← Optimization & Theory
Deep Learning › Optimization & Theory ›

Model Compression

1674 directly classified papers

Papers per year

Papers

Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models NIPS 2024
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding ACL 2024
LLM in a flash: Efficient Large Language Model Inference with Limited Memory ACL 2024
UniPTS: A Unified Framework for Proficient Post-Training Sparsity CVPR 2024
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization NIPS 2024
ChunkAttention: Efficient Self-Attention with Prefix-Aware KV Cache and Two-Phase Partition ACL 2024
On the Impact of Calibration Data in Post-training Quantization and Pruning ACL 2024
USDN: A Unified Sample-Wise Dynamic Network With Mixed-Precision and Early-Exit WACV 2024
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression NIPS 2024
BOLD: Boolean Logic Deep Learning NIPS 2024
Dodo: Dynamic Contextual Compression for Decoder-only LMs ACL 2024
Acquiring Clean Language Models from Backdoor Poisoned Datasets by Downscaling Frequency Space ACL 2024
Learning To Compose SuperWeights for Neural Parameter Allocation Search WACV 2024
NACL: A General and Effective KV Cache Eviction Framework for LLM at Inference Time ACL 2024
SwapMoE: Serving Off-the-shelf MoE-based Large Language Models with Tunable Memory Budget ACL 2024
PartialFormer: Modeling Part Instead of Whole for Machine Translation ACL 2024
Attention-Driven Training-Free Efficiency Enhancement of Diffusion Models CVPR 2024
WRP: Weight Recover Prune for Structured Sparsity ACL 2024
Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models ACL 2024
SparseFlow: Accelerating Transformers by Sparsifying Information Flows ACL 2024
MELoRA: Mini-Ensemble Low-Rank Adapters for Parameter-Efficient Fine-Tuning ACL 2024
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection CVPR 2024
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models NIPS 2024
QDyLoRA: Quantized Dynamic Low-Rank Adaptation for Efficient Large Language Model Tuning EMNLP 2024
Parameter Competition Balancing for Model Merging NIPS 2024