Related papers: LeCo: Lightweight Compression via Learning Serial …

Large Language Models (LLMs) often generate unnecessarily verbose Chain-of-Thought (CoT) reasoning that increases computational costs and latency without proportional performance gains. In this paper, we propose Fine-grained Group policy…

We propose a new neural network design paradigm Reversible Column Network (RevCol). The main body of RevCol is composed of multiple copies of subnetworks, named columns respectively, between which multi-level reversible connections are…

Despite the substantial advancements demonstrated by learning-based neural models in the LiDAR Point Cloud Compression (LPCC) task, realizing real-time compression - an indispensable criterion for numerous industrial applications - remains…

Effective token compression remains a critical challenge for scaling models to handle increasingly complex and diverse datasets. A novel mechanism based on contextual reinforcement is introduced, dynamically adjusting token importance…

Designing a unified neural network to efficiently and inherently process sequential data with arbitrary lengths is a central and challenging problem in sequence modeling. The design choices in Transformer, including quadratic complexity and…

Efficient data processing is increasingly vital, with query optimizers playing a fundamental role in translating SQL queries into optimal execution plans. Traditional cost-based optimizers, however, often generate suboptimal plans due to…

Reducing dimensionality is a key preprocessing step in many data analysis applications to address the negative effects of the curse of dimensionality and collinearity on model performance and computational complexity, to denoise the data or…

The explosive growth of multi-source multimedia data has significantly increased the demands for transmission and storage, placing substantial pressure on bandwidth and storage infrastructures. While Autoregressive Compression Models (ACMs)…

Modern tensor applications, especially foundation models and generative AI applications require multiple input modalities (both vision and language), which increases the demand for flexible accelerator architecture. Existing frameworks…

Domain-specific large language models (LLMs), typically developed by fine-tuning a pre-trained general-purpose LLM on specialized datasets, represent a significant advancement in applied AI. A common strategy in LLM fine-tuning is…

Entropy coding is widely used in typical learned image compression (LIC) that converts latents into a compact bitstream. However, entropy coding is typically sequential and becomes the coding latency bottleneck. To overcome it, we present…

Recommender systems have advanced markedly over the past decade by transforming each user/item into a dense embedding vector with deep learning models. At industrial scale, embedding tables constituted by such vectors of all users/items…

Constrained codes are used to prevent errors from occurring in various data storage and data transmission systems. They can help in increasing the storage density of magnetic storage devices, in managing the lifetime of electronic storage…

Linear combination is a potent data fusion method in information retrieval tasks, thanks to its ability to adjust weights for diverse scenarios. However, achieving optimal weight training has traditionally required manual relevance…

We propose a software framework based on the ideas of the Learning-Compression (LC) algorithm, that allows a user to compress a neural network or other machine learning model using different compression schemes with minimal effort.…

Data used for analytics and machine learning often take the form of tables with categorical entries. We introduce a family of lossless compression algorithms for such data that proceed in four steps: $(i)$ Estimate latent variables…

Recurrent neural networks (RNNs) have recently achieved remarkable successes in a number of applications. However, the huge sizes and computational burden of these models make it difficult for their deployment on edge devices. A practically…

Large Reasoning Models (LRMs) have achieved remarkable success, yet they often suffer from producing unnecessary and verbose reasoning chains. We identify a core aspect of this issue as "invalid thinking" -- models tend to repeatedly…

Efficient computation in deep neural networks is crucial for real-time object detection. However, recent advancements primarily result from improved high-performing hardware rather than improving parameters and FLOP efficiency. This is…

Handling communication overhead in large-scale tensor-parallel training remains a critical challenge due to the dense, near-zero distributions of intermediate tensors, which exacerbate errors under frequent communication and introduce…