Artificial Intelligence › Core AI ›

Model Compression

1928 directly classified papers

Papers per year

Papers

Discretization Is Not Always Better: Rethinking Deep Quantization for Asymmetric Image Retrieval AAAI 2026

Calibrating and Rotating: A Unified Framework for Weight Conditioning in PEFT AAAI 2026

Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration AAAI 2026

L2-LoRA: Improving Low-Rank Adaptation with Layer-Specific Regularization AAAI 2026

LAS: Loss-less ANN-SNN Conversion for Fully Spike-Driven Large Language Models AAAI 2026

HardF-SNN: Hardware-Friendly Quantization for Spiking Neural Networks with Efficient Integer-Arithmetic-Only Inference AAAI 2026

Training-Free ANN-to-SNN Conversion for High-Performance Spiking Transformers AAAI 2026

FastFLUX: Pruning FLUX with Block-wise Replacement and Sandwich Training AAAI 2026

SepPrune: Structured Pruning for Efficient Deep Speech Separation AAAI 2026

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026

Progressive Multi-modal Knowledge Distillation for Multi-spectral Object Re-identification AAAI 2026

LoGIC: Multi-LoRA Guided Importance Consensus for Multi-Task Pruning in Vision Transformers AAAI 2026

SPEED-Q: Staged Processing with Enhanced Distillation Towards Efficient Low-Bit On-Device VLM Quantization AAAI 2026

Transferable Backdoor Attacks for Code Models via Sharpness-Aware Adversarial Perturbation AAAI 2026

Towards Training-Free and Accurate ANN-to-SNN Conversion via Activation-Aware Redistribution AAAI 2026

Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models AAAI 2026

AfriNLLB: Efficient Translation Models for African Languages EACL 2026

Multimodal Adversarial Defense for Vision-Language Models by Leveraging One-To-Many Relationships WACV 2026

Mosaic Pruning: A Hierarchical Framework for Generalizable Pruning of Mixture-of-Experts Models AAAI 2026

HiPrune: Training-Free Visual Token Pruning via Hierarchical Attention in Vision-Language Models (Student Abstract) AAAI 2026

Adaptive Compute Efficient Learning via Conceptual-Criticality (Student Abstract) AAAI 2026

Unveiling AI Safety in Fine-tuning Quantized Model AAAI 2026

Scale Regularization for Stable Low-Rank Adaptation AAAI 2026

From Lightweight CNNs to SpikeNets: Benchmarking Accuracy-Energy Tradeoffs with Pruned Spiking SqueezeNet WACV 2026

Federated Model Synchronization for Diagnostic Redefinition through a Novel Selective Parameter Unlearning WACV 2026