conftrace_
← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1,952 papers

Papers per year

6
114
489
'15
'20
'25

Papers

ReGLA: Refining Gated Linear Attention NAACL 2025
Mamba-Shedder: Post-Transformer Compression for Efficient Selective Structured State Space Models NAACL 2025
SVD-LLM V2: Optimizing Singular Value Truncation for Large Language Model Compression NAACL 2025
MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning NAACL 2025
MoDification: Mixture of Depths Made Easy NAACL 2025
Efficient One-shot Compression via Low-Rank Local Feature Distillation NAACL 2025
Stronger Universal and Transferable Attacks by Suppressing Refusals NAACL 2025
Prompt Compression for Large Language Models: A Survey NAACL 2025
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices NAACL 2025
FedSpaLLM: Federated Pruning of Large Language Models NAACL 2025
Not All Adapters Matter: Selective Adapter Freezing for Memory-Efficient Fine-Tuning of Language Models NAACL 2025
Self-calibration for Language Model Quantization and Pruning NAACL 2025
SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation NAACL 2025
HIGGS: Pushing the Limits of Large Language Model Quantization via the Linearity Theorem NAACL 2025
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025
Local Prompt Optimization NAACL 2025
Can Post-Training Quantization Benefit from an Additional QLoRA Integration? NAACL 2025
Does Self-Attention Need Separate Weights in Transformers? NAACL 2025
Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting NAACL 2025
Code-Optimise: Self-Generated Preference Data for Correctness and Efficiency NAACL 2025
DisComp: A Two-Stage Prompt Optimization Framework Combining Task-Agnostic and Task-Aware Compression NAACL 2025
Token Weighting for Long-Range Language Modeling NAACL 2025
LVLM-Compress-Bench: Benchmarking the Broader Impact of Large Vision-Language Model Compression NAACL 2025
Learning with Less: Knowledge Distillation from Large Language Models via Unlabeled Data NAACL 2025
PipeThreader: Software-Defined Pipelining for Efficient DNN Execution OSDI 2025