6222 papers
This study leverages Large Language Models and ontology-based techniques to extract phenotypes and outcome labels from electronic medical records, enabling a Random Survival Forest model to achieve significant improvements in predicting chemotherapy outcomes for breast cancer and other cancer types.
This study evaluates seven open-source large language models for assisting Japanese pathology report writing, finding that while thinking and medical-specialized models excel in structured reporting and typo correction, their utility varies by task and rater preference, suggesting they are beneficial in specific, clinically relevant scenarios.
This paper introduces a novel framework that integrates survival analysis with classification techniques to develop early risk prediction models for five common chronic diseases, demonstrating performance comparable to or better than state-of-the-art models while providing clinically validated explanations.
This paper demonstrates that while providing Vision-Language Models with accurate symbolic representations significantly improves their performance in interactive environments, the benefits are contingent upon the models' ability to reliably extract these symbols from visual inputs, highlighting perception quality as a critical bottleneck for future VLM-based agents.
This paper presents a comprehensive security analysis of the autonomous LLM agent OpenClaw using a novel five-layer lifecycle framework to identify systemic threats like prompt injection and memory poisoning, while proposing holistic defense strategies to address the limitations of existing point-based security mechanisms.
This paper presents the first systematic study of cross-persistence diagram density, establishing its theoretical foundations and introducing a novel machine learning framework that leverages these diagrams to effectively distinguish point clouds from different manifolds, with experiments demonstrating that adding noise can further enhance classification performance.
MedPruner is a training-free, model-agnostic hierarchical token pruning framework that eliminates anatomical redundancy in 3D medical vision-language models through inter-slice filtering and dynamic token selection, enabling significant computational efficiency while maintaining or improving performance with fewer than 5% of visual tokens.
The paper introduces VisDoT, a framework that enhances visual reasoning in large vision-language models by formalizing human-like perceptual grounding tasks and employing a Decomposition-of-Thought prompting strategy to separate visual perception from logical reasoning, achieving state-of-the-art performance on chart understanding benchmarks.
The paper introduces HouseMind, a multimodal large language model that unifies the understanding, generation, and editing of architectural floor plans by employing discrete room-instance tokens to bridge visual layouts with symbolic reasoning, thereby achieving superior geometric validity and controllability.
The paper proposes IDRL, an individual-aware multimodal framework that disentangles representations into depression-related and unrelated spaces while dynamically fusing features based on individual differences to overcome inter-modal inconsistencies and improve robust depression diagnosis.
This paper introduces Stable Spike, a hardware-friendly method that employs bitwise AND operations to decouple stable spike skeletons from noisy multi-timestep maps and enforce dual consistency, thereby significantly improving the accuracy and generalization of Spiking Neural Networks for ultra-low latency neuromorphic object recognition.
This perspective paper argues that effective human-agent collaboration requires shifting from reactive, step-by-step control to a "simulation-in-the-loop" paradigm, which empowers users to explore simulated future trajectories and make informed decisions based on foresight rather than just immediate correction.
This paper proposes an agentic pipeline that leverages Large Language Models to automatically synthesize programmatic rubrics for transforming complex, heterogeneous clinical data into standardized formats, thereby enabling sample-efficient supervised learning that outperforms traditional models and larger foundation models while offering significant advantages in auditability and deployment cost.
This paper argues that standard policy gradient algorithms inadvertently reduce trajectory diversity by lowering entropy during training, and proposes new entropy-preserving methods like REPO and ADAPO to actively control entropy, thereby maintaining diversity and improving both final performance and the capacity for sequential learning.
This paper proposes a novel causal prosody mediation framework for FastSpeech2 that employs counterfactual training and structural causal modeling to disentangle emotional prosody from linguistic content, thereby enabling improved controllability, expressiveness, and emotion rendering in text-to-speech synthesis.
The paper introduces SemBench, a scalable and language-independent framework that automatically generates synthetic benchmarks using dictionary definitions and sentence encoders to efficiently evaluate the semantic understanding of large language models across different languages.
This paper proposes an Explicit Logic Channel that runs in parallel with black-box Multimodal Large Language Models to perform explicit logical reasoning and probabilistic inference, enabling zero-shot model validation, selection, and performance enhancement through a Consistency Rate metric without requiring ground-truth annotations.
STAIRS-Former is a novel transformer architecture for offline multi-task multi-agent reinforcement learning that leverages spatio-temporal attention, an interleaved recursive structure, and token dropout to effectively handle varying agent populations and long-horizon dependencies, achieving state-of-the-art performance across diverse benchmarks.
This paper introduces OSCBench, a novel benchmark derived from instructional cooking data that evaluates the ability of text-to-video models to generate accurate and temporally consistent object state changes, revealing that current models struggle significantly with this capability despite their progress in other areas.
This paper introduces the "Agent Scaling Law" and the AgentProfile framework to demonstrate that the capabilities of educational AI agents scale predictably with structured profile richness—specifically role clarity, skill depth, tool completeness, runtime capability, and educator expertise—rather than solely through increased model size, as validated by the EduClaw platform's deployment of over 330 agent profiles.