21916 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 paper extends Probabilities of Causation to multi-valued treatments and outcomes by introducing equivalence classes and a replaceability principle to derive sound, closed-form bounds that are empirically tighter and computationally simpler than existing recursive methods.
This systematic review of 62 papers on human-AI co-creative systems identifies key design dimensions and 24 considerations, finding that high user control and adaptive proactive behaviors significantly enhance collaboration, trust, and ownership while highlighting gaps in supporting early creative phases.
This paper demonstrates that billion-parameter language models can achieve state-exact, trace-preserving deletion by replaying training from a token store excluding specific examples, provided the original execution was instrumented to record provenance and an uncontaminated checkpoint is retained, though this method does not guarantee computational efficiency for dispersed deletion requests.
This paper introduces Code-Switching In-Context Learning (CSICL), an inference-time mechanism that gradually transitions from target languages to English to align non-English inputs with English-centric reasoning spaces, thereby significantly improving multilingual LLM performance across diverse languages and low-resource settings.
The paper introduces StarEmbed, a new benchmark for evaluating time series foundation models on irregularly sampled astronomical light curves, demonstrating that while domain-specific baselines remain superior for classification, pre-trained models like Chronos achieve state-of-the-art performance in clustering and out-of-distribution detection.
This paper introduces DiffGRM, a diffusion-based generative recommendation model that overcomes the limitations of autoregressive methods by employing a masked discrete diffusion framework with specialized tokenization, training, and inference strategies to enable bidirectional context and balanced supervision for improved recommendation accuracy.
The paper introduces CityRiSE, a novel framework that leverages reinforcement learning with carefully curated multi-modal data and verifiable rewards to enhance Large Vision-Language Models' ability to perform accurate, interpretable, and generalizable reasoning for urban socio-economic status prediction across diverse and unseen contexts.
RadarGen is a diffusion-based framework that synthesizes realistic automotive radar point clouds from multi-view camera imagery by leveraging BEV-aligned visual, semantic, and motion cues to bridge the domain gap for multimodal generative simulation.
The paper introduces LAMaS, a novel framework that reduces end-to-end latency in multi-agent systems by learning latency-aware execution graphs with critical-path credit assignment during training and employing a lightweight adaptive controller to eliminate redundant interactions during inference, achieving over 50% latency reduction while maintaining task accuracy.
This paper introduces SOOPER, a safe reinforcement learning framework that leverages conservative policy priors and probabilistic dynamics models to guarantee safety during online exploration while achieving optimal convergence and outperforming state-of-the-art methods on both benchmarks and real-world hardware.