Training with differential privacy (DP) provides a guarantee to members in a dataset that they cannot be identified by users of the released model. However, tho...
Sketches are simple human hand-drawn abstractions of complex scenes and real-world objects. Although the field of sketch representation learning has advanced si...
Tokenizer adaptation plays an important role in transferring pre-trained language models to new domains or languages. In this work, we address two complementary...
While recent developments in large language models have improved bias detection and classification, sensitive subjects like religion still present challenges be...
Mixture-of-Experts (MoE), while offering significant advantages as a Large Language Model (LLM) architecture, faces substantial challenges when deployed on low-...
Automated verification tools based on SMT solvers have made significant progress in verifying complex software systems. However, these tools face a fundamental ...
Efficient simulation of complex plasma dynamics is crucial for advancing fusion energy research. Particle-in-Cell (PIC) Monte Carlo (MC) simulations provide ins...
The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuro...
Spiking neural networks (SNNs) have emerged as a promising direction in both computational neuroscience and artificial intelligence, offering advantages such as...
Transformer decoders have achieved strong results across tasks, but the memory required for the KV cache becomes prohibitive at long sequence lengths. Although ...
Machine learning for early prediction in medicine has recently shown breakthrough performance, however, the focus on improving prediction accuracy has led to a ...
Modern software systems increasingly strain traditional codebase organization strategies. Monorepos offer consistency but often suffer from scalability issues a...
This paper discusses the challenges encountered when analyzing the energy efficiency of synthetic benchmarks and the Gromacs package on the Fritz and Alex HPC c...
Much recent work on distributed quantum computing have focused on the use of entangled pairs and distributed two qubit gates. But there has also been work on ef...
Recent developments in large language models (LLMs) have introduced new requirements for efficient and robust training. As LLM clusters scale, node failures, le...
This paper presents a formalized analysis of the sigmoid function and a fully mechanized proof of the Universal Approximation Theorem (UAT) in Isabelle/HOL, a h...
Molecular Dynamics simulations can help scientists to gather valuable insights for physical processes on an atomic scale. This work explores various techniques ...
In this paper, we propose a double-edge-assisted computation offloading and resource allocation scheme tailored for space-air-marine integrated networks (SAMINs...
Novice programmers often face challenges in fault localization due to their limited experience and understanding of programming syntax and logic. Traditional me...
Large language model (LLM)-based techniques have achieved notable progress in generating harnesses for program fuzzing. However, applying them to arbitrary func...
The architectural shift to prefill/decode (PD) disaggregation in LLM serving improves resource utilization but struggles with the bursty nature of modern worklo...
Graph classification is a fundamental task in domains ranging from molecular property prediction to materials design. While graph neural networks (GNNs) achieve...
Vibe coding is a new programming paradigm in which human engineers instruct large language model (LLM) agents to complete complex coding tasks with little super...
We propose MagicQuill V2, a novel system that introduces a layered composition paradigm to generative image editing, bridging the gap between the sema...
