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

Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. For example, an AI writing assistant is required to update its suggestions in real time as a document is edited.…

Writing high-performance GPU kernels is among the most labor-intensive tasks in machine learning systems engineering. We present AutoKernel, an open-source framework that applies an autonomous agent loop to GPU kernel optimization for…

Coding agents are increasingly used as general-purpose problem solvers, but their flexibility does not by itself confer the domain expertise needed for specialized tasks. Recent work addresses this through \textit{agent skills}: reusable…

As large language models (LLMs) continue to advance in programming tasks, LLM-driven coding systems have evolved from one-shot code generation into complex systems capable of iterative improvement during inference. However, existing code…

Performance optimization of deep learning models is conducted either manually or through automatic architecture search, or a combination of both. On the other hand, their performance strongly depends on the target hardware and how…

GPU kernel generation by LLMs has recently experienced rapid development, leveraging test-time scaling and reinforcement learning techniques. However, a key challenge for kernel generation is the scarcity of high-quality data, as most…

Quantum kernels hold great promise for offering computational advantages over classical learners, with the effectiveness of these kernels closely tied to the design of the quantum feature map. However, the challenge of designing effective…

Hybrid opto-electronic neural networks combine optical front-ends with electronic back-ends to perform vision tasks, but joint end-to-end (E2E) optimization of optical and electronic components is computationally expensive due to large…

Fine-tuning provides an effective means to specialize pre-trained models for various downstream tasks. However, fine-tuning often incurs high memory overhead, especially for large transformer-based models, such as LLMs. While existing…

Calculating the most efficient schedule of work in a neural network compiler is a difficult task. There are many parameters to be accounted for that can positively or adversely affect that schedule depending on their configuration - How…

While the ``deep reasoning'' paradigm has spurred significant advances in verifiable domains like mathematics, its application to open-ended, creative generation remains a critical challenge. The two dominant methods for instilling…

The usage of neural network models puts multiple objectives in conflict with each other: Ideally we would like to create a neural model that is effective, efficient, and interpretable at the same time. However, in most instances we have to…

In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the…

Dynamic convolution learns a linear mixture of $n$ static kernels weighted with their sample-dependent attentions, demonstrating superior performance compared to normal convolution. However, existing designs are parameter-inefficient: they…

Deep kernel learning aims at designing nonlinear combinations of multiple standard elementary kernels by training deep networks. This scheme has proven to be effective, but intractable when handling large-scale datasets especially when the…

Despite rapid recent progress in the terminal capabilities of large language models, the training data strategies behind state-of-the-art terminal agents remain largely undisclosed. We address this gap through a systematic study of data…

This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms,…

Kernel matrices are crucial in many learning tasks such as support vector machines or kernel ridge regression. The kernel matrix is typically dense and large-scale. Depending on the dimension of the feature space even the computation of all…

Accelerator-based neutrino physics is entering an energy-frontier regime in which interactions reach the TeV scale and produce exceptionally dense, overlapping detector signatures. In this regime, event interpretation becomes impractical…