While prompt engineering has emerged as a crucial technique for optimizing large language model performance, the underlying optimization landscape remains poorly understood. Current approaches treat prompt optimization as a black-box problem, applying sophisticated search algorithms without characterizing the landscape topology they navigate. We present a systematic analysis of fitness landscape structures in prompt engineering using autocorrelation analysis across semantic embedding spaces. Through experiments on error detection tasks with two distinct prompt generation strategies -- systematic enumeration (1,024 prompts) and novelty-driven diversification (1,000 prompts) -- we reveal fundamentally different landscape topologies. Systematic prompt generation yields smoothly decaying autocorrelation, while diversified generation exhibits non-monotonic patterns with peak correlation at intermediate semantic distances, indicating rugged, hierarchically structured landscapes. Task-specific analysis across 10 error detection categories reveals varying degrees of ruggedness across different error types. Our findings provide an empirical foundation for understanding the complexity of optimization in prompt engineering landscapes.

We introduce SasAgent, a multi-agent AI system powered by large language models (LLMs) that automates small-angle scattering (SAS) data analysis by leveraging tools from the SasView software and enables user interaction via text input. SasAgent features a coordinator agent that interprets user prompts and delegates tasks to three specialized agents for scattering length density (SLD) calculation, synthetic data generation, and experimental data fitting. These agents utilize LLM-friendly tools to execute tasks efficiently. These tools, including the model data tool, Retrieval-Augmented Generation (RAG) documentation tool, bump fitting tool, and SLD calculator tool, are derived from the SasView Python library. A user-friendly Gradio-based interface enhances user accessibility. Through diverse examples, we demonstrate SasAgent's ability to interpret complex prompts, calculate SLDs, generate accurate scattering data, and fit experimental datasets with high precision. This work showcases the potential of LLM-driven AI systems to streamline scientific workflows and enhance automation in SAS research.

Large Language Models (LLMs) have demonstrated effectiveness across a wide variety of tasks involving natural language, however, a fundamental problem of hallucinations still plagues these models, limiting their trustworthiness in generating consistent, truthful information. Detecting hallucinations has quickly become an important topic, with various methods such as uncertainty estimation, LLM Judges, retrieval augmented generation (RAG), and consistency checks showing promise. Many of these methods build upon foundational metrics, such as ROUGE, BERTScore, or Perplexity, which often lack the semantic depth necessary to detect hallucinations effectively. In this work, we propose a novel approach inspired by ROUGE that constructs an N-Gram frequency tensor from LLM-generated text. This tensor captures richer semantic structure by encoding co-occurrence patterns, enabling better differentiation between factual and hallucinated content. We demonstrate this by applying tensor decomposition methods to extract singular values from each mode and use these as input features to train a multi-layer perceptron (MLP) binary classifier for hallucinations. Our method is evaluated on the HaluEval dataset and demonstrates significant improvements over traditional baselines, as well as competitive performance against state-of-the-art LLM judges.

Membership Inference Attacks (MIAs) have emerged as a principled framework for auditing the privacy of synthetic data generated by tabular generative models, where many diverse methods have been proposed that each exploit different privacy leakage signals. However, in realistic threat scenarios, an adversary must choose a single method without a priori guarantee that it will be the empirically highest performing option. We study this challenge as a decision theoretic problem under uncertainty and conduct the largest synthetic data privacy benchmark to date. Here, we find that no MIA constitutes a strictly dominant strategy across a wide variety of model architectures and dataset domains under our threat model. Motivated by these findings, we propose ensemble MIAs and show that unsupervised ensembles built on individual attacks offer empirically more robust, regret-minimizing strategies than individual attacks.

We introduce a general, scalable computational framework for multi-axis 3D printing based on implicit neural fields (INFs) that unifies all stages of toolpath generation and global collision-free motion planning. In our pipeline, input models are represented as signed distance fields, with fabrication objectives such as support-free printing, surface finish quality, and extrusion control being directly encoded in the optimization of an implicit guidance field. This unified approach enables toolpath optimization across both surface and interior domains, allowing shell and infill paths to be generated via implicit field interpolation. The printing sequence and multi-axis motion are then jointly optimized over a continuous quaternion field. Our continuous formulation constructs the evolving printing object as a time-varying SDF, supporting differentiable global collision handling throughout INF-based motion planning. Compared to explicit-representation-based methods, INF-3DP achieves up to two orders of magnitude speedup and significantly reduces waypoint-to-surface error. We validate our framework on diverse, complex models and demonstrate its efficiency with physical fabrication experiments using a robot-assisted multi-axis system.

Accurate classification of pests and diseases plays a vital role in precision agriculture, enabling efficient identification, targeted interventions, and preventing their further spread. However, current methods primarily focus on binary classification, which limits their practical applications, especially in scenarios where accurately identifying the specific type of disease or pest is essential. We propose a robust deep learning based model for multi-class classification of onion crop diseases and pests. We enhance a pre-trained Convolutional Neural Network (CNN) model by integrating attention based modules and employing comprehensive data augmentation pipeline to mitigate class imbalance. We propose a model which gives 96.90% overall accuracy and 0.96 F1 score on real-world field image dataset. This model gives better results than other approaches using the same datasets.

Segmentation of brain tumors from Magnetic Resonance Imaging (MRI) remains a pivotal challenge in medical image analysis due to the heterogeneous nature of tumor morphology and intensity distributions. Accurate delineation of tumor boundaries is critical for clinical decision-making, radiotherapy planning, and longitudinal disease monitoring. In this study, we perform a comprehensive comparative analysis of two major clustering paradigms applied in MRI tumor segmentation: hard clustering, exemplified by the K-Means algorithm, and soft clustering, represented by Fuzzy C-Means (FCM). While K-Means assigns each pixel strictly to a single cluster, FCM introduces partial memberships, meaning each pixel can belong to multiple clusters with varying degrees of association. Experimental validation was performed using the BraTS2020 dataset, incorporating pre-processing through Gaussian filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE). Evaluation metrics included the Dice Similarity Coefficient (DSC) and processing time, which collectively demonstrated that K-Means achieved superior speed with an average runtime of 0.3s per image, whereas FCM attained higher segmentation accuracy with an average DSC of 0.67 compared to 0.43 for K-Means, albeit at a higher computational cost (1.3s per image). These results highlight the inherent trade-off between computational efficiency and boundary precision.

We introduce Plantbot, a hybrid lifeform that connects a living plant with a mobile robot through a network of large language model (LLM) modules. Each module - responsible for sensing, vision, dialogue, or action - operates asynchronously and communicates via natural language, enabling seamless interaction across biological and artificial domains. This architecture leverages the capacity of LLMs to serve as hybrid interfaces, where natural language functions as a universal protocol, translating multimodal data (soil moisture, temperature, visual context) into linguistic messages that coordinate system behaviors. The integrated network transforms plant states into robotic actions, installing normativity essential for agency within the sensor-motor loop. By combining biological and robotic elements through LLM-mediated communication, Plantbot behaves as an embodied, adaptive agent capable of responding autonomously to environmental conditions. This approach suggests possibilities for a new model of artificial life, where decentralized, LLM modules coordination enable novel interactions between biological and artificial systems.

Detecting and preventing falls in humans is a critical component of assistive robotic systems. While significant progress has been made in detecting falls, the prediction of falls before they happen, and analysis of the transient state between stability and an impending fall remain unexplored. In this paper, we propose a anticipatory fall detection method that utilizes a hybrid model combining Dynamic Graph Neural Networks (DGNN) with Long Short-Term Memory (LSTM) networks that decoupled the motion prediction and gait classification tasks to anticipate falls with high accuracy. Our approach employs real-time skeletal features extracted from video sequences as input for the proposed model. The DGNN acts as a classifier, distinguishing between three gait states: stable, transient, and fall. The LSTM-based network then predicts human movement in subsequent time steps, enabling early detection of falls. The proposed model was trained and validated using the OUMVLP-Pose and URFD datasets, demonstrating superior performance in terms of prediction error and recognition accuracy compared to models relying solely on DGNN and models from literature. The results indicate that decoupling prediction and classification improves performance compared to addressing the unified problem using only the DGNN. Furthermore, our method allows for the monitoring of the transient state, offering valuable insights that could enhance the functionality of advanced assistance systems.

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint, (iii) partial occlusion, and (iv) visual confusion across adjacent classes. To mitigate this degradation, we introduce the Re-Thinking Vision Language Model (RT -VLM) framework. The foundation of this framework is a unique synthetic dataset generation pipeline that produces images annotated with "4-Clues": precise bounding boxes, class names, detailed object-level captions, and a comprehensive context-level caption for the entire scene. We then perform parameter efficient supervised tuning of Llama 3.2 11B Vision Instruct on this resource. At inference time, a two stage Re-Thinking scheme is executed: the model first emits its own four clues, then re examines these responses as evidence and iteratively corrects them. Across robustness benchmarks that isolate individual domain shifts, RT -VLM consistently surpasses strong baselines. These findings indicate that the integration of structured multimodal evidence with an explicit self critique loop constitutes a promising route toward reliable and transferable visual understanding.