The safe deployment of autonomous systems in safety-critical settings requires a paradigm that combines human expertise with AI-driven analysis, especially when anomalies are unforeseen. We introduce AURA (Autonomous Resilience Agent), a collaborative framework for anomaly and fault diagnostics in robotics. AURA integrates large language models (LLMs), a high-fidelity digital twin (DT), and human-in-the-loop interaction to detect and respond to anomalous behavior in real time. The architecture uses two agents with clear roles: (i) a low-level State Anomaly Characterization Agent that monitors telemetry and converts signals into a structured natural-language problem description, and (ii) a high-level Diagnostic Reasoning Agent that conducts a knowledge-grounded dialogue with an operator to identify root causes, drawing on external sources. Human-validated diagnoses are then converted into new training examples that refine the low-level perceptual model. This feedback loop progressively distills expert knowledge into the AI, transforming it from a static tool into an adaptive partner. We describe the framework's operating principles and provide a concrete implementation, establishing a pattern for trustworthy, continually improving human-robot teams.

Elicited performance requirements need to be quantified for compliance in different engineering tasks, e.g., configuration tuning and performance testing. Much existing work has relied on manual quantification, which is expensive and error-prone due to the imprecision. In this paper, we present LQPR, a highly efficient automatic approach for performance requirements quantification.LQPR relies on a new theoretical framework that converts quantification as a classification problem. Despite the prevalent applications of Large Language Models (LLMs) for requirement analytics, LQPR takes a different perspective to address the classification: we observed that performance requirements can exhibit strong patterns and are often short/concise, therefore we design a lightweight linguistically induced matching mechanism. We compare LQPR against nine state-of-the-art learning-based approaches over diverse datasets, demonstrating that it is ranked as the sole best for 75% or more cases with two orders less cost. Our work proves that, at least for performance requirement quantification, specialized methods can be more suitable than the general LLM-driven approaches.

We introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing the environment in a JSON text format, we enable semantic information to be added and edited in a format that both humans and FMs understand, while grounding the robot to existing nodes during planning to avoid infeasible states during deployment. Our proposed framework employs a two stage approach, first mapping the environment alongside an operator with a Vision-FM, then using the SENT-Map representation alongside a natural-language query within an FM for planning. Our experimental results show that semantic-enhancement enables even small locally-deployable FMs to successfully plan over indoor environments.

The rapid adoption of large language models (LLMs) in healthcare has been accompanied by scrutiny of their oversight. Existing monitoring approaches, inherited from traditional machine learning (ML), are task-based and founded on assumed performance degradation arising from dataset drift. In contrast, with LLMs, inevitable model degradation due to changes in populations compared to the training dataset cannot be assumed, because LLMs were not trained for any specific task in any given population. We therefore propose a new organizing principle guiding generalist LLM monitoring that is scalable and grounded in how these models are developed and used in practice: capability-based monitoring. Capability-based monitoring is motivated by the fact that LLMs are generalist systems whose overlapping internal capabilities are reused across numerous downstream tasks. Instead of evaluating each downstream task independently, this approach organizes monitoring around shared model capabilities, such as summarization, reasoning, translation, or safety guardrails, in order to enable cross-task detection of systemic weaknesses, long-tail errors, and emergent behaviors that task-based monitoring may miss. We describe considerations for developers, organizational leaders, and professional societies for implementing a capability-based monitoring approach. Ultimately, capability-based monitoring will provide a scalable foundation for safe, adaptive, and collaborative monitoring of LLMs and future generalist artificial intelligence models in healthcare.

Vision-language models demonstrate unprecedented performance and generalization across a wide range of tasks and scenarios. Integrating these foundation models into robotic navigation systems opens pathways toward building general-purpose robots. Yet, evaluating these models' navigation capabilities remains constrained by costly real-world trials, overly simplified simulations, and limited benchmarks. We introduce NaviTrace, a high-quality Visual Question Answering benchmark where a model receives an instruction and embodiment type (human, legged robot, wheeled robot, bicycle) and must output a 2D navigation trace in image space. Across 1000 scenarios and more than 3000 expert traces, we systematically evaluate eight state-of-the-art VLMs using a newly introduced semantic-aware trace score. This metric combines Dynamic Time Warping distance, goal endpoint error, and embodiment-conditioned penalties derived from per-pixel semantics and correlates with human preferences. Our evaluation reveals consistent gap to human performance caused by poor spatial grounding and goal localization. NaviTrace establishes a scalable and reproducible benchmark for real-world robotic navigation. The benchmark and leaderboard can be found at https://leggedrobotics.github.io/navitrace_webpage/.

Large language models (LLMs) have demonstrated strong performance on function-level code generation benchmarks, yet real-world software development increasingly demands class-level implementations that integrate multiple methods, attributes, and dependencies within authentic project contexts. This gap between benchmark performance and practical utility raises critical questions about LLMs' readiness for production code assistance, particularly regarding their ability to generalize across familiar and novel codebases. We introduce a benchmark derived from real-world open-source repositories, comprising classes divided into seen and unseen partitions to evaluate generalization under practical conditions. We systematically examine how input specification completeness and retrieval-augmented generation affect class-level correctness across multiple state-of-the-art LLMs. Our evaluation reveals a substantial performance gap: while LLMs achieve 84 to 89% correctness on synthetic benchmarks, they attain only 25 to 34% on real-world class tasks, with minimal distinction between familiar and novel codebases. Comprehensive documentation provides marginal improvements (1 to 3%), whereas retrieval augmentation yields greater gains (4 to 7%) by supplying concrete implementation patterns. Error analysis identifies AttributeError, TypeError, and AssertionError as dominant failure modes, with distinct patterns between synthetic and real-world scenarios. These findings provide actionable insights for enhancing context modelling, documentation strategies, and retrieval integration in production code assistance tools.

Virtual try-on aims to synthesize a realistic image of a person wearing a target garment, but accurately modeling garment-body correspondence remains a persistent challenge, especially under pose and appearance variation. In this paper, we propose Voost - a unified and scalable framework that jointly learns virtual try-on and try-off with a single diffusion transformer. By modeling both tasks jointly, Voost enables each garment-person pair to supervise both directions and supports flexible conditioning over generation direction and garment category, enhancing garment-body relational reasoning without task-specific networks, auxiliary losses, or additional labels. In addition, we introduce two inference-time techniques: attention temperature scaling for robustness to resolution or mask variation, and self-corrective sampling that leverages bidirectional consistency between tasks. Extensive experiments demonstrate that Voost achieves state-of-the-art results on both try-on and try-off benchmarks, consistently outperforming strong baselines in alignment accuracy, visual fidelity, and generalization.

Weight decay is a standard regularization technique for training large language models (LLMs). While it is common to assign a uniform decay rate to every layer, this approach overlooks the structural diversity of LLMs and the varying spectral properties across modules. In this paper, we introduce AlphaDecay, a simple yet effective method that adaptively assigns different weight decay strengths to each module of an LLM. Our approach is guided by Heavy-Tailed Self-Regularization (HT-SR) theory, which analyzes the empirical spectral density (ESD) of weight correlation matrices to quantify "heavy-tailedness." Modules exhibiting more pronounced heavy-tailed ESDs, reflecting stronger feature learning, are assigned weaker decay, while modules with lighter-tailed spectra receive stronger decay. Our method leverages tailored weight decay assignments to balance the module-wise differences in spectral properties, leading to improved performance. Extensive pre-training tasks with various model sizes from 60M to 1B demonstrate that AlphaDecay achieves better perplexity and generalization than conventional uniform decay and other adaptive decay baselines. Our code is available at https://github.com/hed-ucas/AlphaDecay.

Large language models (LLMs) have transformed natural language processing, but their reliable deployment requires effective uncertainty quantification (UQ). Existing UQ methods are often heuristic and lack a probabilistic interpretation. This paper begins by providing a theoretical justification for the role of perturbations in UQ for LLMs. We then introduce a dual random walk perspective, modeling input-output pairs as two Markov chains with transition probabilities defined by semantic similarity. Building on this, we propose a fully probabilistic framework based on an inverse model, which quantifies uncertainty by evaluating the diversity of the input space conditioned on a given output through systematic perturbations. Within this framework, we define a new uncertainty measure, Inv-Entropy. A key strength of our framework is its flexibility: it supports various definitions of uncertainty measures, embeddings, perturbation strategies, and similarity metrics. We also propose GAAP, a perturbation algorithm based on genetic algorithms, which enhances the diversity of sampled inputs. In addition, we introduce a new evaluation metric, Temperature Sensitivity of Uncertainty (TSU), which directly assesses uncertainty without relying on correctness as a proxy. Extensive experiments demonstrate that Inv-Entropy outperforms existing semantic UQ methods. The code to reproduce the results can be found at https://github.com/UMDataScienceLab/Uncertainty-Quantification-for-LLMs.

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware capabilities. Existing strategies, such as aggressive quantization, pruning, or remote inference, trade accuracy for efficiency or lead to substantial cost burdens. This position paper introduces a new framework that leverages speculative decoding, previously viewed primarily as a decoding acceleration technique for autoregressive generation of LLMs, as a promising approach specifically adapted for edge computing by orchestrating computation across heterogeneous devices. We propose \acronym, a framework that allows lightweight edge devices to draft multiple candidate tokens locally using diverse draft models, while a single, shared edge server verifies the tokens utilizing a more precise target model. To further increase the efficiency of verification, the edge server batch the diverse verification requests from devices. This approach supports device heterogeneity and reduces server-side memory footprint by sharing the same upstream target model across multiple devices. Our initial experiments with Jetson Orin Nano, Raspberry Pi 4B/5, and an edge server equipped with 4 Nvidia A100 GPUs indicate substantial benefits: 2.2 more system throughput, 2.8 more system capacity, and better cost efficiency, all without sacrificing model accuracy.