19296 papers
The intersection of computer science and artificial intelligence represents one of the most rapidly evolving frontiers in modern research. This field explores how machines learn from data to solve complex problems, from recognizing patterns in images to generating human-like text. While the underlying mathematics can be dense, the potential applications touch nearly every aspect of daily life, reshaping industries and redefining what is computationally possible.
At Gist.Science, we monitor every new preprint in this category as it appears on arXiv, the primary repository for these breakthroughs. Our team processes each submission immediately, offering both accessible plain-language overviews and detailed technical summaries to ensure the research is understandable for everyone, regardless of their background. This dual approach bridges the gap between raw data and public understanding.
Below are the latest papers in the computer science and artificial intelligence category, freshly summarized for your exploration.
This study demonstrates that while large language models can be equally effective at convincing people to believe or disbelieve conspiracy theories depending on their instructions, implementing accurate information guardrails and leveraging specific model capabilities can significantly mitigate the risk of AI-driven misinformation.
This paper proposes Quality-Aware Robust Multi-View Clustering (QARMVC), a novel framework that addresses heterogeneous observation noise by quantifying instance-level data quality through reconstruction discrepancies and integrating these scores into a hierarchical learning strategy to adaptively suppress noise propagation and construct a robust global consensus.
This study presents a YOLO-based deep learning framework integrated with High-Resolution Class Activation Mapping (HiResCAM) to achieve over 96% accuracy in the automated, interpretable identification of Ichneumonoidea wasp families from high-resolution images, thereby addressing the challenges of manual taxonomic identification in biodiversity and biological control programs.
RegNetAgents is an AI-driven multi-agent framework that integrates bulk tumor and single-cell gene regulatory networks to systematically identify, rank, and interpret cancer-specific regulatory drivers with high statistical significance and biological relevance.
The paper proposes LBA, a sampling-based method that iteratively integrates prior and posterior knowledge to construct an approximate distribution of high-quality adversarial examples, thereby significantly outperforming existing greedy approaches in generating semantically preserved hard-label adversarial texts under low query budgets.
This paper introduces Token Time Continuous Diffusion (TTCD), a continuous-space diffusion language model that utilizes per-token time scheduling to deterministically map noise to tokens, achieving superior performance in conditional generation and high-speed inference compared to existing discrete models.
Polestar is a training-free inference framework that leverages token representation drift as a unified signal to enable efficient KV-cache reuse and reliable token commitment, thereby significantly improving both the accuracy and throughput of diffusion large language models.
This paper introduces "tool efficiency" and "marginal tool utility" as new quantitative metrics to directly evaluate and optimize the rate of useful tool calls in LLM agent trajectories, aiming to guide the creation of leaner tool suites that complement traditional accuracy-based evaluations.
This paper challenges the assumption that sophisticated prompting techniques enhance Large Language Model performance by demonstrating through a comprehensive empirical study that baseline prompting consistently outperforms complex methods, with only minimal expert or inductive framing yielding slight improvements, thereby suggesting the field should prioritize genuine model advancement over prompt engineering.
The paper introduces MAPS, a novel multi-agent framework that balances individual subjective perspectives with shared meaning in dialogue by utilizing domain-weighted profiles, dynamic memory, and interpretable attention, thereby enabling cognitively distinct agents to achieve semantic alignment without sacrificing diversity.