Model Architecture

LoRA-GA: Low-Rank Adaptation with Gradient Approximation NeurIPS 2024 Low-Rank Prune-And-Factorize for Language Model Compression COLING 2024 Low-Rank Rescaled Vision Transformer Fine-Tuning: A Residual Design Approach CVPR 2024 LP-3DGS: Learning to Prune 3D Gaussian Splatting NeurIPS 2024 LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning ICLR 2024 LSK3DNet: Towards Effective and Efficient 3D Perception with Large Sparse Kernels CVPR 2024 MACE: Mass Concept Erasure in Diffusion Models CVPR 2024 MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer CVPR 2024 MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization NeurIPS 2024 Magnitude Invariant Parametrizations Improve Hypernetwork Learning ICLR 2024 Making Vision Transformers Truly Shift-Equivariant CVPR 2024 Markov Knowledge Distillation: Make Nasty Teachers trained by Self-undermining Knowledge Distillation Fully Distillable ECCV 2024 MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models NeurIPS 2024 Masks, Signs, And Learning Rate Rewinding ICLR 2024 MAS-SAM: Segment Any Marine Animal with Aggregated Features IJCAI 2024 Matryoshka Query Transformer for Large Vision-Language Models NeurIPS 2024 MaxQ: Multi-Axis Query for N:M Sparsity Network CVPR 2024 MCA: Moment Channel Attention Networks AAAI 2024 MD tree: a model-diagnostic tree grown on loss landscape ICML 2024 Measuring Per-Unit Interpretability at Scale Without Humans NeurIPS 2024 Medical Neural Architecture Search: Survey and Taxonomy IJCAI 2024 Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length NeurIPS 2024 Memory-Augmenting Decoder-Only Language Models through Encoders (Student Abstract) AAAI 2024 Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization NeurIPS 2024 Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning ECCV 2024