Efficient Computing

LowFormer: Hardware Efficient Design for Convolutional Transformer Backbones WACV 2025 Low-Hallucination and Efficient Coreference Resolution with LLMs EMNLP 2025 LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits ICML 2025 Low-Rank Thinning ICML 2025 Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation COLING 2025 LP Data Pipeline: Lightweight, Purpose-driven Data Pipeline for Large Language Models EMNLP 2025 LRA-QViT: Integrating Low-Rank Approximation and Quantization for Robust and Efficient Vision Transformers ICML 2025 LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices NAACL 2025 LSDC: An Efficient and Effective Large-Scale Data Compression Method for Supervised Fine-tuning of Large Language Models NAACL 2025 LSNet: See Large, Focus Small CVPR 2025 LVBench: An Extreme Long Video Understanding Benchmark ICCV 2025 LV-XAttn: Distributed Cross-Attention for Long Visual Inputs in Multimodal Large Language Models ICML 2025 M2EIT: Multi-Domain Mixture of Experts for Robust Neural Inertial Tracking ICCV 2025 M3Net: Efficient Time-Frequency Integration Network with Mirror Attention for Audio Classification on Edge AAAI 2025 MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projection ACL 2025 MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference ACL 2025 MAD-TD: Model-Augmented Data stabilizes High Update Ratio RL ICLR 2025 MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding ICLR 2025 MagicPIG: LSH Sampling for Efficient LLM Generation ICLR 2025 MAIN-RAG: Multi-Agent Filtering Retrieval-Augmented Generation ACL 2025 Making Hard Problems Easier with Custom Data Distributions and Loss Regularization: A Case Study in Modular Arithmetic ICML 2025 Mamba Drafters for Speculative Decoding EMNLP 2025 Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models NAACL 2025 MARIO-0.5B: A Multi-Agent Lightweight Model for Real-Time Open Information Extraction in Low-Resource Settings EMNLP 2025 MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems ICML 2025