← Core AI
Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and Modalities EMNLP 2025
Efficient Unstructured Pruning of Mamba State-Space Models for Resource-Constrained Environments EMNLP 2025
On Pruning State-Space LLMs EMNLP 2025
XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression EMNLP 2025
Model Unlearning via Sparse Autoencoder Subspace Guided Projections EMNLP 2025
ProCut: LLM Prompt Compression via Attribution Estimation EMNLP 2025
Seeing More, Saying More: Lightweight Language Experts are Dynamic Video Token Compressors EMNLP 2025
Aggregation Mechanism Based Graph Heterogeneous Networks Distillation IJCAI 2025
TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models EMNLP 2025
VoCo-LLaMA: Towards Vision Compression with Large Language Models CVPR 2025
An Orthogonal High-Rank Adaptation for Large Language Models EMNLP 2025
Interpreting the Effects of Quantization on LLMs IJCNLP 2025
VisiPruner: Decoding Discontinuous Cross-Modal Dynamics for Efficient Multimodal LLMs EMNLP 2025
LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices NAACL 2025
DSMoE: Matrix-Partitioned Experts with Dynamic Routing for Computation-Efficient Dense LLMs EMNLP 2025
FreqMoE: Dynamic Frequency Enhancement for Neural PDE Solvers IJCAI 2025
MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines EMNLP 2025
Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting NAACL 2025
GAP: a Global Adaptive Pruning Method for Large Language Models EMNLP 2025
Local Prompt Optimization NAACL 2025
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection EMNLP 2025
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate NAACL 2025
zFLoRA: Zero-Latency Fused Low-Rank Adapters EMNLP 2025
Misclassification-driven Fingerprinting for DNNs Using Frequency-aware GANs IJCAI 2025
Why Do Some Inputs Break Low-Bit LLM Quantization? EMNLP 2025