Efficient Computing

Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation CVPR 2025 SegResMamba: An Efficient Architecture for 3D Medical Image Segmentation MIDL 2025 Semantic Agreement Enables Efficient Open-Ended LLM Cascades EMNLP 2025 Sequence Accumulation and Beyond: Infinite Context Length on Single GPU and Large Clusters AAAI 2025 ShiftwiseConv: Small Convolutional Kernel with Large Kernel Effect CVPR 2025 Sketch Down the FLOPs: Towards Efficient Networks for Human Sketch CVPR 2025 Sketch-of-Thought: Efficient LLM Reasoning with Adaptive Cognitive-Inspired Sketching EMNLP 2025 SLoW: Select Low-frequency Words! Automatic Dictionary Selection for Translation on Large Language Models EMNLP 2025 SMamba: Sparse Mamba for Event-based Object Detection AAAI 2025 Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference ACL 2025 Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025 SMLE: Safe Machine Learning via Embedded Overapproximation AAAI 2025 SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer CVPR 2025 Sparse-to-Dense: A Free Lunch for Lossless Acceleration of Video Understanding in LLMs ACL 2025 SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks AAAI 2025 Spectral Scaling Laws in Language Models: emphHow Effectively Do Feed-Forward Networks Use Their Latent Space? EMNLP 2025 Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025 Spec-VLA: Speculative Decoding for Vision-Language-Action Models with Relaxed Acceptance EMNLP 2025 Spike2Former: Efficient Spiking Transformer for High-performance Image Segmentation AAAI 2025 SpikingSSMs: Learning Long Sequences with Sparse and Parallel Spiking State Space Models AAAI 2025 SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers ACL 2025 SPvR: Structured Pruning via Ranking UAI 2025 Squeezed Attention: Accelerating Long Context Length LLM Inference ACL 2025 Star with Bilinear Mapping CVPR 2025 State-offset Tuning: State-based Parameter-Efficient Fine-Tuning for State Space Models ACL 2025