Token-Efficient VMamba via Adaptive Patch Pruning and Merging for Person Re-Identification CVPR 2026 SSMRadNet : A Sample-wise State-Space Framework for Efficient and Ultra-Light Radar Segmentation and Object Detection WACV 2026 SSSD: Simply-Scalable Speculative Decoding ACL 2026 Stability Implies Redundancy: Delta Attention Selective Halting for Efficient Long-Context Prefilling ACL 2026 STAC: Plug-and-Play Spatio-Temporal Aware Cache Compression for Streaming 3D Reconstruction CVPR 2026 Step-GRPO: Internalizing Dynamic Early Exit for Efficient Reasoning ACL 2026 StreamingTOM: Streaming Token Compression for Efficient Video Understanding CVPR 2026 StriaTrace: Efficient Tracing and Diagnosis for Online LLM Inference (Operational Systems) OSDI 2026 SwiftEP: Accelerating MoE Inference with Buffer Fusion and TMA Offloading NSDI 2026 SYMI: Efficient Mixture-of-Experts Training via Model and Optimizer State Decoupling NSDI 2026 SYMPHONY: Enabling Compute-Memory Disaggregation in LLM Serving Systems NSDI 2026 TalkLoRA: Communication-Aware Mixture of Low-Rank Adaptation for Large Language Models ACL 2026 Task-Aware LLM Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios ACL 2026 TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts CVPR 2026 The Evolution of Thought: Tracking LLM Overthinking via Reasoning Dynamics Analysis ACL 2026 The Pitfalls of KV Cache Compression ACL 2026 Think Better, Not Longer: Token-Level Marginal Utility for Efficient Reasoning in Large Reasoning Models ACL 2026