The user of Engineering Manuals (EM) finds it difficult to read EM s because they are long, have a dense format which includes written documents, step by step p...
Modern deep learning methods typically treat image sequences as large tensors of sequentially stacked frames. However, is this straightforward representation id...
Industrial recommender systems face two fundamental limitations under the log-driven paradigm: (1) knowledge poverty in ID-based item representations that cause...
The increasing integration of AI tools in education has led prior research to explore their impact on learning processes. Nevertheless, most existing studies fo...
Methods that use Large Language Models (LLM) as planners for embodied instruction following tasks have become widespread. To successfully complete tasks, the LL...
In hard-label black-box adversarial attacks, where only the top-1 predicted label is accessible, the prohibitive query complexity poses a major obstacle to prac...
Large language models (LLMs) are increasingly used in software development, but their level of software security expertise remains unclear. This work systematic...
Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise t...
Human infants, with only a few hundred hours of speech exposure, acquire basic units of new languages, highlighting a striking efficiency gap compared to the da...
We demonstrate how to formally specify distributed algorithms as declarative axiomatic theories in a modal logic. We exhibit the method on a simple voting proto...
Large language models (LLMs) are increasingly deployed as conversational assistants in open-domain, multi-turn settings, where users often provide incomplete or...
Current Large Language Models (LLMs) safety approaches focus on explicitly harmful content while overlooking a critical vulnerability: the inability to understa...
Healthcare AI needs large, diverse datasets, yet strict privacy and governance constraints prevent raw data sharing across institutions. Federated learning (FL)...
Large Language Models (LLMs) are widely used for automated code generation, yet their apparent successes often mask a tension between pretraining objectives and...
Higher-order interactions beyond pairwise relationships in large complex networks are often modeled as hypergraphs. Analyzing hypergraph properties such as tria...
Distributed attention is a fundamental problem for scaling context window for Large Language Models (LLMs). The state-of-the-art method, Ring-Attention, suffers...
As foundation models grow in size, fine-tuning them becomes increasingly expensive. While GPU spot instances offer a low-cost alternative to on-demand resources...
Locating the files and functions requiring modification in large open-source software (OSS) repositories is challenging due to their scale and structural comple...
The rapid growth of large language models (LLMs) and the continuous release of new GPU products have significantly increased the demand for distributed training...
Free-viewpoint video (FVV) enables immersive viewing experiences by allowing users to view scenes from arbitrary perspectives. As a prominent reconstruction tec...
Extending well-structured transition systems to incorporate a probabilistic scheduling rule, we define a new class of stochastic well-structured transition syst...
Hybrid AI-HPC workflows combine large-scale simulation, training, high-throughput inference, and tightly coupled, agent-driven control within a single execution...
As LLMs advance their reasoning capabilities about the physical world, the absence of rigorous benchmarks for evaluating their ability to generate scientificall...
While Ethereum has successfully achieved dynamic availability together with safety, a fundamental delay remains between transaction execution and immutable fina...
