Related papers: Towards Cold-Start Drafting and Continual Refining…

Kernel methods provide an elegant and principled approach to nonparametric learning, but so far could hardly be used in large scale problems, since na\"ive implementations scale poorly with data size. Recent advances have shown the benefits…

Applying a pre-trained large model to downstream tasks is prohibitive under resource-constrained conditions. Recent dominant approaches for addressing efficiency issues involve adding a few learnable parameters to the fixed backbone model.…

The scalability of large language models for long-context reasoning is severely constrained by the linear growth of their Transformer key-value cache, which incurs significant memory and computational costs. We posit that as a model…

Large Language Models (LLMs) have shown promise for automated vulnerability repair (AVR), but they still face several limitations, including the lack of intra-vulnerability experience accumulation and the lack of cross-vulnerability…

Statefulness is essential for large language model (LLM) agents to perform long-term planning and problem-solving. This makes memory a critical component, yet its management and evolution remain largely underexplored. Existing evaluations…

It has become standard to solve NLP tasks by fine-tuning pre-trained language models (LMs), especially in low-data settings. There is minimal theoretical understanding of empirical success, e.g., why fine-tuning a model with $10^8$ or more…

Kernel machines have sustained continuous progress in the field of quantum chemistry. In particular, they have proven to be successful in the low-data regime of force field reconstruction. This is because many equivariances and invariances…

This paper proposes ReBNet, an end-to-end framework for training reconfigurable binary neural networks on software and developing efficient accelerators for execution on FPGA. Binary neural networks offer an intriguing opportunity for…

Deploying Transformer-based large language models (LLMs) on resource-constrained edge devices for long-sequence tasks remains challenging due to the quadratic time complexity of self-attention and growing Key-Value (KV) cache demands. While…

In the past decade, we have witnessed a dramatically increasing volume of data collected from varied sources. The explosion of data has transformed the world as more information is available for collection and analysis than ever before. To…

Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images. Among these methods, explicit kernel estimation approaches have demonstrated unprecedented…

Kernel methods provide a flexible and theoretically grounded approach to nonlinear and nonparametric learning. While memory and run-time requirements hinder their applicability to large datasets, many low-rank kernel approximations, such as…

Deep neural networks (DNNs) are reshaping the field of information processing. With their exponential growth challenging existing electronic hardware, optical neural networks (ONNs) are emerging to process DNN tasks in the optical domain…

Neural Processing Units (NPUs) are key to enabling efficient AI inference in resource-constrained edge environments. While peak tera operations per second (TOPS) is often used to gauge performance, it poorly reflects real-world performance…

The deployment of intelligent reinforcement learning (RL) agents on resource-constrained edge devices remains a fundamental challenge due to the substantial memory, computational, and energy requirements of modern deep learning systems.…

Many edge devices employ Recurrent Neural Networks (RNN) to enhance their product intelligence. However, the increasing computation complexity poses challenges for performance, energy efficiency and product development time. In this paper,…

Dynamic convolution learns a linear mixture of n static kernels weighted with their input-dependent attentions, demonstrating superior performance than normal convolution. However, it increases the number of convolutional parameters by n…

The computational complexity of kernel methods has often been a major barrier for applying them to large-scale learning problems. We argue that this barrier can be effectively overcome. In particular, we develop methods to scale up kernel…

We present the first end-to-end deployment of the Gemma3 family of large language and vision models on a tiled edge dataflow architecture (AMD Ryzen AI NPU). Our work introduces a set of hardware-aware techniques. For prefill, we introduce…

Performing Retrieval-Augmented Generation (RAG) directly on mobile devices is promising for data privacy and responsiveness but is hindered by the architectural constraints of mobile NPUs. Specifically, current hardware struggles with the…