inference efficiency

Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 StitchLLM: Serving LLMs, One Block at a Time ACL 2025 Streaming Video Question-Answering with In-context Video KV-Cache Retrieval ICLR 2025 Streamlining the Collaborative Chain of Models into A Single Forward Pass in Generation-Based Tasks ACL 2025 TableKV: KV Cache Compression for In-Context Table Processing ACL 2025 TACO-RL: Task Aware Prompt Compression Optimization with Reinforcement Learning ACL 2025 TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models AAAI 2025 Temporal Separation with Entropy Regularization for Knowledge Distillation in Spiking Neural Networks CVPR 2025 Thinking with DistilQwen: A Tale of Four Distilled Reasoning and Reward Model Series EMNLP 2025 ThinK: Thinner Key Cache by Query-Driven Pruning ICLR 2025 Thought calibration: Efficient and confident test-time scaling EMNLP 2025 Token Cropr: Faster ViTs for Quite a Few Tasks CVPR 2025 Towards Economical Inference: Enabling DeepSeek’s Multi-Head Latent Attention in Any Transformer-based LLMs ACL 2025 Training Free Exponential Context Extension via Cascading KV Cache ICLR 2025 Tree-Structured Non-Autoregressive Decoding for Sequence-to-Sequence Text Generation EMNLP 2025 TTD-SQL: Tree-Guided Token Decoding for Efficient and Schema-Aware SQL Generation EMNLP 2025 UniICL: An Efficient ICL Framework Unifying Compression, Selection, and Generation ACL 2025 VFlowOpt: A Token Pruning Framework for LMMs with Visual Information Flow-Guided Optimization ICCV 2025 VisualRWKV: Exploring Recurrent Neural Networks for Visual Language Models COLING 2025 zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025 Adaptive Depth Networks with Skippable Sub-Paths NeurIPS 2024 Anchor-based Large Language Models ACL 2024 Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models CVPR 2024 BilevelPruning: Unified Dynamic and Static Channel Pruning for Convolutional Neural Networks CVPR 2024 Block Transformer: Global-to-Local Language Modeling for Fast Inference NeurIPS 2024