parameter efficiency

3D Gaussian Point Encoders WACV 2026 Boosting Fine-Grained Urban Flow Inference via Lightweight Architecture and Focalized Optimization AAAI 2026 Completely Modular Fine-tuning for Dynamic Language Adaptation EACL 2026 D2MoRA: Diversity-Regulated Asymmetric MoE-LoRA Decomposition for Efficient Multi-Task Adaptation AAAI 2026 EchoMimicV3: 1.3B Parameters Are All You Need for Unified Multi-Modal and Multi-Task Human Animation AAAI 2026 ELO: Efficient Layer-Specific Optimization for Continual Pretraining of Multilingual LLMs EACL 2026 GMoE: Global Mixture of Experts with Logit Propagation ACL 2026 Infinity-MoE: Generalizing Mixture of Experts to Infinite Experts EACL 2026 LoRA in LoRA: Towards Parameter-Efficient Architecture Expansion for Continual Visual Instruction Tuning AAAI 2026 MoLoRA: Boosting LLM-based End-to-end Speech Translation with Mixture of Low-rank Experts AAAI 2026 NeuronMoE: Efficient Cross-Lingual Extension via Neuron-Guided Mixture-of-Experts EACL 2026 Parameter-Efficient Quality Estimation via Frozen Recursive Models EACL 2026 PartialNet: Compute Less, Perform Better AAAI 2026 PointNSP: Autoregressive 3D Point Cloud Generation with Next-Scale Level-of-Detail Prediction CVPR 2026 Prototype-as-Prompt: Multimodal Sentiment Prototypes Endowing Large Language Models the Capability to Perform Multimodal Sentiment Analysis CVPR 2026 RelaCtrl: Relevance-Guided Efficient Control for Diffusion Transformers AAAI 2026 R-MMA: Enhancing Vision-Language Models with Recurrent Adapters for Few-Shot and Cross-Domain Generalization WACV 2026 Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning AAAI 2026 Sparse Tuning Enhances Plasticity in PTM-based Continual Learning AAAI 2026 Tailored ViT Slimming: Budget-Aware Multi-Dimensional Sparsity Regularization for Vision Transformers Pruning (Student Abstract) AAAI 2026 Text Slider: Efficient and Plug-and-Play Continuous Concept Control for Image/Video Synthesis via LoRA Adapters WACV 2026 Token-Context Attention for NLI: An Alternative to Self-Attention AAAI 2026 Union-of-Experts: Neurons in Mixture-of-Experts are Secretly Routers ACL 2026 1+1>2: A Synergistic Sparse and Low-Rank Compression Method for Large Language Models EMNLP 2025 5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks CVPR 2025