conftrace_

sparse activation

36 papers

Explore in graph

Co-occurring keywords

mixture of expert (640) model compression (3302) parameter efficiency (417) large language model (13587) neural network (6616) language model (4599) expert routing (44) feed-forward network (79) model scaling (135) convolutional neural network (4226)

Papers

Scene Experts: Specializing in 3D Gaussian Splatting with Adaptive Decomposition AAAI 2026
Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis ACL 2026
Maximum Score Routing For Mixture-of-Experts ACL 2025
Sparse Activation Editing for Reliable Instruction Following in Narratives EMNLP 2025
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025
A Closer Look into Mixture-of-Experts in Large Language Models NAACL 2025
SMoSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks AAAI 2025
COUNTDOWN: Contextually Sparse Activation Filtering Out Unnecessary Weights in Down Projection EMNLP 2025
Mixture of Languages: Improved Multilingual Encoders Through Language Grouping EMNLP 2025
Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis CVPR 2025
Efficient Data Driven Mixture-of-Expert Extraction from Trained Networks CVPR 2025
SoLA: Leveraging Soft Activation Sparsity and Low-Rank Decomposition for Large Language Model Compression AAAI 2025
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control NIPS 2024
Neural Networks with Sparse Activation Induced by Large Bias: Tighter Analysis with Bias-Generalized NTK JMLR 2024
Harnessing Manycore Processors with Distributed Memory for Accelerated Training of Sparse and Recurrent Models AAAI 2024
Breaking ReLU Barrier: Generalized MoEfication for Dense Pretrained Models EMNLP 2024
Unraveling Babel: Exploring Multilingual Activation Patterns of LLMs and Their Applications EMNLP 2024
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models ACL 2024
Mixture of Diverse Size Experts EMNLP 2024
Efficient Spiking Neural Networks with Sparse Selective Activation for Continual Learning AAAI 2024
Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference NIPS 2023
On the Compositional Generalization in Versatile Open-domain Dialogue ACL 2023
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine Translation ACL 2023
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity EMNLP 2023
On the Benefits of Learning to Route in Mixture-of-Experts Models EMNLP 2023