Much work has been done on conversational LLM agents which directly assist human users with tasks. We present an alternative paradigm for interacting with LLM agents, which we call "overhearing agents". These overhearing agents do not actively participate in conversation -- instead, they "listen in" on human-to-human conversations and perform background tasks or provide suggestions to assist the user. In this work, we explore the overhearing agents paradigm through the lens of Dungeons & Dragons gameplay. We present an in-depth study using large multimodal audio-language models as overhearing agents to assist a Dungeon Master. We perform a human evaluation to examine the helpfulness of such agents and find that some large audio-language models have the emergent ability to perform overhearing agent tasks using implicit audio cues. Finally, we release Python libraries and our project code to support further research into the overhearing agents paradigm at https://github.com/zhudotexe/overhearing_agents.

Federated Learning with client-level differential privacy (DP) provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg struggle when clients have heterogeneous privacy requirements, as they must uniformly enforce the strictest privacy level across clients, leading to excessive DP noise and significant model utility degradation. Existing methods to improve the model utility in such heterogeneous privacy settings often assume a trusted server and are largely heuristic, resulting in suboptimal performance and lacking strong theoretical underpinnings. In this work, we address these challenges under a practical attack model where both clients and the server are honest-but-curious. We propose GDPFed, which partitions clients into groups based on their privacy budgets and achieves client-level DP within each group to reduce the privacy budget waste and hence improve the model utility. Based on the privacy and convergence analysis of GDPFed, we find that the magnitude of DP noise depends on both model dimensionality and the per-group client sampling ratios. To further improve the performance of GDPFed, we introduce GDPFed$^+$, which integrates model sparsification to eliminate unnecessary noise and optimizes per-group client sampling ratios to minimize convergence error. Extensive empirical evaluations on multiple benchmark datasets demonstrate the effectiveness of GDPFed$^+$, showing substantial performance gains compared with state-of-the-art methods.

The limited ability to reason across occupational data from different sources is a long-standing bottleneck for data-driven labour market analytics. Previous research has relied on hand-crafted ontologies that allow such reasoning but are computationally expensive and require careful maintenance by human experts. The rise of language processing machine learning models offers a scalable alternative by learning shared semantic spaces that bridge diverse occupational vocabularies without extensive human curation. We present an embedding-based alignment process that links any free-form German job title to two established ontologies - the German Klassifikation der Berufe and the International Standard Classification of Education. Using publicly available data from the German Federal Employment Agency, we construct a dataset to fine-tune a Sentence-BERT model to learn the structure imposed by the ontologies. The enriched pairs (job title, embedding) define a similarity graph structure that we can use for efficient approximate nearest-neighbour search, allowing us to frame the classification process as a semantic search problem. This allows for greater flexibility, e.g., adding more classes. We discuss design decisions, open challenges, and outline ongoing work on extending the graph with other ontologies and multilingual titles.

Recent breakthroughs in Large Language Models (LLMs) and Large Circuit Models (LCMs) have sparked excitement across the electronic design automation (EDA) community, promising a revolution in circuit design and optimization. Yet, this excitement is met with significant skepticism: Are these AI models a genuine revolution in circuit design, or a temporary wave of inflated expectations? This paper serves as a foundational text for the corresponding ICCAD 2025 panel, bringing together perspectives from leading experts in academia and industry. It critically examines the practical capabilities, fundamental limitations, and future prospects of large AI models in hardware design. The paper synthesizes the core arguments surrounding reliability, scalability, and interpretability, framing the debate on whether these models can meaningfully outperform or complement traditional EDA methods. The result is an authoritative overview offering fresh insights into one of today's most contentious and impactful technology trends.

The ability of Large Language Models (LLMs) to solve complex tasks has made them crucial in the development of AI-based applications. However, the high computational requirements to fine-tune these LLMs on downstream tasks pose significant challenges, particularly when resources are limited. In response to this challenge, we introduce L1RA, a novel technique aimed at dynamically distributing the rank of low-rank adapters during fine-tuning using LoRA. Given a rank budget (i.e., total sum of adapters rank), L1RA leverages L1 regularisation to prune redundant ranks and redistribute them across adapters, thereby optimising resource utilisation. Through a series of comprehensive experiments, we empirically demonstrate that L1RA maintains comparable or even reduced computational overhead compared to other LoRA variants, including the vanilla approach, while achieving same or better performances. Moreover, the post-training analysis of rank distribution unveiled insights into the specific model components requiring the most adaptation to align with the task objective: the feed-forward layers and the attention output projection. These results highlight the efficacy of L1RA in not only enhancing the efficiency of LLM fine-tuning, but also in providing valuable diagnostic information for model refinement and customisation. In conclusion, L1RA stands as a promising technique for advancing the performance and interpretability of LLM adaptation, particularly in scenarios where computational resources are constrained.

Continuous advancements in robotics and AI are driving the integration of robots from industry into everyday environments. However, dynamic and unpredictable human activities in daily lives would directly or indirectly conflict with robot actions. Besides, due to the social attributes of such human-induced conflicts, solutions are not always unique and depend highly on the user's personal preferences. To address these challenges and facilitate the development of household robots, we propose COMMET, a system for human-induced COnflicts in Mobile Manipulation of Everyday Tasks. COMMET employs a hybrid detection approach, which begins with multi-modal retrieval and escalates to fine-tuned model inference for low-confidence cases. Based on collected user preferred options and settings, GPT-4o will be used to summarize user preferences from relevant cases. In preliminary studies, our detection module shows better accuracy and latency compared with GPT models. To facilitate future research, we also design a user-friendly interface for user data collection and demonstrate an effective workflow for real-world deployments.

Personality manipulation in large language models (LLMs) is increasingly applied in customer service and agentic scenarios, yet its mechanisms and trade-offs remain unclear. We present a systematic study of personality control using the Big Five traits, comparing in-context learning (ICL), parameter-efficient fine-tuning (PEFT), and mechanistic steering (MS). Our contributions are fourfold. First, we construct a contrastive dataset with balanced high/low trait responses, enabling effective steering vector computation and fair cross-method evaluation. Second, we introduce a unified evaluation framework based on within-run $Δ$ analysis that disentangles, reasoning capability, agent performance, and demographic bias across MMLU, GAIA, and BBQ benchmarks. Third, we develop trait purification techniques to separate openness from conscientiousness, addressing representational overlap in trait encoding. Fourth, we propose a three-level stability framework that quantifies method-, trait-, and combination-level robustness, offering practical guidance under deployment constraints. Experiments on Gemma-2-2B-IT and LLaMA-3-8B-Instruct reveal clear trade-offs: ICL achieves strong alignment with minimal capability loss, PEFT delivers the highest alignment at the cost of degraded task performance, and MS provides lightweight runtime control with competitive effectiveness. Trait-level analysis shows openness as uniquely challenging, agreeableness as most resistant to ICL, and personality encoding consolidating around intermediate layers. Taken together, these results establish personality manipulation as a multi-level probe into behavioral representation, linking surface conditioning, parameter encoding, and activation-level steering, and positioning mechanistic steering as a lightweight alternative to fine-tuning for both deployment and interpretability.

Timely and accurate floodwater depth estimation is critical for road accessibility and emergency response. While recent computer vision methods have enabled flood detection, they suffer from both accuracy limitations and poor generalization due to dependence on fixed object detectors and task - specific training. To enable accurate depth estimation that can generalize across diverse flood scenarios, t his paper presents FloodVision, a zero - shot framework that combines the semantic reasoning abilities of the foundation v ision - l anguage m odel GPT - 4 o with a structured domain knowledge graph. The knowledge graph encodes canonical real - world dimensions for common urban objects including vehicles, people, and infrastructure elements to ground the model's reasoning in physical reality. FloodVision dynamically identifies visible reference objects in RGB images, retrieves verified heights from the knowledge graph to mitigate hallucination, estimates submergence ratios, and applies statistical outlier filtering to compute final depth values. Evaluated on 110 crowdsourced images from MyCoast New York, FloodVision achieves a mean absolute error of 8.17 cm, re ducing the GPT - 4o - only baseline (10.28 cm) by 20 .5 % and surpassing prior CNN - based methods. The system generalizes well across varying scenes and operates in near real - time, making it suitable for future integration into digital twin platforms and citizen - reporting apps for smart city flood resilience.

Keywords: Clinical information extraction Large language model Clinical concept extraction Clinical relation extraction Instruction tuning ABSTRACT Background N atural language processing (NLP) is a key technology t o extract important patient information from clinical narratives to support healthcare applications. The r apid development of large language models (LLMs) has revolutionized many NLP tasks in the clinical domain, yet their optimal use in patient information extraction tasks requires further exploration . This study examines LLMs ' effectiveness in patient information extraction, focusing on LLM architectures, fine - tuning strategies, and multi - task instruction tuning techniques for developing robust and generalizable patient information extraction systems . Methods This study aims to explore k ey concept s of using LLMs for clinical concept and relation extraction tasks, includ ing: ( 1) encoder - only or decoder - only LLMs, ( 2) prompt - based parameter - efficient fine - tuning (PEFT) algorithms, and ( 3) multi - task instruction tuning on few - shot learning performance . We benchmarked a suite of LLMs, including encoder - based LLMs (BERT, GatorTron) and decoder - based LLMs (GatorTronGPT, Llama 3.1, GatorTronLlama), across five datasets. We compared traditional full - size fine - tuning and prompt - based PEFT . W e explored a multi - task instruction tuning framework that combines both tasks across four datasets to evaluate the zero - shot and few - shot learning performance using the leave - one - dataset - out strategy . Results For single - task clinical CE, t he two decoder - based LLMs (Llama 3.1 and GatorTronLlama) achieved the best performance, with average F1 score s of 0.8964 and 0.8981, respectively, across the five datasets, outperforming other LLMs with average F1 improvement of 0.7~3.3%. E ncoder - based LLMs with prompt - based learning outperformed those implemented using classification .

Digital maps play a crucial role in various applications such as navigation, fleet management, and ride-sharing, necessitating their accuracy and currency, which require timely updates. While the majority of geospatial databases (GDBs) provide high-quality information, their data is (i) limited to specific regions and/or (ii) missing some entities, even in their covered areas. Map conflation is the process of augmentation of a GDB using another GDB to conflate missing spatial features. Existing map conflation methods suffer from two main limitations: (1) They are designed for the conflation of linear objects (e.g., road networks) and cannot simply be extended to non-linear objects, thus missing information about most entities in the map. (2) They are heuristic algorithmic approaches that are based on pre-defined rules, unable to learn entities matching in a data-driven manner. To address these limitations, we design KRAFT, a learning based approach consisting of three parts: (1) Knowledge Graph Construction - where each GDB is represented by a knowledge graph, (2) Map Matching - where we use a knowledge graph alignment method as well as a geospatial feature encoder to match entities in obtained knowledge graphs, and (3) Map Merging - where we merge matched entities in the previous modules in a consistent manner, using a mixed integer linear programming formulation that fully merges the GDBs without adding any inconsistencies. Our experimental evaluation shows that not only does KRAFT achieve outstanding performance compared to state-of-the-art and baseline methods in map conflation tasks, but each of its modules (e.g., Map Matching and Map Merging) also separately outperforms traditional matching and merging methods.