parameter efficiency

A Closer Look into Mixture-of-Experts in Large Language Models NAACL 2025 Archaeology at TSAR 2025 Shared Task Teaching Small Models to do CEFR Simplifications EMNLP 2025 BSLoRA: Enhancing the Parameter Efficiency of LoRA with Intra-Layer and Inter-Layer Sharing ICML 2025 Can We Get Rid of Handcrafted Feature Extractors? SparseViT: Nonsemantics-Centered, Parameter-Efficient Image Manipulation Localization Through Spare-Coding Transformer AAAI 2025 CLIP-UP: A Simple and Efficient Mixture-of-Experts CLIP Training Recipe with Sparse Upcycling EMNLP 2025 CoA: Towards Real Image Dehazing via Compression-and-Adaptation CVPR 2025 CoLA: Compute-Efficient Pre-Training of LLMs via Low-Rank Activation EMNLP 2025 Complexity Experts are Task-Discriminative Learners for Any Image Restoration CVPR 2025 DAM: Dynamic Adapter Merging for Continual Video QA Learning WACV 2025 DenseLoRA: Dense Low-Rank Adaptation of Large Language Models ACL 2025 DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models CVPR 2025 Designing Concise ConvNets with Columnar Stages ICLR 2025 Device-Cloud Collaborative Correction for On-Device Recommendation IJCAI 2025 Diffusion Model Patching via Mixture-of-Prompts AAAI 2025 DIVE into MoE: Diversity-Enhanced Reconstruction of Large Language Models from Dense into Mixture-of-Experts ACL 2025 Diversifying the Expert Knowledge for Task-Agnostic Pruning in Sparse Mixture-of-Experts ACL 2025 Drop-Upcycling: Training Sparse Mixture of Experts with Partial Re-initialization ICLR 2025 Eagle: Exploring The Design Space for Multimodal LLMs with Mixture of Encoders ICLR 2025 Effective and Efficient Medical Image Segmentation with Hierarchical Context Interaction WACV 2025 Efficient Architectures for High Resolution Vision-Language Models COLING 2025 Efficient Attention-Sharing Information Distillation Transformer for Lightweight Single Image Super-Resolution AAAI 2025 Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks CVPR 2025 Efficient Knowledge Editing via Minimal Precomputation ACL 2025 Efficient Learning with Sine-Activated Low-Rank Matrices ICLR 2025 Efficiently Editing Mixture-of-Experts Models with Compressed Experts EMNLP 2025