Multimodal large language models (MLLMs) have shown strong vision-language reasoning abilities but still lack robust 3D spatial understanding, which is critical for autonomous driving. This limitation stems from two key challenges: (1) the difficulty of constructing accessible yet effective 3D representations without expensive manual annotations, and (2) the loss of fine-grained spatial details in VLMs due to the absence of large-scale 3D vision-language pretraining. To address these challenges, we propose OccVLA, a novel framework that integrates 3D occupancy representations into a unified multimodal reasoning process. Unlike prior approaches that rely on explicit 3D inputs, OccVLA treats dense 3D occupancy as both a predictive output and a supervisory signal, enabling the model to learn fine-grained spatial structures directly from 2D visual inputs. The occupancy prediction are regarded as implicit reasoning processes and can be skipped during inference without performance degradation, thereby adding no extra computational overhead. OccVLA achieves state-of-the-art results on the nuScenes benchmark for trajectory planning and demonstrates superior performance on 3D visual question-answering tasks, offering a scalable, interpretable, and fully vision-based solution for autonomous driving. Recently, end-to-end autonomous driving (Hu et al., 2022; Jiang et al., 2023; contributors, 2023; Hu et al., 2023) has witnessed remarkable advances, driven by increasing demands for real-world deployments.

The effective execution of tests for REST APIs remains a considerable challenge for development teams, driven by the inherent complexity of distributed systems, the multitude of possible scenarios, and the limited time available for test design. Exhaustive testing of all input combinations is impractical, often resulting in undetected failures, high manual effort, and limited test coverage. To address these issues, we introduce RestTSLLM, an approach that uses Test Specification Language (TSL) in conjunction with Large Language Models (LLMs) to automate the generation of test cases for REST APIs. The approach targets two core challenges: the creation of test scenarios and the definition of appropriate input data. The proposed solution integrates prompt engineering techniques with an automated pipeline to evaluate various LLMs on their ability to generate tests from OpenAPI specifications. The evaluation focused on metrics such as success rate, test coverage, and mutation score, enabling a systematic comparison of model performance. The results indicate that the best-performing LLMs - Claude 3.5 Sonnet (Anthropic), Deepseek R1 (Deepseek), Qwen 2.5 32b (Alibaba), and Sabia 3 (Maritaca) - consistently produced robust and contextually coherent REST API tests. Among them, Claude 3.5 Sonnet outperformed all other models across every metric, emerging in this study as the most suitable model for this task. These findings highlight the potential of LLMs to automate the generation of tests based on API specifications.

This work presents a Biomedical Literature Question Answering (Q&A) system based on a Retrieval-Augmented Generation (RAG) architecture, designed to improve access to accurate, evidence-based medical information. Addressing the shortcomings of conventional health search engines and the lag in public access to biomedical research, the system integrates diverse sources, including PubMed articles, curated Q&A datasets, and medical encyclopedias ,to retrieve relevant information and generate concise, context-aware responses. The retrieval pipeline uses MiniLM-based semantic embeddings and FAISS vector search, while answer generation is performed by a fine-tuned Mistral-7B-v0.3 language model optimized using QLoRA for efficient, low-resource training. The system supports both general medical queries and domain-specific tasks, with a focused evaluation on breast cancer literature demonstrating the value of domain-aligned retrieval. Empirical results, measured using BERTScore (F1), show substantial improvements in factual consistency and semantic relevance compared to baseline models. The findings underscore the potential of RAG-enhanced language models to bridge the gap between complex biomedical literature and accessible public health knowledge, paving the way for future work on multilingual adaptation, privacy-preserving inference, and personalized medical AI systems.

Autonomous microrobots in blood vessels could enable minimally invasive therapies, but navigation is challenged by dense, moving obstacles. We propose a real-time path planning framework that couples an analytic geometry global planner (AGP) with two reactive local escape controllers, one based on rules and one based on reinforcement learning, to handle sudden moving obstacles. Using real-time imaging, the system estimates the positions of the microrobot, obstacles, and targets and computes collision-free motions. In simulation, AGP yields shorter paths and faster planning than weighted A* (WA*), particle swarm optimization (PSO), and rapidly exploring random trees (RRT), while maintaining feasibility and determinism. We extend AGP from 2D to 3D without loss of speed. In both simulations and experiments, the combined global planner and local controllers reliably avoid moving obstacles and reach targets. The average planning time is 40 ms per frame, compatible with 25 fps image acquisition and real-time closed-loop control. These results advance autonomous microrobot navigation and targeted drug delivery in vascular environments.

The You Only Look Once (YOLO) architecture is crucial for real-time object detection. However, deploying it in resource-constrained environments such as unmanned aerial vehicles (UAVs) requires efficient transfer learning. Although layer freezing is a common technique, the specific impact of various freezing configurations on contemporary YOLOv8 and YOLOv10 architectures remains unexplored, particularly with regard to the interplay between freezing depth, dataset characteristics, and training dynamics. This research addresses this gap by presenting a detailed analysis of layer-freezing strategies. We systematically investigate multiple freezing configurations across YOLOv8 and YOLOv10 variants using four challenging datasets that represent critical infrastructure monitoring. Our methodology integrates a gradient behavior analysis (L2 norm) and visual explanations (Grad-CAM) to provide deeper insights into training dynamics under different freezing strategies. Our results reveal that there is no universal optimal freezing strategy but, rather, one that depends on the properties of the data. For example, freezing the backbone is effective for preserving general-purpose features, while a shallower freeze is better suited to handling extreme class imbalance. These configurations reduce graphics processing unit (GPU) memory consumption by up to 28% compared to full fine-tuning and, in some cases, achieve mean average precision (mAP@50) scores that surpass those of full fine-tuning. Gradient analysis corroborates these findings, showing distinct convergence patterns for moderately frozen models. Ultimately, this work provides empirical findings and practical guidelines for selecting freezing strategies. It offers a practical, evidence-based approach to balanced transfer learning for object detection in scenarios with limited resources.

Reinforcement learning with verifiable rewards has significantly advanced reasoning in large language models (LLMs), but such signals remain coarse, offering only binary correctness feedback. This limitation often results in inefficiencies, including overly verbose reasoning and high computational cost, while existing solutions often compromise accuracy. To address this, we introduce self-aligned reward (SAR), a self-guided signal that complements verifiable rewards to encourage both reasoning accuracy and efficiency. SAR is defined as the relative perplexity difference between an answer conditioned on the query and the standalone answer, thereby favoring responses that are concise and query-specific. Quantitative analysis reveals that SAR reliably distinguishes answer quality: concise, correct answers score higher than redundant ones, and partially correct answers score higher than entirely incorrect ones. Evaluation on 4 models across 7 benchmarks shows that integrating SAR with prevalent RL algorithms like PPO and GRPO improves accuracy by 4%, while reducing inference cost by 30%. Further analysis demonstrates that SAR achieves a Pareto-optimal trade-off between correctness and efficiency compared to reward signals based on length or self-confidence. We also show that SAR shortens responses while preserving advanced reasoning behaviors, demonstrating its ability to suppress unnecessary elaboration without losing critical reasoning. These results highlight the promise of self-aligned reward as a fine-grained complement to verifiable rewards, paving the way for more efficient and effective LLM training.Figure 1: Training with self-aligned reward enhances both efficiency and accuracy. We present the relative gains in efficiency and accuracy compared to the respective base model in math reasoning benchmarks. Efficiency gain is measured as the drop in average response length. Recently, reinforcement learning (RL) with verifiable rewards has attracted broad attention in LLM training, demonstrating remarkable improvements in reasoning skills (Guo et al., 2025; Jaech et al., 2024). Work done during an internship at Amazon Web Services.

Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. We present, to our knowledge, the first deployment of a Mamba-based neural architecture on a resource-constrained MCU, a fully C-based runtime-free inference engine: MambaLite-Micro. Our pipeline maps a trained PyTorch Mamba model to on-device execution by (1) exporting model weights into a lightweight format, and (2) implementing a handcrafted Mamba layer and supporting operators in C with operator fusion and memory layout optimization. MambaLite-Micro eliminates large intermediate tensors, reducing 83.0% peak memory, while maintaining an average numerical error of only 1.7x10-5 relative to the PyTorch Mamba implementation. When evaluated on keyword spotting(KWS) and human activity recognition (HAR) tasks, MambaLite-Micro achieved 100% consistency with the PyTorch baselines, fully preserving classification accuracy. We further validated portability by deploying on both ESP32S3 and STM32H7 microcontrollers, demonstrating consistent operation across heterogeneous embedded platforms and paving the way for bringing advanced sequence models like Mamba to real-world resource-constrained applications.

Tokenization inefficiency imposes structural disadvantages on morphologically complex, low-resource languages, inflating compute resources and depressing accuracy. We evaluate 10 large language models (LLMs) on AfriMMLU (9,000 MCQA items; 5 subjects; 16 African languages) and show that fertility (tokens/word) reliably predicts accuracy. Higher fertility consistently predicts lower accuracy across all models and subjects. We further find that reasoning models (DeepSeek, o1) consistently outperform non-reasoning peers across high and low resource languages in the AfriMMLU dataset, narrowing accuracy gaps observed in prior generations. Finally, translating token inflation to economics, a doubling in tokens results in quadrupled training cost and time, underscoring the token tax faced by many languages. These results motivate morphologically aware tokenization, fair pricing, and multilingual benchmarks for equitable natural language processing (NLP).

Hospital call centers serve as the primary contact point for patients within a hospital system. They also generate substantial volumes of staff messages as navigators process patient requests and communicate with the hospital offices following the established protocol restrictions and guidelines. This continuously accumulated large amount of text data can be mined and processed to retrieve insights; however, traditional supervised learning approaches require annotated data, extensive training, and model tuning. Large Language Models (LLMs) offer a paradigm shift toward more computationally efficient methodologies for healthcare analytics. This paper presents a multi-stage LLM-based framework that identifies staff message topics and classifies messages by their reasons in a multi-class fashion. In the process, multiple LLM types, including reasoning, general-purpose, and lightweight models, were evaluated. The best-performing model was o3, achieving 78.4% weighted F1-score and 79.2% accuracy, followed closely by gpt-5 (75.3% Weighted F1-score and 76.2% accuracy). The proposed methodology incorporates data security measures and HIPAA compliance requirements essential for healthcare environments. The processed LLM outputs are integrated into a visualization decision support tool that transforms the staff messages into actionable insights accessible to healthcare professionals. This approach enables more efficient utilization of the collected staff messaging data, identifies navigator training opportunities, and supports improved patient experience and care quality.

Large Language Models (LLMs) are increasingly vulnerable to a sophisticated form of adversarial prompting known as camouflaged jailbreaking. This method embeds malicious intent within seemingly benign language to evade existing safety mechanisms. Unlike overt attacks, these subtle prompts exploit contextual ambiguity and the flexible nature of language, posing significant challenges to current defense systems. This paper investigates the construction and impact of camouflaged jailbreak prompts, emphasizing their deceptive characteristics and the limitations of traditional keyword-based detection methods. We introduce a novel benchmark dataset, Camouflaged Jailbreak Prompts, containing 500 curated examples (400 harmful and 100 benign prompts) designed to rigorously stress-test LLM safety protocols. In addition, we propose a multi-faceted evaluation framework that measures harmfulness across seven dimensions: Safety Awareness, Technical Feasibility, Implementation Safeguards, Harmful Potential, Educational Value, Content Quality, and Compliance Score. Our findings reveal a stark contrast in LLM behavior: while models demonstrate high safety and content quality with benign inputs, they exhibit a significant decline in performance and safety when confronted with camouflaged jailbreak attempts. This disparity underscores a pervasive vulnerability, highlighting the urgent need for more nuanced and adaptive security strategies to ensure the responsible and robust deployment of LLMs in real-world applications.