inference efficiency

Byte Latent Transformer: Patches Scale Better Than Tokens ACL 2025 CENTAUR: Bridging the Impossible Trinity of Privacy, Efficiency, and Performance in Privacy-Preserving Transformer Inference ACL 2025 Constrained Decoding with Speculative Lookaheads NAACL 2025 Conversational SimulMT: Efficient Simultaneous Translation with Large Language Models ACL 2025 COSEE: Consistency-Oriented Signal-Based Early Exiting via Calibrated Sample Weighting Mechanism AAAI 2025 Cost-Optimal Grouped-Query Attention for Long-Context Modeling EMNLP 2025 CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models EMNLP 2025 DAST: Difficulty-Adaptive Slow-Thinking for Large Reasoning Models EMNLP 2025 Decoupled Multi-Predictor Optimization for Inference-Efficient Model Tuning ICCV 2025 DLP: Dynamic Layerwise Pruning in Large Language Models ICML 2025 DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads ICLR 2025 DyCoke: Dynamic Compression of Tokens for Fast Video Large Language Models CVPR 2025 EasyInv: Toward Fast and Better DDIM Inversion ICML 2025 Efficient but Vulnerable: Benchmarking and Defending LLM Batch Prompting Attack ACL 2025 Efficient Inference for Large Language Models –Algorithm, Model, and System EMNLP 2025 Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments EMNLP 2025 Enhancing RAG Efficiency with Adaptive Context Compression EMNLP 2025 Ensembles of Low-Rank Expert Adapters ICLR 2025 ETA: Efficiency through Thinking Ahead, A Dual Approach to Self-Driving with Large Models ICCV 2025 Faster and Better LLMs via Latency-Aware Test-Time Scaling EMNLP 2025 Faster Parameter-Efficient Tuning with Token Redundancy Reduction CVPR 2025 FlashBack: Efficient Retrieval-Augmented Language Modeling for Fast Inference ACL 2025 FlexiDiT: Your Diffusion Transformer Can Easily Generate High-Quality Samples with Less Compute CVPR 2025 FLRC: Fine-grained Low-Rank Compressor for Efficient LLM Inference EMNLP 2025 FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point ACL 2025