arXiv preprints from January 1, 2026 through July 21, 2026 — 05:04:15 EST
We present BioNIC, a multi-layer feedforward neural network for emotion classification, inspired by detailed synaptic connectivity graphs from the MICrONs dataset. At a structural level, we incorporate architectural constraints derived from a single cortical column of the mouse Primary Visual Cortex(V1): connectivity imposed via...
Signal Temporal Logic (STL) has been widely adopted as a specification language for specifying desirable behaviors of hybrid systems. By monitoring a given STL specification, we can detect the executions that violate it, which are often referred to as counterexamples. In practice, these counterexamples may arise from different causes...
Large Language Model (LLM) judges exhibit strong reasoning capabilities but are limited to textual content. This leaves current automatic Speech-to-Speech (S2S) evaluation methods reliant on opaque and expensive Audio Language Models (ALMs). In this work, we propose TRACE (Textual Reasoning over Audio Cues for Evaluation), a novel...
This paper presents the flexible RIM Hand, a biomimetic robotic hand that precisely replicates the carpometacarpal (CMC) joints and employs superelastic Nitinol wires throughout its skeletal framework. By modeling the full carpal-to-metacarpal anatomy, the design enables realistic palm deformation through tendon-driven fingers while...
Probabilistic confidence metrics are increasingly adopted as proxies for reasoning quality in Best-of-N selection, under the assumption that higher confidence reflects higher reasoning fidelity. In this work, we challenge this assumption by investigating whether these metrics truly capture inter-step causal dependencies necessary for...
Principle-based alignment often lacks context sensitivity and completeness. Grounded in Theory of Mind, we propose role conditioning as a compact alternative: social roles (e.g., mother, judge) implicitly encode both values and the cognitive schemas required to apply them. We introduce a training-free pipeline featuring a...
In this paper, we propose active recap learning (ARL), a framework for enhancing large language model (LLM) in understanding long contexts. ARL enables models to revisit and summarize earlier content through targeted sequence construction during contined pretraining and retrospective summarization at inference. First, we identify key...
The fact that robots are getting deployed more often in dynamic environments, together with the increasing complexity of their software systems, raises the need for self-adaptive approaches. In these environments robotic software systems increasingly operate amid (1) uncertainties, where symptoms are easy to observe but root causes...
Symbolic computation, powered by modern computer algebra systems, has important applications in mathematical reasoning through exact deep computations. The efficiency of symbolic computation is largely constrained by such deep computations in high dimension. This creates a fundamental barrier on labelled data acquisition if leveraging...
In recent years, the non-deterministic properties of language models have garnered considerable attention and have shown a significant influence on real-world applications. However, such properties remain under-explored in machine translation (MT), a complex, non-deterministic NLP task. In this study, we systematically evaluate modern...
We introduce Yuan3.0 Ultra, an open-source Mixture-of-Experts (MoE) large language model featuring 68.8B activated parameters and 1010B total parameters, specially designed to enhance performance on enterprise scenarios tasks while maintaining competitive capabilities on general purpose tasks. We propose Layer-Adaptive Expert Pruning...
VeriFast is a leading tool for the modular formal verification of correctness properties of single-threaded and multi-threaded C and Rust programs. It verifies a program by symbolically executing each function in isolation, exploiting user-annotated preconditions, postconditions, and loop invariants written in a form of separation...
Self-annotation is the gold standard for collecting affective state labels in affective computing. Existing methods typically rely on full annotation, requiring users to continuously label affective states across entire sessions. While this process yields fine-grained data, it is time-consuming, cognitively demanding, and prone to...
Public blockchains provide no native mechanism to verify the legal identity behind a deployed smart contract, which blocks institutional adoption and compliance with EU regulations such as MiCA and AMLR. We present KYC Seal, the first protocol that extends the EU eIDAS trust infrastructure to Ethereum smart contracts by...
This survey provides a comprehensive overview of the study of the binary and Boolean rank from both a mathematical and a computational perspective, with particular emphasis on their relationship to the real rank. We review the basic definitions of these rank functions and present the main alternative formulations of the binary and...
Deep neural two-sample tests have recently shown strong power for detecting distributional differences between groups, yet their black-box nature limits interpretability and practical adoption in biomedical analysis. Moreover, most existing post-hoc explainability methods rely on class labels, making them unsuitable for label-free...
Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from...
Change Detection (CD) is a fundamental task in remote sensing. It monitors the evolution of land cover over time. Based on this, Open-Vocabulary Change Detection (OVCD) introduces a new requirement. It aims to reduce the reliance on predefined categories. Existing training-free OVCD methods mostly use CLIP to identify categories....
In model-driven engineering and beyond, software models are key development artifacts. In practice, they often grow to substantial size and complexity, undergoing thousands of modifications over time due to evolution, refactoring, and maintenance. The rise of AI has sparked interest in how software modeling activities can be...
Despite their widespread adoption in various domains, especially due to their powerful reasoning capabilities, Large Language Models (LLMs) are not the off-the-shelf choice to drive multi-objective optimization yet. Conventional strategies rank high in benchmarks due to their intrinsic capabilities to handle numerical inputs and...
Log anomaly detection is essential for system reliability, but it is extremely challenging to do considering it involves class imbalance. Additionally, the models trained in one domain are not applicable to other domains, necessitating the need for cross-domain adaptation (such as HDFS and Linux). Traditional detection models often...
External Human-Machine Interfaces (eHMIs) have been proposed to facilitate communication between Automated Vehicles (AVs) and pedestrians. However, no attention was given to Deaf and Hard-of-Hearing (DHH) people. We conducted a formative study through focus groups with 6 DHH people and 6 key stakeholders (including researchers,...
Large language models (LLMs) have demonstrated strong capabilities in knowledge representation and reasoning based on textual data. However, their reliance on language material alone limits their ability to adapt, verify reasoning outcomes, and operate effectively in open and dynamic real-world environments. In this paper, we propose...
Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures yet struggle with high-level semantic context. We argue that these paradigms are fundamentally...
Computerized Adaptive Testing (CAT) has proven effective for efficient LLM evaluation on multiple-choice benchmarks, but modern LLM evaluation increasingly relies on generation tasks where outputs are scored continuously rather than marked correct/incorrect. We present a principled extension of IRT-based adaptive testing to continuous...