9092 papers
This paper presents a task-based model demonstrating that while generative AI homogenizes individual skills, it can simultaneously increase aggregate inequality by shifting economic value toward concentrated complementary assets, with the net outcome determined by the technology's structure and labor market institutions rather than a single universal verdict.
The paper introduces CBR-to-SQL, a Case-Based Reasoning framework that improves Text-to-SQL generation in healthcare by utilizing abstract case templates and a two-stage retrieval process to achieve higher accuracy, sample efficiency, and robustness compared to standard Retrieval-Augmented Generation methods on the MIMICSQL dataset.
PRISM is an instruction-conditioned framework that integrates imitation learning with reinforcement learning and human feedback to efficiently refine generic robotic manipulation policies into robust, fine-grained behaviors for new goals and constraints.
This paper introduces Tool-Genesis, a diagnostic benchmark designed to evaluate and quantify the capabilities of self-evolving language agents in autonomously creating and utilizing tools from abstract requirements, revealing that even state-of-the-art models struggle with interface precision and logic execution, which leads to significant downstream performance degradation.
This study proposes and validates a GeoAI hybrid framework integrating MGWR, Random Forest, and ST-GCN to effectively model the spatiotemporal heterogeneity of multimodal traffic flows and their interaction with land use, demonstrating superior predictive accuracy and revealing distinct urban traffic typologies that underscore the critical role of local morphological context in mobility planning.
This paper demonstrates that pretraining tokenizers with an autoencoding objective before training dynamics models significantly enhances the computational efficiency and accuracy of physics foundation models, particularly when the pretraining data aligns with the downstream physical system.
DreamCAD is a multi-modal generative framework that enables scalable, high-fidelity CAD generation by representing editable BReps as differentiable parametric surfaces for training on unannotated 3D meshes, while also introducing the large-scale CADCap-1M dataset to advance text-to-CAD research.
This paper demonstrates that the topology of service-dependency graphs fundamentally determines the stability and scalability of decentralized, price-based resource allocation in real-time AI service economies, proposing a hybrid architecture that encapsulates complex sub-graphs to significantly reduce price volatility while maintaining throughput and matching centralized allocation quality.
The paper introduces RACAS, a robot-agnostic agentic system that uses natural language communication between LLM/VLM-based modules to control diverse robotic platforms without requiring code modifications or retraining, successfully demonstrating its effectiveness across wheeled, multi-jointed, and underwater robots.
This paper proposes Adversarial Batch Representation Augmentation (ABRA), a domain generalization framework that synthesizes worst-case bio-batch perturbations via structured uncertainty modeling and angular geometric margins to achieve state-of-the-art batch correction and generalization in high-content cellular screening without relying on additional prior knowledge.
This paper introduces the Post Fusion Stabilizer (PFS), a lightweight, plug-and-play module that enhances the robustness of existing camera-LiDAR fusion 3D detectors against domain shifts and sensor failures by stabilizing bird's-eye view feature statistics and adaptively correcting degraded cues without requiring architectural changes or retraining.
The paper introduces SCOUT, a computationally efficient method for open-world interactive object search that leverages 3D scene graphs and relational heuristics distilled from large language models to outperform embedding-based approaches while matching LLM-level performance in both simulation and real-world environments.
This study demonstrates that large language models' moral judgments are highly fragile and manipulable, as they are significantly more influenced by narrative perspective, persuasion cues, and evaluation protocols than by the underlying moral substance of a dilemma.
This paper presents an algorithmic audit of TikTok revealing that while the platform technically complies with the Digital Service Act's ban on profiled advertising to minors, it effectively circumvents this protection by delivering highly personalized, often undisclosed influencer marketing content to adolescents, thereby highlighting the urgent need to expand the regulatory definition of "advertisement" to cover such commercial practices.
This paper introduces Implicit Error Counting (IEC), a reference-free reinforcement learning post-training method that enumerates and weights errors to generate rewards, demonstrating superior performance over Rubrics as Rewards (RaR) in virtual try-on tasks where multiple valid outputs exist and ideal reference answers are unavailable.
This paper introduces SecureRAG-RTL, a novel Retrieval-Augmented Generation framework that significantly improves hardware vulnerability detection in HDL designs by integrating domain-specific knowledge retrieval with large language models, achieving an average 30% increase in accuracy while also releasing a new benchmark dataset of 14 annotated designs.
This paper introduces a novel pseudo-3D longitudinal inpainting framework based on Denoising Diffusion Probabilistic Models and Region-Aware Diffusion that significantly outperforms state-of-the-art baselines in perceptual fidelity, temporal stability, and processing speed for removing evolving lesions from brain MRI scans.
The paper introduces Ptychi-Evolve, an autonomous framework that leverages large language models and evolutionary mechanisms to automatically discover and evolve novel regularization algorithms for ptychography, achieving significant reconstruction quality improvements across diverse imaging datasets.
The paper introduces the CoT-Control evaluation suite to demonstrate that current reasoning models possess significantly lower controllability over their chains of thought compared to their final outputs, suggesting that CoT monitoring remains a viable tool for detecting misbehavior despite concerns about models manipulating their internal reasoning processes.
This paper argues that while AI promises to revolutionize climate information, its current reliance on Global North-dominated infrastructure and biased data risks exacerbating global inequality, necessitating a shift toward data-centric development, shared digital public infrastructure, and co-produced knowledge to ensure equitable outcomes.