arXiv preprints from January 1, 2026 through September 12, 2026 — 13:31:15 EST
Catastrophic forgetting remains a major challenge for continual learning (CL) in automatic speech recognition (ASR), where models must adapt to new domains without losing performance on previously learned conditions. Several CL methods have been proposed for ASR, and, recently, weight averaging - where models are averaged in a merging...
Chain-of-Thought (CoT) prompting has achieved remarkable success in unlocking the reasoning capabilities of Large Language Models (LLMs). Although CoT prompting enhances reasoning, its verbosity imposes substantial computational overhead. Recent works often focus exclusively on outcome alignment and lack supervision on the...
We report the discovery of the trigger for detachment bifurcation phenomenon in tokamak divertors, revealed through steady-state and time-dependent UEDGE simulations: The observed electron temperature cliff at the outer target in DIII-D H-mode plasmas with ion $B\times \nabla B$ drift driven into the active divertor results from a...
The Marcinkiewicz--Zygmund theorem is a fundamental result in probability theory that establishes rates of convergence in the strong law of large numbers (SLLN). Although numerous extensions have been developed for dependent sequences, many classes of processes, particularly those exhibiting strong dependence, remain unexplored. In...
Reinforcement Learning (RL) has empowered Multimodal Large Language Models (MLLMs) to achieve superior human preference alignment in Image Quality Assessment (IQA). However, existing RL-based IQA models typically rely on coarse-grained global views, failing to capture subtle local degradations in high-resolution scenarios. While...
This study provides a foundational theoretical investigation into the mathematical existence and asymptotic properties of Ulanowicz's structural resilience. While ecological evidence suggests that sustainable systems gravitate toward an optimal efficiency-redundancy balance at $α= 1/\mathrm{e}$, the mathematical attainability of this...
Federated learning (FL) enables collaborative model training without sharing raw data in edge environments, but is constrained by limited communication bandwidth and heterogeneous client data distributions. Prototype-based FL mitigates this issue by exchanging class-wise feature prototypes instead of full model parameters; however,...
This short note proposes a model-driven conditional Fourier neural operator (MD-CFNO) for synthetic turbulence generation. Spectrum-consistent synthetic turbulence is essential for inflow boundary construction in computational fluid dynamics and for broadband aeroacoustic noise prediction. Data-driven turbulence synthesis with neural...
Achieving pronunciation proficiency in a second language (L2) remains a challenge, despite the development of Computer-Assisted Pronunciation Training (CAPT) systems. Traditional CAPT systems often provide unintuitive feedback that lacks actionable guidance, limiting its effectiveness. Recent advancements in audio-language models...
The effectiveness of collision-free trajectory planners depends on the quality and diversity of training data, especially for rare scenarios. A widely used approach to improve dataset diversity involves generating realistic synthetic traffic scenarios. However, producing such scenarios remains difficult due to the precision required...
Reliable drone detection is challenging due to limited annotated real-world data, large appearance variability, and the presence of visually similar distractors such as birds. To address these challenges, this paper introduces SimD3, a large-scale high-fidelity synthetic dataset designed for robust drone detection in complex aerial...
Artificial Intelligence-Generated Content (AIGC) has made significant strides, with high-resolution text-to-image (T2I) generation becoming increasingly critical for improving users' Quality of Experience (QoE). Although resource-constrained edge computing adequately supports fast low-resolution T2I generations, achieving...
In this paper, we apply an implicit Euler scheme to discretize the complex Ginzburg-Landau equation and prove the existence of a numerical attractor for the discrete Ginzburg-Landau system. We establish the upper semicontinuity of the numerical attractor with respect to the global attractor as the time step tends to zero. Furthermore,...
The results of a study of the cosmic ray composition in individual events in the energy range (2-12.5) EeV using the muon correlation method is presented. The considered sample included showers with zenith angles less than 60 degrees recorded in the period 1974-2018. The existence of four separate groups of primary particles with...
The rapid evolution of diffusion models has democratized face swapping but also raises concerns about privacy and identity security. Existing proactive defenses, often adapted from image editing attacks, prove ineffective in this context. We attribute this failure to an oversight of the structural resilience and the unique static...
Billboard Advertising has emerged as an effective out-of-home advertising technique, where the goal is to select a limited number of slots and play advertisement content there, with the hope that it will be observed by many people and, effectively, a significant number of them will be influenced towards the brand. Given a trajectory...
For a discrete dynamical system on $\R$ generated by a quadratic function, we show, using elementary computations, that the existence, number, and stability of 3-cycles are determined by a single parameter depending on the coefficients of the function.
A central challenge in developing Multimodal Large Language Models (MLLMs) is effectively integrating heterogeneous inputs into a cohesive reasoning engine. Current paradigms predominantly rely on modular architectures that introduce modality-specific encoders and cross-modal fusion mechanisms. However, these designs are fundamentally...
Agentic workflows that use autonomous AI Agents powered by Large Language Models (LLMs) and Model Context Protocol (MCP) servers is rapidly rising. This introduces challenges in scalable cloud deployment and state management. Traditional hosting on Virtual Machines (VMs) is resource-intensive and lacks elasticity....
We compare different circuits implementing distributed versions of quantum computations, using entangled pairs only, and using distributed fan-out operations (using GHZ states). We highlight the advantages of using distributed fan-out operations in terms of reductions in circuit depth and (possibly) entanglement resources. We note...
Climate change is progressing asynchronously between the Arctic and Antarctic, with important implications for global climate dynamics. While the Arctic has experienced rapid warming and pronounced amplification, the Antarctic has exhibited a delayed and heterogeneous response. Here, we identify an Interdecadal Bipolar Oscillation...
AI models for drug discovery and chemical literature mining must interpret molecular images and generate outputs consistent with 3D geometry and stereochemistry. Most molecular language models rely on strings or graphs, while vision-language models often miss stereochemical details and struggle to map continuous 3D structures into...
Software systems that run for long periods often suffer from software aging, which is typically caused by Aging-Related Bugs (ARBs). To mitigate the risk of ARBs early in the development phase, ARB prediction has been introduced into software aging research. However, due to the difficulty of collecting ARBs, within-project ARB...
Despite the widespread success of Graph Neural Networks (GNNs), understanding the reasons behind their specific predictions remains challenging. Existing explainability methods face a trade-off that gradient-based approaches are computationally efficient but often ignore structural interactions, while game-theoretic techniques capture...
We present a unified framework that combines early- and late-Universe observations to constrain three functional realizations of f(T,B) gravity: the linear, quadratic, and general power-law models. First, constraints on deviations from the standard weak interaction freeze-out temperature are derived using the most recent measurements...