9297 papers
The paper introduces GMM-PIELM, a probabilistic adaptive sampling framework that significantly improves the accuracy and conditioning of Physics-Informed Extreme Learning Machines for stiff PDEs by autonomously concentrating basis function centers in high-error regions like shock fronts, achieving orders-of-magnitude lower errors than baseline methods while retaining rapid closed-form training speeds.
The paper introduces EpisTwin, a neuro-symbolic framework that overcomes data fragmentation in Personal AI by grounding generative reasoning in a verifiable Personal Knowledge Graph derived from multimodal data, utilizing an agentic coordinator for complex reasoning and visual refinement, and validated by a new synthetic benchmark called PersonalQA-71-100.
The paper introduces DEX-AR, a novel dynamic explainability method that generates per-token and sequence-level heatmaps for autoregressive Vision-Language Models by computing layer-wise gradients and employing dynamic filtering to distinguish visually-grounded from linguistic tokens, thereby improving interpretability and performance across multiple benchmarks.
This paper proposes a three-stage post-training pipeline that computes fine-grained entropy-based uncertainty, calibrates them via Platt scaling, and uses reinforcement learning to teach language models to efficiently generate interpretable and well-calibrated uncertainty estimates at test time, outperforming existing post-hoc methods in both performance and generalization.
A four-week field study comparing contextual bandits and Large Language Models for personalized health interventions reveals that while unconstrained LLMs significantly outperform template-based systems in perceived helpfulness due to their ability to acknowledge user context, they fail to systematically explore diverse behavior change techniques, highlighting a critical design trade-off between structured exploration and generative autonomy in reflective AI health systems.
The paper introduces SAHOO, a practical framework that employs a Goal Drift Index, constraint preservation checks, and regression-risk quantification to effectively monitor and control alignment drift while significantly improving performance in recursive self-improving systems across code, reasoning, and truthfulness tasks.
The paper introduces AIRT, an end-to-end deep-learning framework that generates high-quality, deliverable single-arc VMAT prostate treatment plans in under one second directly from CT images and contours, demonstrating non-inferiority to standard clinical planning systems while significantly accelerating workflow efficiency.
K-MaT is a novel prompt-learning framework that enables the zero-shot transfer of large-scale biomedical vision-language models from high-end to low-end imaging modalities by anchoring prompts to clinical text and aligning their decision manifolds via Fused Gromov-Wasserstein optimal transport, thereby achieving state-of-the-art performance while mitigating catastrophic forgetting.
MoEless is a novel serverless serving framework that mitigates expert load imbalance in Mixture-of-Experts (MoE) large language models through proactive load prediction and dynamic scaling, achieving significant reductions in inference latency and cost compared to existing solutions.
The paper introduces the Dynamic Chunking Diffusion Transformer (DC-DiT), a model that adaptively compresses image tokens based on spatial detail and diffusion timesteps to achieve superior generation quality and efficiency over standard DiTs while requiring minimal additional training.
This paper introduces CLAIRE, a hybrid deep learning framework that combines unsupervised latent representation learning with supervised classification and game-theoretic interpretability to achieve robust, explainable fault detection in high-dimensional industrial environments.
This paper introduces ESAA-Security, an event-sourced architecture that transforms AI-assisted security auditing from unreliable free-form LLM conversations into a traceable, reproducible, and verifiable governance pipeline by separating agent cognition from deterministic state mutations to ensure immutable audit trails for AI-generated code.
This paper extends kinetic-based regularization to accurately estimate spatial derivatives from noisy data through explicit and implicit schemes, demonstrating its effectiveness in enabling stable shock capture for 1D hyperbolic PDEs while preserving conservation laws.
This paper introduces a prompt group-aware training framework that enhances the robustness and generalization of text-guided nuclei segmentation by enforcing consistency among semantically related prompts through quality-guided regularization and logit-level constraints, achieving significant performance gains without altering model architecture or inference.
This paper proposes a schema-gated agentic AI architecture that resolves the trade-off between conversational flexibility and execution determinism in scientific workflows by enforcing machine-checkable specifications as mandatory execution boundaries, a solution validated through multi-model LLM scoring of 20 existing systems.
This paper introduces Physical Simulator In-the-loop Video Generation (PSIVG), a framework that integrates a physical simulator and a test-time texture optimization technique into the video diffusion process to generate visually realistic videos that strictly adhere to real-world physical laws like gravity and collision.
This paper proposes a reference architecture for reinforcement learning frameworks by analyzing 18 state-of-the-practice implementations through grounded theory to establish a common basis for comparison, evaluation, and integration.
The paper proposes CLoPA, a continual low-parameter adaptation strategy that efficiently tunes a small fraction of the nnInteractive model on incoming annotation data, rapidly achieving expert-level performance across diverse medical imaging tasks without requiring new parameters or altering the inference pipeline.
This paper investigates the accuracy and potential biases of Large Language Models in abductive reasoning by converting a syllogistic dataset to evaluate their ability to draw tentative conclusions from limited information, aiming to bridge the gap between machine and human cognition beyond formal deduction.
This paper proposes a prosodic-boundary-aware post-training strategy for LLM-based TTS that enables natural streaming generation with incremental text input by learning early stopping at content boundaries and utilizing a sliding-window prompt to prevent long-form collapse, significantly outperforming existing baselines in both short and long-form scenarios.