model acceleration

Accelerating Autoregressive Video Diffusion via History-Guided Cache and Residual Correction CVPR 2026 AdaSpec: Adaptive Multilingual Speculative Decoding with Self-Synthesized Language-Aware Training and Vocabulary Simplification AAAI 2026 Co-Me: Confidence Guided Token Merging for Visual Geometric Transformers CVPR 2026 DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models AAAI 2026 DiffBench Meets DiffAgent: End-to-End LLM-Driven Diffusion Acceleration Code Generation AAAI 2026 PCFormer: Accelerating Privacy-preserving Transformer Inference by Partition and Combination AAAI 2026 ProCache: Constraint-Aware Feature Caching with Selective Computation for Diffusion Transformer Acceleration AAAI 2026 ResCa: Residual Caching for Diffusion Transformers Acceleration CVPR 2026 Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios AAAI 2026 Sparrow: Text-Anchored Window Attention with Visual-Semantic Glimpsing for Speculative Decoding in Video LLMs ACL 2026 Steering Pretrained Drafters During Speculative Decoding AAAI 2026 Trimming the Fat: Redundancy-Aware Acceleration Framework for DGNNs AAAI 2026 Accelerating Adaptive Retrieval Augmented Generation via Instruction-Driven Representation Reduction of Retrieval Overlaps ACL 2025 Accelerating Dense LLMs via L0-regularized Mixture-of-Experts ACL 2025 Accelerating Diffusion Transformers with Token-wise Feature Caching ICLR 2025 Accelerating Diffusion Transformer via Gradient-Optimized Cache ICCV 2025 Accelerating Diffusion Transformer via Increment-Calibrated Caching with Channel-Aware Singular Value Decomposition CVPR 2025 Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025 A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training CVPR 2025 A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs CVPR 2025 Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration CVPR 2025 CLaSp: In-Context Layer Skip for Self-Speculative Decoding ACL 2025 Does Acceleration Cause Hidden Instability in Vision Language Models? Uncovering Instance-Level Divergence Through a Large-Scale Empirical Study EMNLP 2025 EffiVLM-BENCH: A Comprehensive Benchmark for Evaluating Training-Free Acceleration in Large Vision-Language Models ACL 2025 FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality ICLR 2025