Efficient Computing

LEASH: Adaptive Length Penalty and Reward Shaping for Efficient Large Reasoning Model ACL 2026 Libra: Flexible Request Partitioning and Scheduling for Serving Unbalanced and Dynamic LLM Workloads NSDI 2026 Lite Any Stereo: Efficient Zero-Shot Stereo Matching CVPR 2026 LLM-as-Scheduler: Agentic Workflow Dynamic Scheduling ACL 2026 LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval ACL 2026 LoPrune: Efficient Data Pruning for LoRA-Based Fine-Tuning of Vision Transformer CVPR 2026 LoPT: Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model ACL 2026 LS-ViT: Least-Squares Hessian Based Block Reconstruction for Low-Bit Post-Training Quantization of Vision Transformers CVPR 2026 MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference ACL 2026 MemFlow: A Lightweight Forward Memorizing Framework for Quick Domain Adaptive Feature Mapping CVPR 2026 Memory-Efficient Fine-Tuning Diffusion Transformers via Dynamic Patch Sampling and Block Skipping CVPR 2026 Memory-Efficient Structured Backpropagation for On-Device LLM Fine-Tuning ACL 2026 MeToM: Metadata-Guided Token Merging for Efficient Video LLMs CVPR 2026 MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe CVPR 2026 Mitigating Structural Knowledge Collapse in Domain-Specific LLMs via Morpheme-Aware KV-Aggregation ACL 2026 MixerCSeg: An Efficient Mixer Architecture for Crack Segmentation via Decoupled Mamba Attention CVPR 2026 MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts Models ACL 2026 MobileLLM-Flash: Latency-Guided On-Device LLM Design for Industry Scale Deployment ACL 2026 MoDES: Accelerating Mixture-of-Experts Multimodal Large Language Models via Dynamic Expert Skipping CVPR 2026 MSPT: Efficient Large-Scale Physical Modeling via Parallelized Multi-Scale Attention CVPR 2026 MTRouter: Cost-Aware Multi-Turn LLM Routing with History–Model Joint Embeddings ACL 2026 Multi-Scale Local Speculative Decoding for Image Generation CVPR 2026 Murakkab: Resource-Efficient Agentic Workflow Orchestration in Cloud Platforms OSDI 2026 MUR: Momentum Uncertainty guided Reasoning for Large Language Models ACL 2026 mVLM: A Vision Language Model for mNPUs CVPR 2026