搜索结果：alias-based

Large language models are increasingly evaluated as interactive agents, yet standard agent benchmarks conflate two qualitatively distinct sources of success: semantic tool-use and interface-specific interaction pattern memorization. Because both mechanisms can yield identical task success on the original interface, benchmark scores alone are not identifiable evidence of environment-invariant capability. We propose PIPE, a protocol-level evaluation augmentation for diagnosing interface reliance by minimally rewriting environment interfaces while preserving task semantics and execution behavior. Across 16 environments from AgentBench and AgentGym and a range of open-source and API-based agents, PIPE reveals that trajectory-SFT substantially amplifies interface shortcutting: trained agents degrade sharply under minimal interface rewrites, while non-trajectory-trained models remain largely stable. We further introduce Interface Reliance (IR), a counterbalanced alias-based metric that quantifies preference for training-time interfaces, and show that interface shortcutting exhibits environment-dependent, non-monotonic training dynamics that remain invisible under standard evaluation. Our

Motivation: Biomedical question answering often requires evidence beyond topically retrieved literature, including gene alias resolution, database identifier normalization, and atlas-derived biological measurements. However, existing retrieval-augmented generation (RAG) systems typically follow a fixed workflow and lack an explicit mechanism for deciding when retrieved text is sufficient, when curated biomedical knowledge is required, or when executable evidence assembly over structured measurements should be invoked. This motivates a substrate-aware large language model (LLM) harness that selectively assembles sufficient evidence across literature, knowledge bases, and biological atlases. Results: We introduce BioHarness, an LLM harness for staged biomedical evidence assembly across literature retrieval, curated biomedical knowledge resources, and atlas-derived structured measurements. BioHarness first attempts to answer from reranked literature evidence and escalates through grounded cascade control to REPL-style evidence assembly only when the current evidence is uncertain, weakly grounded, or substrate-mismatched. Across 19,302 biomedical QA items spanning seven answer formats,

Large-scale, standardized datasets for Advanced Persistent Threat (APT) research are scarce, and inconsistent actor aliases and redundant samples hinder reproducibility. This paper presents APT-ClaritySet and its construction pipeline that normalizes threat actor aliases (reconciling approximately 11.22\% of inconsistent names) and applies graph-feature deduplication -- reducing the subset of statically analyzable executables by 47.55\% while retaining behaviorally distinct variants. APT-ClaritySet comprises: (i) APT-ClaritySet-Full, the complete pre-deduplication collection with 34{,}363 malware samples attributed to 305 APT groups (2006 - early 2025); (ii) APT-ClaritySet-Unique, the deduplicated release with 25{,}923 unique samples spanning 303 groups and standardized attributions; and (iii) APT-ClaritySet-FuncReuse, a function-level resource that includes 324{,}538 function-reuse clusters (FRCs) enabling measurement of inter-/intra-group sharing, evolution, and tooling lineage. By releasing these components and detailing the alias normalization and scalable deduplication pipeline, this work provides a high-fidelity, reproducible foundation for quantitative studies of APT pattern

Authentication is the cornerstone of information security in our daily lives. However, disabled users such as Blind and Low-Vision (BLV) ones are left behind in digital services due to the lack of accessibility. According to the World Health Organization, 36 million people are blind worldwide. It is estimated that there will be 115 million by 2050, due to the ageing of the population. Yet accessing digital services has become increasingly essential. At the same time, cyber threats targeting individuals have also increased strongly in the last few years. The ALIAS project addresses the need for accessible digital authentication solutions for BLV users facing challenges with digital technology. Security systems can inhibit access for these individuals as they become more complex. This project aims to create a barrier-free authentication system based on cognitive ergonomics and user experience (UX) design methods specifically for BLV users. This paper presents an overview of current research in this area. We also identify research gaps, and finally, we present our project's methodology and approach. First, we will build a knowledge base on the digital practices and cognitive models of

Large language models are increasingly used for text classification tasks such as sentiment analysis, yet their reliance on natural language prompts exposes them to prompt injection attacks. In particular, class-directive injections exploit knowledge of the model's label set (e.g., positive vs. negative) to override its intended behavior through adversarial instructions. Existing defenses, such as detection-based filters, instruction hierarchies, and signed prompts, either require model retraining or remain vulnerable to obfuscation. This paper introduces Label Disguise Defense (LDD), a lightweight and model-agnostic strategy that conceals true labels by replacing them with semantically transformed or unrelated alias labels(e.g., blue vs. yellow). The model learns these new label mappings implicitly through few-shot demonstrations, preventing direct correspondence between injected directives and decision outputs. We evaluate LDD across nine state-of-the-art models, including GPT-5, GPT-4o, LLaMA3.2, Gemma3, and Mistral variants, under varying few-shot and an adversarial setting. Our results show that the ability of LDD to recover performance lost to the adversarial attack varies ac

Existing dynamic scene reconstruction methods based on Gaussian Splatting enable real-time rendering and generate realistic images. However, adjusting the camera's focal length or the distance between Gaussian primitives and the camera to modify rendering resolution often introduces strong artifacts, stemming from the frequency constraints of 4D Gaussians and Gaussian scale mismatch induced by the 2D dilated filter. To address this, we derive a maximum sampling frequency formulation for 4D Gaussian Splatting and introduce a 4D scale-adaptive filter and scale loss, which flexibly regulates the sampling frequency of 4D Gaussian Splatting. Our approach eliminates high-frequency artifacts under increased rendering frequencies while effectively reducing redundant Gaussians in multi-view video reconstruction. We validate the proposed method through monocular and multi-view video reconstruction experiments.Ours project page: https://4d-alias-free.github.io/4D-Alias-free/

The creative potential of computers has intrigued researchers for decades. Since the emergence of Generative AI (Gen AI), computer creativity has found many new dimensions and applications. As Gen AI permeates mainstream discourse and usage, researchers are delving into how it can improve and complement what humans do. Creative potential is a highly relevant notion to design practice and research, especially in the initial stages of ideation and conceptualisation. There is scope to improve creative potential in these stages, especially using machine intelligence. We propose a structured ideation session involving inspirational stimuli and utilise Gen AI in delivering this structure to designers through ALIA: Analogical LLM Ideation Agent, a tool for small-group ideation scenarios. The tool is developed by enabling speech based interactions with a Large Language Model (LLM) for inference generation. Inspiration is drawn from the synectic ideation method and the dialectics philosophy to design the optimal stimuli in group ideation. The tool is tested in design ideation sessions to compare the output of the AI-assisted ideation sessions to that of tradi tional ideation sessions. Preli

Cross-organizational collaboration in Model-Based Systems Engineering (MBSE) faces many challenges in achieving semantic alignment across independently developed system models. SysML v2 introduces enhanced structural modularity and formal semantics, offering a stronger foundation for interoperable modeling. Meanwhile, GPT-based Large Language Models (LLMs) provide new capabilities for assisting model understanding and integration. This paper proposes a structured, prompt-driven approach for LLM-assisted semantic alignment of SysML v2 models. The core contribution lies in the iterative development of an alignment approach and interaction prompts, incorporating model extraction, semantic matching, and verification. The approach leverages SysML v2 constructs such as alias, import, and metadata extensions to support traceable, soft alignment integration. It is demonstrated with a GPT-based LLM through an example of a measurement system. Benefits and limitations are discussed.

In this paper, we describe and benchmark a competitor-discovery component used within an agentic AI system for fast drug asset due diligence. A competitor-discovery AI agent, given an indication, retrieves all drugs comprising the competitive landscape of that indication and extracts canonical attributes for these drugs. The competitor definition is investor-specific, and data is paywalled/licensed, fragmented across registries, ontology-mismatched by indication, alias-heavy for drug names, multimodal, and rapidly changing. Although considered the best tool for this problem, the current LLM-based AI systems aren't capable of reliably retrieving all competing drug names, and there is no accepted public benchmark for this task. To address the lack of evaluation, we use LLM-based agents to transform five years of multi-modal, unstructured diligence memos from a private biotech VC fund into a structured evaluation corpus mapping indications to competitor drugs with normalized attributes. We also introduce a competitor validating LLM-as-a-judge agent that filters out false positives from the list of predicted competitors to maximize precision and suppress hallucinations. On this benchma

Multi-agent Large Language Model (LLM) systems have been leading the way in applied LLM research across a number of fields. One notable area is software development, where researchers have advanced the automation of code implementation, code testing, code maintenance, inter alia, using LLM agents. However, software development is a multifaceted environment that extends beyond just code. As such, a successful LLM system must factor in multiple stages of the software development life-cycle (SDLC). In this paper, we propose a vision for ALMAS, an Autonomous LLM-based Multi-Agent Software Engineering framework, which follows the above SDLC philosophy such that it may work within an agile software development team to perform several tasks end-to-end. ALMAS aligns its agents with agile roles, and can be used in a modular fashion to seamlessly integrate with human developers and their development environment. We showcase the progress towards ALMAS through our published works and a use case demonstrating the framework, where ALMAS is able to seamlessly generate an application and add a new feature.

Convolutional neural operator is a CNN-based architecture recently proposed to enforce structure-preserving continuous-discrete equivalence and enable the genuine, alias-free learning of solution operators of PDEs. This neural operator was demonstrated to outperform for certain cases some baseline models such as DeepONet, Fourier neural operator, and Galerkin transformer in terms of surrogate accuracy. The convolutional neural operator, however, seems not to be validated for few-shot learning. We extend the model to few-shot learning scenarios by first pre-training a convolutional neural operator using a source dataset and then adjusting the parameters of the trained neural operator using only a small target dataset. We investigate three strategies for adjusting the parameters of a trained neural operator, including fine-tuning, low-rank adaption, and neuron linear transformation, and find that the neuron linear transformation strategy enjoys the highest surrogate accuracy in solving PDEs such as Kuramoto-Sivashinsky equation, Brusselator diffusion-reaction system, and Navier-Stokes equations.

The battle for AI leadership is on, with OpenAI in the United States and DeepSeek in China as key contenders. In response to these global trends, the Spanish government has proposed ALIA, a public and transparent AI infrastructure incorporating small language models designed to support Spanish and co-official languages such as Basque. This paper presents the results of Red Teaming sessions, where ten participants applied their expertise and creativity to manually test three of the latest models from these initiatives$\unicode{x2013}$OpenAI o3-mini, DeepSeek R1, and ALIA Salamandra$\unicode{x2013}$focusing on biases and safety concerns. The results, based on 670 conversations, revealed vulnerabilities in all the models under test, with biased or unsafe responses ranging from 29.5% in o3-mini to 50.6% in Salamandra. These findings underscore the persistent challenges in developing reliable and trustworthy AI systems, particularly those intended to support Spanish and Basque languages.

We present a ground-based transit detection of HIP 41378 f, a long-period ($P = 542$ days), extremely low-density ($0.09 \pm 0.02$ g cm$^{-3}$) giant exoplanet in a dynamically complex system. Using photometry from Tierras, TRAPPIST-North, and multiple LCOGT sites, we constrain the transit center time to $T_{C,6} = 2460438.891 \pm 0.052$ BJD TDB. This marks only the second ground-based detection of HIP 41378 f, currently the longest-period and longest-duration transiting exoplanet observed from the ground. We use this new detection, along with a recently published transit time from Rossiter-McLaughlin observations, to update the TTV solution for HIP 41378 f. We predict the next two transits will occur at $T_{C,7} = 2460980.793^{+0.098}_{-0.129}$ BJD TDB (2025 November 1) and $T_{C,8} = 2461522.653^{+0.213}_{-0.238}$ BJD TDB (2027 April 27). Incorporating new TESS Sector 88 data, we also rule out the 101-day orbital period alias for HIP 41378 d, and find that the remaining viable solutions are centered on the 278, 371, and 1113-day aliases. The latter two imply dynamical configurations that challenge the canonical view of planet e as the dominant perturber of planet f. Our results s

In the present work, the ideal shear strength (τ_is) of dilute Ni34XZ ternary alloys (X or Z = Al, Co, Cr, Fe, Mn, Mo, Nb, Si, Ti) are predicted by first-principles calculations based on density functional theory (DFT) in terms of pure alias shear deformations. The τ_is results show that within the concentration up to 8.3% of alloying elements, τ_is increases with composition in binary systems with Mn, Fe, and Co in ascending order, and decreases with composition with Nb, Si, Mo, Ti, Al, and Cr in descending order. The composition dependence of τ_is in binary and ternary systems is modeled using the CALculation of PHAse Diagrams (CALPHAD) approach considering lattice instability, indicating that atomic bonding strength significantly influences τ_is. Correlational analyses further show that lattice constant and elastic constant C11 affect τ_is, the most out of the elemental features.

This paper makes some modifications to the warped product space. Based on Alias,Impera and Rigoli, a warping function is added to the warped product space. This new function affects the Riemannian metric of the warped product space. In this new warped product space, we continue to discuss the sufficient condition for calculating the height of the immersed surface.

Due to their ability to anchor into tall urban landforms, such as lampposts or street lights, robotic aerial base stations (RABSs) can create a hyper-flexible wireless multi-hop heterogeneous network to meet the forthcoming green, densified, and dynamic network deployment to support, inter alia, high data rates. In this work, we propose a network infrastructure that can concurrently support the wireless backhaul link capacity and access link traffic demand in the millimeter-wave (mmWave) frequency band. The RABSs grasping locations, resource blocks (RBs) assignment, and route flow control are simultaneously optimized to maximize the served traffic demands. Robotic base stations capitalize on the fact that traffic distribution varies considerably across both time and space within a given geographical area. Hence, they are able to relocate to suitable locations, i.e., 'follow' the traffic demand as it unfolds to increase the overall network efficiency. To tackle the curse of dimensionality of the proposed mixed-integer linear problem, we propose a greedy algorithm to obtain a competitive solution with low computational complexity. Compared to baseline models, which are heterogeneous

Portable heart rate monitoring (HRM) systems based on electrocardiograms (ECGs) have become increasingly crucial for preventing lifestyle diseases. For such portable systems, minimizing power consumption and sampling rate is critical due to the substantial data generated during long-term ECG monitoring. The variable pulse-width finite rate of innovation (VPW-FRI) framework provides an effective solution for low-rate sampling and compression of ECG signals. We develop a time-based sub-Nyquist sampling and reconstruction method for ECG signals specifically designed for HRM applications. Our approach harnesses the integrate-and-fire time-encoding machine (IF-TEM) as a power-efficient, time-based, asynchronous sampler, generating a sequence of time instants without the need for a global clock. The ECG signal is represented as a linear combination of VPW-FRI pulses, which is then subjected to pre-filtering before being sampled by the IF-TEM sampler. A compactly supported robust filter with a frequency-domain alias cancellation condition is used to combat the effects of noise. Our reconstruction process involves consecutive partial summations of discrete representations of the input sign

While surface-based view synthesis algorithms are appealing due to their low computational requirements, they often struggle to reproduce thin structures. In contrast, more expensive methods that model the scene's geometry as a volumetric density field (e.g. NeRF) excel at reconstructing fine geometric detail. However, density fields often represent geometry in a "fuzzy" manner, which hinders exact localization of the surface. In this work, we modify density fields to encourage them to converge towards surfaces, without compromising their ability to reconstruct thin structures. First, we employ a discrete opacity grid representation instead of a continuous density field, which allows opacity values to discontinuously transition from zero to one at the surface. Second, we anti-alias by casting multiple rays per pixel, which allows occlusion boundaries and subpixel structures to be modelled without using semi-transparent voxels. Third, we minimize the binary entropy of the opacity values, which facilitates the extraction of surface geometry by encouraging opacity values to binarize towards the end of training. Lastly, we develop a fusion-based meshing strategy followed by mesh simpli

Drought is a complex environmental phenomenon that affects millions of people and communities all over the globe and is too elusive to be accurately predicted. This is mostly due to the scalability and variability of the web of environmental parameters that directly/indirectly causes the onset of different categories of drought. Since the dawn of man, efforts have been made to uniquely understand the natural indicators that provide signs of likely environmental events. These indicators/signs in the form of indigenous knowledge system have been used for generations. The intricate complexity of drought has, however, always been a major stumbling block for accurate drought prediction and forecasting systems. Recently, scientists in the field of agriculture and environmental monitoring have been discussing the integration of indigenous knowledge and scientific knowledge for a more accurate environmental forecasting system in order to incorporate diverse environmental information for a reliable drought forecast. Hence, in this research, the core objective is the development of a semantics-based data integration middleware that encompasses and integrates heterogeneous data models of loca