Model Compression
2개 벤치마크 · 논문 1,630편 · 이 태스크의 논문 보기 →
Benchmarks
Most implemented
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Well-Read Students Learn Better: On the Importance of Pre-training Compact Models
GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers
AMC: AutoML for Model Compression and Acceleration on Mobile Devices
Learned Step Size Quantization
The State of Sparsity in Deep Neural Networks
Papers
Debias-SparseGPT: Bias-Aware Pruning for Large Language Models
Model compression techniques such as pruning and quantization facilitate the efficient deployment and acceleration of Large Language Models (LLMs). However, recent studies show that weight sparsification methods, such as…
Computational EfficiencyModel CompressionWhen Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMs
Sparse autoencoders (SAEs) are widely used to interpret the internal representations of large language models (LLMs), yet their reliability under post-hoc model compression remains poorly understood. We present a systema…
Model CompressionExploring the Performance Frontier of Compact Unified Image Generation Models
We present Swift-Image, a compact unified model for text-to-image generation, single-image editing, and multi-image editing. Our goal is to explore how far a relatively small visual generator can be pushed through system…
Text-to-Image GenerationReinforcement LearningModel CompressionImage EditingKilobyte Models: Neural Networks as a Seed and a Quantized Latent
The cost of storing and transmitting a trained neural network scales with its parameter count, a bottleneck for over-the-air updates, on-device libraries, and other bandwidth-bound deployments. We study an extreme form o…
Model CompressionMemory Efficient Tabular Foundation Models
Tabular Foundation Models, such as TabPFN, have received a large amount of recent attention due to their performance on in-context tabular machine learning tasks, which often exceeds classical baselines. However, practic…
Model CompressionCoCaRS: Correlation Calibration-Based Redundancy Suppression for Heterogeneous Knowledge Distillation
Knowledge distillation (KD) enables a compact student model to learn from a powerful teacher and has become an effective paradigm for model compression. The emergence of diverse model architectures has extended KD from h…
Knowledge DistillationModel Compression