inference latency

BILLY: Steering Large Language Models via Merging Persona Vectors for Creative Generation EACL 2026 EnViT: Enhancing the Performance of Early-Exit Vision Transformers via Exit-Aware Structured Dropout-Enabled Self-Distillation AAAI 2026 Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning CVPR 2026 HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models CVPR 2026 NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages AAAI 2026 Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving CVPR 2026 RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query Parallelism AAAI 2026 Rethinking Visual Token Reduction in LVLMs Under Cross-Modal Misalignment AAAI 2026 RoBSA: RoPE-based Blockwise Sparse Multi-head Latent Attention ACL 2026 ROSE: Rotate Your Large Language Model to See CVPR 2026 RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents ACL 2026 ShiftLUT: Spatial Shift Enhanced Look-Up Tables for Efficient Image Restoration CVPR 2026 Task-aware Block Pruning with Output Distribution Signals for Large Language Models EACL 2026 Unleash All Cores: Asymmetry-Aware Scalable DNN Inference on Mobile CPUs OSDI 2026 WikiCLIP: An Efficient Contrastive Baseline for Open-domain Visual Entity Recognition CVPR 2026 Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025 Auto-reconfiguration for Latency Minimization in CPU-based DNN Serving ICML 2025 BEEM: Boosting Performance of Early Exit DNNs using Multi-Exit Classifiers as Experts ICLR 2025 Block-Attention for Efficient Prefilling ICLR 2025 CateKV: On Sequential Consistency for Long-Context LLM Inference Acceleration ICML 2025 CATO: End-to-End Optimization of ML-Based Traffic Analysis Pipelines NSDI 2025 Does quantization affect models’ performance on long-context tasks? EMNLP 2025 EcoDoc: A Cost-Efficient Multimodal Document Processing System for Enterprises Using LLMs ACL 2025 Enhancing Acoustic-to-Articulatory Inversion with Multi-Target Pretraining for Low-Resource Settings Interspeech 2025 EXIT: Context-Aware Extractive Compression for Enhancing Retrieval-Augmented Generation ACL 2025