Efficient Computing

Small Encoders Can Rival Large Decoders in Detecting Groundedness ACL 2025 Small Language Models in the Real World: Insights from Industrial Text Classification ACL 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 SMEC:Rethinking Matryoshka Representation Learning for Retrieval Embedding Compression EMNLP 2025 SMMF: Square-Matricized Momentum Factorization for Memory-Efficient Optimization AAAI 2025 SmolDocling: An ultra-compact vision-language model for end-to-end multi-modal document conversion ICCV 2025 SnapGen: Taming High-Resolution Text-to-Image Models for Mobile Devices with Efficient Architectures and Training CVPR 2025 SnapGen-V: Generating a Five-Second Video within Five Seconds on a Mobile Device CVPR 2025 SoftMatcha: A Soft and Fast Pattern Matcher for Billion-Scale Corpus Searches ICLR 2025 SOGS: Second-Order Anchor for Advanced 3D Gaussian Splatting CVPR 2025 SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression AAAI 2025 SolEval: Benchmarking Large Language Models for Repository-level Solidity Smart Contract Generation EMNLP 2025 Solving Differential Equations with Constrained Learning ICLR 2025 Sorbet: A Neuromorphic Hardware-Compatible Transformer-Based Spiking Language Model ICML 2025 Soundwave: Less is More for Speech-Text Alignment in LLMs ACL 2025 SPA-BENCH: A COMPREHENSIVE BENCHMARK FOR SMARTPHONE AGENT EVALUATION ICLR 2025 SPAM: Spike-Aware Adam with Momentum Reset for Stable LLM Training ICLR 2025 SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference ICML 2025 Sparse Learning for State Space Models on Mobile ICLR 2025 SparseMM: Head Sparsity Emerges from Visual Concept Responses in MLLMs ICCV 2025 Sparse Video-Gen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity ICML 2025 SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference ICCV 2025 SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference ICML 2025