Efficient Computing

Focal Plane Visual Feature Generation and Matching on a Pixel Processor Array ICCV 2025 FocusLLM: Precise Understanding of Long Context by Dynamic Condensing ACL 2025 Forget the Data and Fine-Tuning! Just Fold the Network to Compress ICLR 2025 Fork in the Road: Reflections and Optimizations for Cold Start Latency in Production Serverless Systems OSDI 2025 FPE2M2: Approaching Lossless and Efficient Quantization with Native Floating Point ACL 2025 FrameFusion: Combining Similarity and Importance for Video Token Reduction on Large Vision Language Models ICCV 2025 FreeCG: Free the Design Space of Clebsch-Gordan Transform for Machine Learning Force Fields ICLR 2025 FREE: Fast and Robust Vision Language Models with Early Exits ACL 2025 Free Lunch Enhancements for Multi-modal Crowd Counting CVPR 2025 FreeNet: Liberating Depth-Wise Separable Operations for Building Faster Mobile Vision Architectures AAAI 2025 FreqTS: Frequency-Aware Token Selection for Accelerating Diffusion Models AAAI 2025 Frequency-Aligned Knowledge Distillation for Lightweight Spatiotemporal Forecasting ICCV 2025 Frequency Dynamic Convolution for Dense Image Prediction CVPR 2025 From Address Blocks to Authorized Prefixes: Redesigning RPKI ROV with a Hierarchical Hashing Scheme for Fast and Memory-Efficient Validation NSDI 2025 From Decoupling to Adaptive Transformation: a Wider Optimization Space for PTQ ICLR 2025 From Long to Lean: Performance-aware and Adaptive Chain-of-Thought Compression via Multi-round Refinement EMNLP 2025 From Low Rank Gradient Subspace Stabilization to Low-Rank Weights: Observations, Theories, and Applications ICML 2025 From Objectives to Questions: A Planning-based Framework for Educational Mathematical Question Generation ACL 2025 From PEFT to DEFT: Parameter Efficient Finetuning for Reducing Activation Density in Transformers AAAI 2025 From Remembering to Metacognition: Do Existing Benchmarks Accurately Evaluate LLMs? EMNLP 2025 From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers ICCV 2025 From Understanding to Generation: An Efficient Shortcut for Evaluating Language Models EMNLP 2025 From Weight-Based to State-Based Fine-Tuning: Further Memory Reduction on LoRA with Parallel Control ICML 2025 Frozen Layers: Memory-efficient Many-fidelity Hyperparameter Optimization AutoML 2025 FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling ACL 2025