conftrace_

parameter sharing

227 papers

Explore in graph

Also known as

PS PSS

Co-occurring keywords · papers mentioning both

multi-task learning (48) model compression (46) transfer learning (28) neural machine translation (19) neural network (18) neural architecture search (17) convolutional neural network (12) parameter efficiency (11) efficient computing (10) multilingual translation (9)

Papers

More Experts Than Galaxies: Conditionally-Overlapping Experts with Biologically-Inspired Fixed Routing ICLR 2025 MoS: Unleashing Parameter Efficiency of Low-Rank Adaptation with Mixture of Shards ICLR 2025 Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks WACV 2025 Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers JMLR 2025 RECAST: Reparameterized, Compact weight Adaptation for Sequential Tasks ICLR 2025 Relaxed Recursive Transformers: Effective Parameter Sharing with Layer-wise LoRA ICLR 2025 RingFormer: Rethinking Recurrent Transformer with Adaptive Level Signals EMNLP 2025 Sparsifying Mamba EMNLP 2025 Task-wrapped Continual Learning in Task-Oriented Dialogue Systems NAACL 2025 Towards Consistent Multi-Task Learning: Unlocking the Potential of Task-Specific Parameters CVPR 2025 VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting ICCV 2025 What Causes Knowledge Loss in Multilingual Language Models? ACL 2025 XLM-Muriel at SemEval-2025 Task 11: Hard Parameter Sharing for Multi-lingual Multi-label Emotion Detection SemEval 2025 ADMN: Agent-Driven Modular Network for Dynamic Parameter Sharing in Cooperative Multi-Agent Reinforcement Learning IJCAI 2024 Can Transformers Learn n-gram Language Models? EMNLP 2024 Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers NeurIPS 2024 DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion NeurIPS 2024 Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance NeurIPS 2024 FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing AAAI 2024 FLY-TTS: Fast, Lightweight and High-Quality End-to-End Text-to-Speech Synthesis Interspeech 2024 Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning NeurIPS 2024 Learning Causal Dynamics Models in Object-Oriented Environments ICML 2024 Learning To Compose SuperWeights for Neural Parameter Allocation Search WACV 2024 MGit: A Model Versioning and Management System ICML 2024 MoEUT: Mixture-of-Experts Universal Transformers NeurIPS 2024