model acceleration

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning ICCV 2025 Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration ICCV 2025 FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures AAAI 2025 From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers ICCV 2025 LazyDiT: Lazy Learning for the Acceleration of Diffusion Transformers AAAI 2025 LazyMAR: Accelerating Masked Autoregressive Models via Feature Caching ICCV 2025 Learning Few-Step Diffusion Models by Trajectory Distribution Matching ICCV 2025 Libra-Merging: Importance-redundancy and Pruning-merging Trade-off for Acceleration Plug-in in Large Vision-Language Model CVPR 2025 Mamba Drafters for Speculative Decoding EMNLP 2025 PLD+: Accelerating LLM Inference by Leveraging Language Model Artifacts NAACL 2025 PROXSPARSE: REGULARIZED LEARNING OF SEMI-STRUCTURED SPARSITY MASKS FOR PRETRAINED LLMS ICML 2025 SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device CVPR 2025 SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs ICCV 2025 SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation ACL 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 TCFG: Truncated Classifier-Free Guidance for Efficient and Scalable Text-to-Image Acceleration ICCV 2025 Cascade Speculative Drafting for Even Faster LLM Inference NeurIPS 2024 DeepCache: Accelerating Diffusion Models for Free CVPR 2024 Efficiency for Free: Ideal Data Are Transportable Representations NeurIPS 2024 FasterVD: On Acceleration of Video Diffusion Models IJCAI 2024 FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner NeurIPS 2024 Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting NeurIPS 2024 SpecHub: Provable Acceleration to Multi-Draft Speculative Decoding EMNLP 2024 Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution NeurIPS 2024 Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters EMNLP 2024