inference acceleration

Accelerating LLM Inference Throughput via Asynchronous KV Cache Prefetching AAAI 2026 AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation CVPR 2026 Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration CVPR 2026 An Empirical Study of Speculative Decoding for Small Language Models EACL 2026 APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention ACL 2026 ApET: Approximation-Error Guided Token Compression for Efficient VLMs CVPR 2026 AVGGT: Rethinking Global Attention for Accelerating VGGT CVPR 2026 Beyond Fixed Formulas: Data-Driven Linear Predictor for Efficient Diffusion Models CVPR 2026 CasMoE: A Cascaded Framework for Efficient MoE Inference on Resource-constrained Devices AAAI 2026 CommitMoE: Efficient Fallback-Free MoE Inference with Offloading Under GPU Memory Constraints AAAI 2026 ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification ACL 2026 CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit ACL 2026 D2Cache: Second-Order Delta Caching for Higher Video Diffusion Acceleration CVPR 2026 D3ToM: Decider-Guided Dynamic Token Merging for Accelerating Diffusion MLLMs AAAI 2026 DIAA: A Decoding-Efficient Inference Acceleration Approach for On-Device Large Language Models AAAI 2026 EVTP-IVS: Effective Visual Token Pruning For Unifying Instruction Visual Segmentation In Multi-Modal Large Language Models WACV 2026 FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters CVPR 2026 FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation CVPR 2026 Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing ACL 2026 Forecast Then Calibrate: Feature Caching as ODE for Efficient Diffusion Transformers AAAI 2026 Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Diffusion Transformers CVPR 2026 From Inheritance to Saturation: Disentangling the Evolution of Visual Redundancy for Architecture-Aware MLLM Inference Acceleration ACL 2026 Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models AAAI 2026 HALO: Hardware-Aware Quantization with Low Critical-Path-Delay Weights for LLM Acceleration AAAI 2026 Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling AAAI 2026