arXiv:2511.08086v1 Announce Type: cross Abstract: The use of learned dynamics models, also known as world models, can improve the sample efficiency of reinforcement learning. Recent work suggests that the underlying causal graphs of such dynamics models are sparsely connected, with each of the future state variables depending only on a small subset of the current […]
AI-Driven Contribution Evaluation and Conflict Resolution: A Framework & Design for Group Workload Investigation
arXiv:2511.07667v1 Announce Type: new Abstract: The equitable assessment of individual contribution in teams remains a persistent challenge, where conflict and disparity in workload can result in unfair performance evaluation, often requiring manual intervention – a costly and challenging process. We survey existing tool features and identify a gap in conflict resolution methods and AI integration. […]
Comparative Analysis of Large Language Models for the Machine-Assisted Resolution of User Intentions
arXiv:2510.08576v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have emerged as transformative tools for natural language understanding and user intent resolution, enabling tasks such as translation, summarization, and, increasingly, the orchestration of complex workflows. This development signifies a paradigm shift from conventional, GUI-driven user interfaces toward intuitive, language-first interaction paradigms. Rather than manually navigating […]
Hierarchical Direction Perception via Atomic Dot-Product Operators for Rotation-Invariant Point Clouds Learning
arXiv:2511.08240v1 Announce Type: cross Abstract: Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The core of this issue is the disruption of the point cloud’s intrinsic directional characteristics caused by rotational perturbations. Recent […]
Auto-US: An Ultrasound Video Diagnosis Agent Using Video Classification Framework and LLMs
arXiv:2511.07748v1 Announce Type: cross Abstract: AI-assisted ultrasound video diagnosis presents new opportunities to enhance the efficiency and accuracy of medical imaging analysis. However, existing research remains limited in terms of dataset diversity, diagnostic performance, and clinical applicability. In this study, we propose textbfAuto-US, an intelligent diagnosis agent that integrates ultrasound video data with clinical diagnostic […]
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
arXiv:2511.07587v1 Announce Type: new Abstract: Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation with external memory frameworks. Current solutions, which have evolved from retrieval using semantic embeddings to more sophisticated structured knowledge […]
Sparse3DPR: Training-Free 3D Hierarchical Scene Parsing and Task-Adaptive Subgraph Reasoning from Sparse RGB Views
arXiv:2511.07813v1 Announce Type: cross Abstract: Recently, large language models (LLMs) have been explored widely for 3D scene understanding. Among them, training-free approaches are gaining attention for their flexibility and generalization over training-based methods. However, they typically struggle with accuracy and efficiency in practical deployment. To address the problems, we propose Sparse3DPR, a novel training-free framework […]
Procedural Knowledge Improves Agentic LLM Workflows
arXiv:2511.07568v1 Announce Type: new Abstract: Large language models (LLMs) often struggle when performing agentic tasks without substantial tool support, prom-pt engineering, or fine tuning. Despite research showing that domain-dependent, procedural knowledge can dramatically increase planning efficiency, little work evaluates its potential for improving LLM performance on agentic tasks that may require implicit planning. We formalize, […]
Libra-MIL: Multimodal Prototypes Stereoscopic Infused with Task-specific Language Priors for Few-shot Whole Slide Image Classification
arXiv:2511.07941v1 Announce Type: cross Abstract: While Large Language Models (LLMs) are emerging as a promising direction in computational pathology, the substantial computational cost of giga-pixel Whole Slide Images (WSIs) necessitates the use of Multi-Instance Learning (MIL) to enable effective modeling. A key challenge is that pathological tasks typically provide only bag-level labels, while instance-level descriptions […]
Biodose Tools updates for criticality accidents and interlaboratory comparisons
arXiv:2511.07497v1 Announce Type: new Abstract: Purpose: Since its initial release, the aim of Biodose Tools was to offer an easy-to-use platform to perform the mathematical calculations needed in biological dosimetry. This update 3.7.1, mainly focuses on new features related to large-scale emergency responses, like criticality accidents dose estimation and laboratory networks. Material and Methods: Biodose […]
Radar-APLANC: Unsupervised Radar-based Heartbeat Sensing via Augmented Pseudo-Label and Noise Contrast
arXiv:2511.08071v1 Announce Type: cross Abstract: Frequency Modulated Continuous Wave (FMCW) radars can measure subtle chest wall oscillations to enable non-contact heartbeat sensing. However, traditional radar-based heartbeat sensing methods face performance degradation due to noise. Learning-based radar methods achieve better noise robustness but require costly labeled signals for supervised training. To overcome these limitations, we propose […]
Beyond Correctness: Confidence-Aware Reward Modeling for Enhancing Large Language Model Reasoning
arXiv:2511.07483v1 Announce Type: new Abstract: Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However, numerous technical reports indicate that purely rule-based reward RL frequently results in poor-quality reasoning chains or inconsistencies between reasoning processes and […]