← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging NIPS 2024
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization NIPS 2024
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget ACL 2024
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization NIPS 2024
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention NIPS 2024
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization NIPS 2024
Understanding the Role of the Projector in Knowledge Distillation AAAI 2024
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length NIPS 2024
Faster and Lighter LLMs: A Survey on Current Challenges and Way Forward IJCAI 2024
FasterVD: On Acceleration of Video Diffusion Models IJCAI 2024
LLM in a flash: Efficient Large Language Model Inference with Limited Memory ACL 2024
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution NIPS 2024
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models NIPS 2024
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation NIPS 2024
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization NIPS 2024
UniPTS: A Unified Framework for Proficient Post-Training Sparsity CVPR 2024
Reasons and Solutions for the Decline in Model Performance after Editing NIPS 2024
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention NIPS 2024
What Makes Quantization for Large Language Model Hard? An Empirical Study from the Lens of Perturbation AAAI 2024
Clockwork Diffusion: Efficient Generation With Model-Step Distillation CVPR 2024
Pick-or-Mix: Dynamic Channel Sampling for ConvNets CVPR 2024
OneBit: Towards Extremely Low-bit Large Language Models NIPS 2024
Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner CVPR 2024
Efficient Stitchable Task Adaptation CVPR 2024
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models NIPS 2024