inference acceleration

SSSD: Simply-Scalable Speculative Decoding ACL 2026 SURF: Signature-Retained Fast Video Generation CVPR 2026 SwiftEP: Accelerating MoE Inference with Buffer Fusion and TMA Offloading NSDI 2026 TABED: Test-Time Adaptive Ensemble Drafting for Robust Speculative Decoding in LVLMs EACL 2026 Talon: Breaking the Synchronization Barrier in Speculative Decoding with Hybrid Model-based and Retrieve-based Drafting AAAI 2026 TAP: A Token-Adaptive Predictor Framework for Training-Free Diffusion Acceleration CVPR 2026 Test-time Sparsity for Extreme Fast Action Diffusion CVPR 2026 TimeRipples: Accelerating vDiTs by Understanding the Spatio-Temporal Correlations in Latent Space CVPR 2026 TokenTiming: A Dynamic Alignment Method for Universal Speculative Decoding Model Pairs ACL 2026 VDE: Training-Free Accelerating Rectified Flow Model via Velocity Decomposition and Estimation CVPR 2026 VVS: Accelerating Speculative Decoding for Visual Autoregressive Generation via Partial Verification Skipping CVPR 2026 WaveEx: Accelerating Flow Matching-based Speech Generation via Wavelet-guided Extrapolation AAAI 2026 When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs CVPR 2026 YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal CVPR 2026 ABQ-LLM: Arbitrary-Bit Quantized Inference Acceleration for Large Language Models AAAI 2025 Accelerated Test-Time Scaling with Model-Free Speculative Sampling EMNLP 2025 Accelerating Autoregressive Speech Synthesis Inference With Speech Speculative Decoding Interspeech 2025 Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding ICLR 2025 Accelerating Dense LLMs via L0-regularized Mixture-of-Experts ACL 2025 Accelerating Flow-Matching-Based Text-to-Speech via Empirically Pruned Step Sampling Interspeech 2025 Accelerating Inference of Retrieval-Augmented Generation via Sparse Context Selection ICLR 2025 Accurate Sublayer Pruning for Large Language Models by Exploiting Latency and Tunability Information IJCAI 2025 Adaptive Caching for Faster Video Generation with Diffusion Transformers ICCV 2025 Adaptive Guidance: Training-free Acceleration of Conditional Diffusion Models AAAI 2025 AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference AAAI 2025