How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However, existing methods rely on uniform precision, ignoring the diverse sensitivity of ViT components to quantization. Metric-based Mixed Precision Quantization (MPQ) is a promising alternative, but previous MPQ methods for ViTs suffer from three major limitations: 1) coarse granularity, 2) mismatch in metric scale across component types, and 3) quantization-unaware bit allocation. In this paper, we propose LampQ (Layer-wise Mixed Precision Quantization for Vision Transformers), an accurate metric-based MPQ method for ViTs to overcome these limitations. LampQ performs layer-wise quantization to achieve both fine-grained control and efficient acceleration, incorporating a type-aware Fisher-based metric to measure sensitivity. Then, LampQ assigns bit-widths optimally through integer linear programming and further updates them iteratively. Extensive experiments show that LampQ provides the state-of-the-art performance in quantizing ViTs pre-trained on various tasks such as image classification, object detection, and zero-shot quantization.

How can we share parameters within large language models to significantly reduce memory costs while preserving accuracy?While parameter sharing is a promising solution to the memory overhead of large language models, existing methods rely on naive grouping and fail to correct sharing-induced discrepancies.We propose an accurate and efficient parameter sharing framework, SharVeT (Similarity-aware sharing with Vector-based Tuning), which performs similarity-based grouping to ensure accurate sharing, allocates parameters adaptively to preserve diversity within each group, and applies lightweight refinement with knowledge distillation to correct sharing-induced discrepancies.Experiments show that SharVeT outperforms existing sharing methods, achieving up to 32.1% lower perplexity and 21.2% higher few-shot reasoning accuracy.

How can we accurately quantize a pre-trained model without any data? Quantization algorithms are widely used for deploying neural networks on resource-constrained edge devices. Zero-shot Quantization (ZSQ) addresses the crucial and practical scenario where training data are inaccessible for privacy or security reasons. However, three significant challenges hinder the performance of existing ZSQ methods: 1) noise in the synthetic dataset, 2) predictions based on off-target patterns, and the 3) misguidance by erroneous hard labels. In this paper, we propose SynQ (Synthesis-aware Fine-tuning for Zero-shot Quantization), a carefully designed ZSQ framework to overcome the limitations of existing methods. SynQ minimizes the noise from the generated samples by exploiting a low-pass filter. Then, SynQ trains the quantized model to improve accuracy by aligning its class activation map with the pre-trained model. Furthermore, SynQ mitigates misguidance from the pre-trained model's error by leveraging only soft labels for difficult samples. Extensive experiments show that SynQ provides the state-of-the-art accuracy, over existing ZSQ methods.

How can we accelerate large language models (LLMs) without sacrificing accuracy? The slow inference speed of LLMs hinders us to benefit from their remarkable performance in diverse applications. This is mainly because numerous sublayers are stacked together in LLMs. Sublayer pruning compresses and expedites LLMs via removing unnecessary sublayers. However, existing sublayer pruning algorithms are limited in accuracy since they naively select sublayers to prune, overlooking the different characteristics of each sublayer. In this paper, we propose SPRINT (Sublayer Pruning with Latency and Tunability Information), an accurate sublayer pruning method for LLMs. SPRINT accurately selects a target sublayer to prune by considering 1) the amount of latency reduction after pruning and 2) the tunability of sublayers. SPRINT iteratively prunes redundant sublayers and swiftly tunes the parameters of remaining sublayers. Experiments show that SPRINT achieves the best accuracy-speedup trade-off, exhibiting up to 23.88%p higher accuracy on zero-shot commonsense reasoning benchmarks compared to existing pruning algorithms.

When we sequentially recommend top-k items to users, how can we recommend them diversely while maintaining accuracy? Aggregate-level diversity is an important topic in recommender system since it is essential to maximize the potential profit of platforms by exposing a variety of items to users. However, previous studies do not consider the order of users receiving recommendations and assume that all users receive recommendations at once. In reality, users do not simultaneously receive recommendations so the preferences of the latter users are not given during recommending to the former users. In this work, we introduce the problem of sequentially diversified recommendation and propose SAPID, an accurate method to address the problem. SAPID removes the popularity bias from the model through a negative sampling mechanism based on temporal popularities. Then, SAPID collects candidate items to recommend based on the distribution of preference scores. Finally, SAPID decides which items to recommend immediately or later according to their estimated exposure opportunities. Extensive experiments show that SAPID shows the state-of-the-art performance in real-world datasets by achieving up to 61.0% increased diversity with 38.9% higher accuracy compared to the second-best competitor.

Given a multidimensional array, how can we optimize the computation process for a part of Fourier coefficients? Discrete Fourier transform plays an overarching role in various data mining tasks. Recent interest has focused on efficiently calculating a small part of Fourier coefficients, exploiting the energy compaction property of real-world data. Current methods for partial Fourier transform frequently encounter efficiency issues, yet the adoption of pre-computation techniques within the PFT algorithm has shown promising performance. However, PFT still faces limitations in handling multidimensional data efficiently and requires manual hyperparameter tuning, leading to additional costs.

How can we accurately recommend actions for users to control their devices at home? Action recommendation for smart home has attracted increasing attention due to its potential impact on the markets of Internet of Things (IoT). However, designing an effective action recommender system is challenging because it requires handling context correlations, considering both queried contexts and previous histories of users, and dealing with capricious intentions in history. In this work, we propose SmartSense, an accurate action recommendation method for smart home. For individual action, SmartSense summarizes its device control and temporal contexts in a self-attentive manner, to reflect the importance of the correlation between them. SmartSense then summarizes sequences considering queried contexts in a query-attentive manner to extract the query-related patterns from the sequential actions. SmartSense also transfers the commonsense knowledge from routine data to better handle intentions in action sequences. As a result, SmartSense addresses all three main challenges of action recommendation for smart home, and achieves the state-of-the-art performance giving up to 9.8% higher [email protected] than the best competitor.