arXiv subjects

Joonyoung Kim

Publications and source records attributed to Joonyoung Kim.

7 recordsLinked to original sources

arXiv2026

TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation

The rapid growth of large language models (LLMs) has heightened the importance of post-training quantization (PTQ) for reducing memory and computation costs. Among PTQ methods, GPTQ has gained significant attention for its efficiency, enabling billion-scale LLMs to be quantized within a few GPU hours. However, GPTQ's assumption of layer-wise independence leads to severe accuracy drops in low-bit regimes. Recently, BoA improved upon GPTQ by incorporating inter-layer dependencies within attention modules, but its reliance on sequential quantization across all out-channels makes it substantially less efficient. In this paper, we propose TurboBoA, a new backpropagation-free PTQ algorithm that preserves the accuracy benefits of BoA while significantly accelerating the process. The proposed TurboBoA introduces three key innovations: (i) joint quantization of multiple out-channels with a closed-form error compensation rule, which reduces sequential bottlenecks and yields more than a three-fold speedup; (ii) a correction mechanism for errors propagated from preceding quantized layers; and (iii) adaptive grid computation with coordinate descent refinement to maintain alignment during iterative updates. Extensive experiments demonstrate that TurboBoA delivers substantial acceleration over BoA while consistently improving accuracy. When combined with outlier suppression techniques, it achieves state-of-the-art results in both weight-only and weight-activation quantization. The code will be available at https://github.com/SamsungLabs/TurboBoA.

cs.LG↗

arXiv2025

BoA: Attention-aware Post-training Quantization without Backpropagation

Post-training quantization (PTQ) is a promising solution for deploying large language models (LLMs) on resource-constrained devices. Early methods developed for small-scale networks, such as ResNet, rely on gradient-based optimization, which becomes impractical for hyper-scale LLMs with billions of parameters. While recently proposed backpropagation-free or transformation-based methods alleviate this issue, they ignore inter-layer interactions or use the naive nearest-rounding-based quantized weight assignment to save the heavy computational cost of weight optimization. In this paper, we introduce a novel backpropagation-free PTQ algorithm that optimizes quantized weights by considering inter-layer dependencies. The key innovation is the development of attention-aware Hessian matrices that capture inter-layer interactions within the attention module. Extensive experiments demonstrate that our approach not only outperforms existing weight quantization methods but also shows good synergy with conventional methods to suppress activation outliers, leading to state-of-the-art weight-activation quantization performance. The code will be available at https://github.com/SamsungLabs/BoA.

cs.LG↗

arXiv2024

Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers

With the increasing complexity of generative AI models, post-training quantization (PTQ) has emerged as a promising solution for deploying hyper-scale models on edge devices such as mobile and TVs. Existing PTQ schemes, however, consume considerable time and resources, which could be a bottleneck in real situations where frequent model updates and multiple hyperparameter tunings are required. As a cost-effective alternative, learning-free PTQ schemes have been proposed. However, the performance is somewhat limited because they cannot consider the inter-layer dependency within the attention module, which is a significant feature of Transformers. In this paper, we thus propose a novel PTQ algorithm that balances accuracy and efficiency. The key idea of the proposed algorithm called aespa is to perform quantization layer-wise for efficiency while targeting attention-wise reconstruction to consider the cross-layer dependency. Through extensive experiments on various language models and complexity analysis, we demonstrate that aespa is accurate and efficient in quantizing Transformer models.

cs.LG↗

arXiv2023

Intuitive Access to Smartphone Settings Using Relevance Model Trained by Contrastive Learning

The more new features that are being added to smartphones, the harder it becomes for users to find them. This is because the feature names are usually short, and there are just too many to remember. In such a case, the users may want to ask contextual queries that describe the features they are looking for, but the standard term frequency-based search cannot process them. This paper presents a novel retrieval system for mobile features that accepts intuitive and contextual search queries. We trained a relevance model via contrastive learning from a pre-trained language model to perceive the contextual relevance between query embeddings and indexed mobile features. Also, to make it run efficiently on-device using minimal resources, we applied knowledge distillation to compress the model without degrading much performance. To verify the feasibility of our method, we collected test queries and conducted comparative experiments with the currently deployed search baselines. The results show that our system outperforms the others on contextual sentence queries and even on usual keyword-based queries.

cs.IR↗

arXiv2021

Augment & Valuate : A Data Enhancement Pipeline for Data-Centric AI

Data scarcity and noise are important issues in industrial applications of machine learning. However, it is often challenging to devise a scalable and generalized approach to address the fundamental distributional and semantic properties of dataset with black box models. For this reason, data-centric approaches are crucial for the automation of machine learning operation pipeline. In order to serve as the basis for this automation, we suggest a domain-agnostic pipeline for refining the quality of data in image classification problems. This pipeline contains data valuation, cleansing, and augmentation. With an appropriate combination of these methods, we could achieve 84.711% test accuracy (ranked #6, Honorable Mention in the Most Innovative) in the Data-Centric AI competition only with the provided dataset.

cs.LG↗

arXiv2021

Neural Sequence-to-grid Module for Learning Symbolic Rules

Logical reasoning tasks over symbols, such as learning arithmetic operations and computer program evaluations, have become challenges to deep learning. In particular, even state-of-the-art neural networks fail to achieve \textit{out-of-distribution} (OOD) generalization of symbolic reasoning tasks, whereas humans can easily extend learned symbolic rules. To resolve this difficulty, we propose a neural sequence-to-grid (seq2grid) module, an input preprocessor that automatically segments and aligns an input sequence into a grid. As our module outputs a grid via a novel differentiable mapping, any neural network structure taking a grid input, such as ResNet or TextCNN, can be jointly trained with our module in an end-to-end fashion. Extensive experiments show that neural networks having our module as an input preprocessor achieve OOD generalization on various arithmetic and algorithmic problems including number sequence prediction problems, algebraic word problems, and computer program evaluation problems while other state-of-the-art sequence transduction models cannot. Moreover, we verify that our module enhances TextCNN to solve the bAbI QA tasks without external memory.

cs.LG↗

arXiv2020

STAR: Spatio-Temporal Prediction of Air Quality Using A Multimodal Approach

With the increase of global economic activities and high energy demand, many countries have raised concerns about air pollution. However, air quality prediction is a challenging issue due to the complex interaction of many factors. In this paper, we propose a multimodal approach for spatio-temporal air quality prediction. Our model learns the multimodal fusion of critical factors to predict future air quality levels. Based on the analyses of data, we also assessed the impacts of critical factors on air quality prediction. We conducted experiments on two real-world air pollution datasets. For Seoul dataset, our method achieved 11% and 8.2% improvement of the mean absolute error in long-term predictions of PM2.5 and PM10, respectively, compared to baselines. Our method also reduced the mean absolute error of PM2.5 predictions by 20% compared to the previous state-of-the-art results on China 1-year dataset.

eess.SP↗