"parameter efficiency" Papers
19 papers found
DeRS: Towards Extremely Efficient Upcycled Mixture-of-Experts Models
Yongqi Huang, Peng Ye, Chenyu Huang et al.
Efficient Source-Free Time-Series Adaptation via Parameter Subspace Disentanglement
Gaurav Patel, Christopher M. Sandino, Behrooz Mahasseni et al.
eQMARL: Entangled Quantum Multi-Agent Reinforcement Learning for Distributed Cooperation over Quantum Channels
Alexander DeRieux, Walid Saad
Layerwise Recurrent Router for Mixture-of-Experts
Zihan Qiu, Zeyu Huang, Shuang Cheng et al.
LLaVA-MoD: Making LLaVA Tiny via MoE-Knowledge Distillation
Fangxun Shu, Yue Liao, Lei Zhang et al.
Sparsity Outperforms Low-Rank Projections in Few-Shot Adaptation
Nairouz Mrabah, Nicolas Richet, Ismail Ayed et al.
TLB-VFI: Temporal-Aware Latent Brownian Bridge Diffusion for Video Frame Interpolation
Zonglin Lyu, Chen Chen
A Tensor Decomposition Perspective on Second-order RNNs
Maude Lizaire, Michael Rizvi-Martel, Marawan Gamal et al.
Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation
Can Yaras, Peng Wang, Laura Balzano et al.
Data-free Neural Representation Compression with Riemannian Neural Dynamics
Zhengqi Pei, Anran Zhang, Shuhui Wang et al.
Efficient Pareto Manifold Learning with Low-Rank Structure
Weiyu CHEN, James Kwok
Flora: Low-Rank Adapters Are Secretly Gradient Compressors
Yongchang Hao, Yanshuai Cao, Lili Mou
Image-adaptive 3D Lookup Tables for Real-time Image Enhancement with Bilateral Grids
Wontae Kim, Nam Ik Cho
In value-based deep reinforcement learning, a pruned network is a good network
Johan Obando Ceron, Aaron Courville, Pablo Samuel Castro
KernelWarehouse: Rethinking the Design of Dynamic Convolution
Chao Li, Anbang Yao
MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions
Kai Zhang, Yi Luan, Hexiang Hu et al.
Progressive Distillation Based on Masked Generation Feature Method for Knowledge Graph Completion
Cunhang Fan, Yujie Chen, Jun Xue et al.
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
Jiwon Song, Kyungseok Oh, Taesu Kim et al.
Taming the Sigmoid Bottleneck: Provably Argmaxable Sparse Multi-Label Classification
Andreas Grivas, Antonio Vergari, Adam Lopez