Temporal Linear Item-Item Model for Sequential Recommendation

In sequential recommendation (SR), neural models have been actively explored due to their remarkable performance, but they suffer from inefficiency inherent to their complexity. On the other hand, linear SR models exhibit high efficiency and achieve competitive or superior accuracy compared to neural models. However, they solely deal with the sequential order of items (i.e., sequential information) and overlook the actual timestamp (i.e., temporal information). It is limited to effectively capturing various user preference drifts over time. To address this issue, we propose a novel linear SR model, named TemporAl LinEar item-item model (TALE), incorporating temporal information while preserving training/inference efficiency, with three key components. (i) Single-target augmentation concentrates on a single target item, enabling us to learn the temporal correlation for the target item. (ii) Time interval-aware weighting utilizes the actual timestamp to discern the item correlation depending on time intervals. (iii) Trend-aware normalization reflects the dynamic shift of item popularity over time. Our empirical studies show that TALE outperforms ten competing SR models by up to 18.71% gains on five benchmark datasets. It also exhibits remarkable effectiveness in evaluating long-tail items by up to 30.45% gains. The source code is available at https://github.com/psm1206/TALE.

Quantization-Aware Imitation-Learning for Resource-Efficient Robotic Control

Deep neural network (DNN)-based policy models like vision-language-action (VLA) models are transformative in automating complex decision-making across applications by interpreting multi-modal data. However, scaling these models greatly increases computational costs, which presents challenges in fields like robot manipulation and autonomous driving that require quick, accurate responses. To address the need for deployment on resource-limited hardware, we propose a new quantization framework for IL-based policy models that fine-tunes parameters to enhance robustness against low-bit precision errors during training, thereby maintaining efficiency and reliability under constrained conditions. Our evaluations with representative robot manipulation for 4-bit weight-quantization on a real edge GPU demonstrate that our framework achieves up to 2.5x speedup and 2.5x energy savings while preserving accuracy. For 4-bit weight and activation quantized self-driving models, the framework achieves up to 3.7x speedup and 3.1x energy saving on a low-end GPU. These results highlight the practical potential of deploying IL-based policy models on resource-constrained devices.

Selectively Dilated Convolution for Accuracy-Preserving Sparse Pillar-based Embedded 3D Object Detection

Pillar-based 3D object detection has gained traction in self-driving technology due to its speed and accuracy facilitated by the artificial densification of pillars for GPU-friendly processing. However, dense pillar processing fundamentally wastes computation since it ignores the inherent sparsity of pillars derived from scattered point cloud data. Motivated by recent embedded accelerators with native sparsity support, sparse pillar convolution methods like submanifold convolution (SubM-Conv) aimed to reduce these redundant computations by applying convolution only on active pillars but suffered considerable accuracy loss. Our research identifies that this accuracy loss is due to the restricted fine-grained spatial information flow (fSIF) of SubM-Conv in sparse pillar networks. To overcome this restriction, we propose a selectively dilated (SD-Conv) convolution that evaluates the importance of encoded pillars and selectively dilates the convolution output, enhancing the receptive field for critical pillars and improving object detection accuracy. To facilitate actual acceleration with this novel convolution approach, we designed SPADE+ as a cost-efficient augmentation to existing embedded sparse convolution accelerators. This design supports the SD-Conv without significant demands in area and SRAM size, realizing superior trade-off between the speedup and model accuracy. This strategic enhancement allows our method to achieve extreme pillar sparsity, leading to up to 18.1x computational savings and 16.2x speedup on the embedded accelerators, without compromising object detection accuracy.

Improving Conversational Abilities of Quantized Large Language Models via Direct Preference Alignment

The rapid advancement of large language models (LLMs) has facilitated their transformation into conversational chatbots that can grasp contextual nuances and generate pertinent sentences, closely mirroring human values through advanced techniques such as instruction tuning and reinforcement learning from human feedback (RLHF). However, the computational efficiency required for LLMs, achieved through techniques like post-training quantization (PTQ), presents challenges such as token-flipping that can impair chatbot performance. In response, we propose a novel preference alignment approach, quantization-aware direct preference optimization (QDPO), that aligns quantized LLMs with their full-precision counterparts, improving conversational abilities. Evaluated on two instruction-tuned LLMs in various languages, QDPO demonstrated superior performance in improving conversational abilities compared to established PTQ and knowledge-distillation fine-tuning techniques, marking a significant step forward in the development of efficient and effective conversational LLMs.

Unsupervised Extractive Dialogue Summarization in Hyperdimensional Space

We present HyperSum, an extractive summarization framework that captures both the efficiency of traditional lexical summarization and the accuracy of contemporary neural approaches. HyperSum exploits the pseudo-orthogonality that emerges when randomly initializing vectors at extremely high dimensions ("blessing of dimensionality") to construct representative and efficient sentence embeddings. Simply clustering the obtained embeddings and extracting their medoids yields competitive summaries. HyperSum often outperforms state-of-the-art summarizers -- in terms of both summary accuracy and faithfulness -- while being 10 to 100 times faster. We open-source HyperSum as a strong baseline for unsupervised extractive summarization.

Unsupervised Dialogue Topic Segmentation in Hyperdimensional Space

We present HyperSeg, a hyperdimensional computing (HDC) approach to unsupervised dialogue topic segmentation. HDC is a class of vector symbolic architectures that leverages the probabilistic orthogonality of randomly drawn vectors at extremely high dimensions (typically over 10,000). HDC generates rich token representations through its low-cost initialization of many unrelated vectors. This is especially beneficial in topic segmentation, which often operates as a resource-constrained pre-processing step for downstream transcript understanding tasks. HyperSeg outperforms the current state-of-the-art in 4 out of 5 segmentation benchmarks -- even when baselines are given partial access to the ground truth -- and is 10 times faster on average. We show that HyperSeg also improves downstream summarization accuracy. With HyperSeg, we demonstrate the viability of HDC in a major language task. We open-source HyperSeg to provide a strong baseline for unsupervised topic segmentation.

Toward a Better Understanding of Loss Functions for Collaborative Filtering

Collaborative filtering (CF) is a pivotal technique in modern recommender systems. The learning process of CF models typically consists of three components: interaction encoder, loss function, and negative sampling. Although many existing studies have proposed various CF models to design sophisticated interaction encoders, recent work shows that simply reformulating the loss functions can achieve significant performance gains. This paper delves into analyzing the relationship among existing loss functions. Our mathematical analysis reveals that the previous loss functions can be interpreted as alignment and uniformity functions: (i) the alignment matches user and item representations, and (ii) the uniformity disperses user and item distributions. Inspired by this analysis, we propose a novel loss function that improves the design of alignment and uniformity considering the unique patterns of datasets called Margin-aware Alignment and Weighted Uniformity (MAWU). The key novelty of MAWU is two-fold: (i) margin-aware alignment (MA) mitigates user/item-specific popularity biases, and (ii) weighted uniformity (WU) adjusts the significance between user and item uniformities to reflect the inherent characteristics of datasets. Extensive experimental results show that MF and LightGCN equipped with MAWU are comparable or superior to state-of-the-art CF models with various loss functions on three public datasets.

uCTRL: Unbiased Contrastive Representation Learning via Alignment and Uniformity for Collaborative Filtering

Because implicit user feedback for the collaborative filtering (CF) models is biased toward popular items, CF models tend to yield recommendation lists with popularity bias. Previous studies have utilized inverse propensity weighting (IPW) or causal inference to mitigate this problem. However, they solely employ pointwise or pairwise loss functions and neglect to adopt a contrastive loss function for learning meaningful user and item representations. In this paper, we propose Unbiased ConTrastive Representation Learning (uCTRL), optimizing alignment and uniformity functions derived from the InfoNCE loss function for CF models. Specifically, we formulate an unbiased alignment function used in uCTRL. We also devise a novel IPW estimation method that removes the bias of both users and items. Despite its simplicity, uCTRL equipped with existing CF models consistently outperforms state-of-the-art unbiased recommender models, up to 12.22% for Recall@20 and 16.33% for NDCG@20 gains, on four benchmark datasets.

PillarAcc: Sparse PointPillars Accelerator for Real-Time Point Cloud 3D Object Detection on Edge Devices

3D object detection using point cloud (PC) data is vital for autonomous driving perception pipelines, where efficient encoding is key to meeting stringent resource and latency requirements. PointPillars, a widely adopted bird's-eye view (BEV) encoding, aggregates 3D point cloud data into 2D pillars for high-accuracy 3D object detection. However, most state-of-the-art methods employing PointPillar overlook the inherent sparsity of pillar encoding, missing opportunities for significant computational reduction. In this study, we propose a groundbreaking algorithm-hardware co-design that accelerates sparse convolution processing and maximizes sparsity utilization in pillar-based 3D object detection networks. We investigate sparsification opportunities using an advanced pillar-pruning method, achieving an optimal balance between accuracy and sparsity. We introduce PillarAcc, a state-of-the-art sparsity support mechanism that enhances sparse pillar convolution through linear complexity input-output mapping generation and conflict-free gather-scatter memory access. Additionally, we propose dataflow optimization techniques, dynamically adjusting the pillar processing schedule for optimal hardware utilization under diverse sparsity operations. We evaluate PillarAcc on various cutting-edge 3D object detection networks and benchmarks, achieving remarkable speedup and energy savings compared to representative edge platforms, demonstrating record-breaking PointPillars speed of 500FPS with minimal compromise in accuracy.

Teacher Intervention: Improving Convergence of Quantization Aware Training for Ultra-Low Precision Transformers

Pre-trained Transformer models such as BERT have shown great success in a wide range of applications, but at the cost of substantial increases in model complexity. Quantization-aware training (QAT) is a promising method to lower the implementation cost and energy consumption. However, aggressive quantization below 2-bit causes considerable accuracy degradation due to unstable convergence, especially when the downstream dataset is not abundant. This work proposes a proactive knowledge distillation method called Teacher Intervention (TI) for fast converging QAT of ultra-low precision pre-trained Transformers. TI intervenes layer-wise signal propagation with the intact signal from the teacher to remove the interference of propagated quantization errors, smoothing loss surface of QAT and expediting the convergence. Furthermore, we propose a gradual intervention mechanism to stabilize the recovery of subsections of Transformer layers from quantization. The proposed schemes enable fast convergence of QAT and improve the model accuracy regardless of the diverse characteristics of downstream fine-tuning tasks. We demonstrate that TI consistently achieves superior accuracy with significantly lower fine-tuning iterations on well-known Transformers of natural language processing as well as computer vision compared to the state-of-the-art QAT methods.