conftrace_

model efficiency

206 papers

Explore in graph

Co-occurring keywords

model compression (3302) efficient computing (781) vision transformer (1106) image classification (1944) large language model (13587) neural network optimization (1293) knowledge distillation (3725) convolutional neural network (4226) attention mechanism (4001) neural architecture search (666)

Papers

RapidNet: Multi-Level Dilated Convolution Based Mobile Backbone WACV 2025
Group-SAE: Efficient Training of Sparse Autoencoders for Large Language Models via Layer Groups EMNLP 2025
zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025
VRCP: Vocabulary Replacement Continued Pretraining for Efficient Multilingual Language Models COLING 2025
Low-Bit Quantization Favors Undertrained LLMs ACL 2025
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency NAACL 2025
Smarter, Not Harder: Training-Free Adaptive Computation for Transformers ACL 2025
Achieving Speed-Accuracy Balance in Vision-based 3D Occupancy Prediction via Geometric-Semantic Disentanglement AAAI 2025
UniEDU: Toward Unified and Efficient Large Multimodal Models for Educational Tasks EMNLP 2025
ReGLA: Refining Gated Linear Attention NAACL 2025
DAViD: Data-efficient and Accurate Vision Models from Synthetic Data ICCV 2025
LSNet: See Large, Focus Small CVPR 2025
ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training EMNLP 2025
LeanVAE: An Ultra-Efficient Reconstruction VAE for Video Diffusion Models ICCV 2025
Efficient Visual Representation Learning with Heat Conduction Equation IJCAI 2025
CARE Transformer: Mobile-Friendly Linear Visual Transformer via Decoupled Dual Interaction CVPR 2025
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba AAAI 2025
Pose Magic: Efficient and Temporally Consistent Human Pose Estimation with a Hybrid Mamba-GCN Network AAAI 2025
Enhancing Large Language Model Performance with Gradient-Based Parameter Selection AAAI 2025
Transformer Layers as Painters AAAI 2025
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models ICCV 2025
TREAD: Token Routing for Efficient Architecture-agnostic Diffusion Training ICCV 2025
MixA: A Mixed Attention approach with Stable Lightweight Linear Attention to enhance Efficiency of Vision Transformers at the Edge ICCV 2025
Bringing RNNs Back to Efficient Open-Ended Video Understanding ICCV 2025
Partial Filter-Sharing: Improved Parameter-Sharing Method for Single Image Super-Resolution Networks WACV 2025