Papers Model Compression
“Model Compression” 태그가 달린 논문 1,632편 · 필터 해제
Distilling Multilingual Vision-Language Models: When Smaller Models Stay Multilingual
Vision-language models (VLMs) exhibit uneven performance across languages, a problem that is often exacerbated when the model size is reduced. While Knowledge distillation (KD) demonstrates promising results in transferr…
Knowledge DistillationModel CompressionEnergy-Efficient Autonomous Driving with Adaptive Perception and Robust Decision
Autonomous driving is an emerging technology that is expected to bring significant social, economic, and environmental benefits. However, these benefits come with rising energy consumption by computation engines, limitin…
Reinforcement LearningAutonomous DrivingModel CompressionUHKD: A Unified Framework for Heterogeneous Knowledge Distillation via Frequency-Domain Representations
Knowledge distillation (KD) is an effective model compression technique that transfers knowledge from a high-performance teacher to a lightweight student, reducing computational and storage costs while maintaining compet…
Knowledge DistillationModel CompressionResource-Efficient and Robust Inference of Deep and Bayesian Neural Networks on Embedded and Analog Computing Platforms
While modern machine learning has transformed numerous application domains, its growing computational demands increasingly constrain scalability and efficiency, particularly on embedded and resource-limited platforms. In…
Bayesian InferenceModel CompressionRethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions
Edge intelligent applications like VR/AR and language model based chatbots have become widespread with the rapid expansion of IoT and mobile devices. However, constrained edge devices often cannot serve the increasingly …
Model CompressionA Survey on Efficient Vision-Language-Action Models
Vision-Language-Action models (VLAs) represent a significant frontier in embodied intelligence, aiming to bridge digital knowledge with physical-world interaction. Despite their remarkable performance, foundational VLAs …
Model CompressionIterative Layer Pruning for Efficient Translation Inference
Large language models (LLMs) have transformed many areas of natural language processing, including machine translation. However, efficient deployment of LLMs remains challenging due to their intensive computational requi…
Machine TranslationModel CompressionScaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search
Large Language Models (LLMs) have demonstrated impressive quality when applied to predictive tasks such as relevance ranking and semantic search. However, deployment of such LLMs remains prohibitively expensive for indus…
Model CompressionTeamFormer: Shallow Parallel Transformers with Progressive Approximation
The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with ch…
Model CompressionA Deep State-Space Model Compression Method using Upper Bound on Output Error
We study deep state-space models (Deep SSMs) that contain linear quadratic-output (LQO) systems as internal blocks and present a compression method with a provable output error guarantee. We first derive an upper bound o…
Model CompressionD-com: Accelerating Iterative Processing to Enable Low-rank Decomposition of Activations
The computation and memory costs of large language models kept increasing over last decade, which reached over the scale of 1T parameters. To address the challenges from the large scale models, model compression techniqu…
Model CompressionCompressibility Measures Complexity: Minimum Description Length Meets Singular Learning Theory
We study neural network compressibility by using singular learning theory to extend the minimum description length (MDL) principle to singular models like neural networks. Through extensive experiments on the Pythia suit…
Model CompressionStratos: An End-to-End Distillation Pipeline for Customized LLMs under Distributed Cloud Environments
The growing industrial demand for customized and cost-efficient large language models (LLMs) is fueled by the rise of vertical, domain-specific tasks and the need to optimize performance under constraints such as latency…
Knowledge DistillationModel CompressionLightweight Facial Landmark Detection in Thermal Images via Multi-Level Cross-Modal Knowledge Transfer
Facial Landmark Detection (FLD) in thermal imagery is critical for applications in challenging lighting conditions, but it is hampered by the lack of rich visual cues. Conventional cross-modal solutions, like feature fus…
Facial Landmark DetectionKnowledge DistillationModel CompressionAndesVL Technical Report: An Efficient Mobile-side Multimodal Large Language Model
In recent years, while cloud-based MLLMs such as QwenVL, InternVL, GPT-4o, Gemini, and Claude Sonnet have demonstrated outstanding performance with enormous model sizes reaching hundreds of billions of parameters, they s…
Model CompressionEntropy Meets Importance: A Unified Head Importance-Entropy Score for Stable and Efficient Transformer Pruning
Transformer-based models have achieved remarkable performance in NLP tasks. However, their structural characteristics-multiple layers and attention heads-introduce efficiency challenges in inference and deployment. To ad…
Model CompressionFewer Weights, More Problems: A Practical Attack on LLM Pruning
Model pruning, i.e., removing a subset of model weights, has become a prominent approach to reducing the memory footprint of large language models (LLMs) during inference. Notably, popular inference engines, such as vLLM…
Model CompressionVanishing Contributions: A Unified Framework for Smooth and Iterative Model Compression
The increasing scale of Deep Neural Networks (DNNs) introduces the need for compression techniques such as pruning, quantization, and low-rank decomposition. While these methods are very effective at reducing memory, com…
Model CompressionARMOR: High-Performance Semi-Structured Pruning via Adaptive Matrix Factorization
Large language models (LLMs) present significant deployment challenges due to their immense computational and memory requirements. While semi-structured pruning, particularly 2:4 sparsity, offers a path to practical hard…
Model CompressionActivation-Informed Pareto-Guided Low-Rank Compression for Efficient LLM/VLM
Large language models (LLM) and vision-language models (VLM) have achieved state-of-the-art performance, but they impose significant memory and computing challenges in deployment. We present a novel low-rank compression …
Model Compression