Quantity Convergence, Quality Divergence: Disentangling Fluency and Accuracy in L2 Mandarin Prosody
arXiv:2602.23071v1 Announce Type: new Abstract: While second language (L2) learners may acquire target syntactic word order, mapping this syntax onto appropriate prosodic structures remains a persistent challenge. This study investigates the fossilization and stability of the L2 syntax-prosody interface by...
CiteLLM: An Agentic Platform for Trustworthy Scientific Reference Discovery
arXiv:2602.23075v1 Announce Type: new Abstract: Large language models (LLMs) have created new opportunities to enhance the efficiency of scholarly activities; however, challenges persist in the ethical deployment of AI assistance, including (1) the trustworthiness of AI-generated content, (2) preservation of...
Modality Collapse as Mismatched Decoding: Information-Theoretic Limits of Multimodal LLMs
arXiv:2602.23136v1 Announce Type: new Abstract: Multimodal LLMs can process speech and images, but they cannot hear a speaker's voice or see an object's texture. We show this is not a failure of encoding: speaker identity, emotion, and visual attributes survive...
MTRAG-UN: A Benchmark for Open Challenges in Multi-Turn RAG Conversations
arXiv:2602.23184v1 Announce Type: new Abstract: We present MTRAG-UN, a benchmark for exploring open challenges in multi-turn retrieval augmented generation, a popular use of large language models. We release a benchmark of 666 tasks containing over 2,800 conversation turns across 6...
Fine-Tuning Without Forgetting In-Context Learning: A Theoretical Analysis of Linear Attention Models
arXiv:2602.23197v1 Announce Type: new Abstract: Transformer-based large language models exhibit in-context learning, enabling adaptation to downstream tasks via few-shot prompting with demonstrations. In practice, such models are often fine-tuned to improve zero-shot performance on downstream tasks, allowing them to solve...
Discourse-Aware Dual-Track Streaming Response for Low-Latency Spoken Dialogue Systems
arXiv:2602.23266v1 Announce Type: new Abstract: Achieving human-like responsiveness is a critical yet challenging goal for cascaded spoken dialogue systems. Conventional ASR-LLM-TTS pipelines follow a strictly sequential paradigm, requiring complete transcription and full reasoning before speech synthesis can begin, which results...
A Mixture-of-Experts Model for Multimodal Emotion Recognition in Conversations
arXiv:2602.23300v1 Announce Type: new Abstract: Emotion Recognition in Conversations (ERC) presents unique challenges, requiring models to capture the temporal flow of multi-turn dialogues and to effectively integrate cues from multiple modalities. We propose Mixture of Speech-Text Experts for Recognition of...
Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
arXiv:2602.23351v1 Announce Type: new Abstract: The lack of reasoning capabilities in Vision-Language Models (VLMs) has remained at the forefront of research discourse. We posit that this behavior stems from a reporting bias in their training data. That is, how people...
To Deceive is to Teach? Forging Perceptual Robustness via Adversarial Reinforcement Learning
arXiv:2602.22227v1 Announce Type: new Abstract: Despite their impressive capabilities, Multimodal Large Language Models (MLLMs) exhibit perceptual fragility when confronted with visually complex scenes. This weakness stems from a reliance on finite training datasets, which are prohibitively expensive to scale and...
Improving Spatial Allocation for Energy System Coupling with Graph Neural Networks
arXiv:2602.22249v1 Announce Type: new Abstract: In energy system analysis, coupling models with mismatched spatial resolutions is a significant challenge. A common solution is assigning weights to high-resolution geographic units for aggregation, but traditional models are limited by using only a...
Causal Direction from Convergence Time: Faster Training in the True Causal Direction
arXiv:2602.22254v1 Announce Type: new Abstract: We introduce Causal Computational Asymmetry (CCA), a principle for causal direction identification based on optimization dynamics in which one neural network is trained to predict $Y$ from $X$ and another to predict $X$ from $Y$,...
Orthogonal Weight Modification Enhances Learning Scalability and Convergence Efficiency without Gradient Backpropagation
arXiv:2602.22259v1 Announce Type: new Abstract: Recognizing the substantial computational cost of backpropagation (BP), non-BP methods have emerged as attractive alternatives for efficient learning on emerging neuromorphic systems. However, existing non-BP approaches still face critical challenges in efficiency and scalability. Inspired...
Code World Models for Parameter Control in Evolutionary Algorithms
arXiv:2602.22260v1 Announce Type: new Abstract: Can an LLM learn how an optimizer behaves -- and use that knowledge to control it? We extend Code World Models (CWMs), LLM-synthesized Python programs that predict environment dynamics, from deterministic games to stochastic combinatorial...
Sustainable LLM Inference using Context-Aware Model Switching
arXiv:2602.22261v1 Announce Type: new Abstract: Large language models have become central to many AI applications, but their growing energy consumption raises serious sustainability concerns. A key limitation in current AI deployments is the reliance on a one-size-fits-all inference strategy where...
Entropy-Controlled Flow Matching
arXiv:2602.22265v1 Announce Type: new Abstract: Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry...
Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin
arXiv:2602.22267v1 Announce Type: new Abstract: The real-time supervision of production processes is a common challenge across several industries. It targets process component monitoring and its predictive maintenance in order to ensure safety, uninterrupted production and maintain high efficiency level. The...
AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
arXiv:2602.22268v1 Announce Type: new Abstract: Quantization followed by parameter-efficient fine-tuning has emerged as a promising paradigm for downstream adaptation under tight GPU memory constraints. However, this sequential pipeline fails to leverage the intricate interaction between quantization bit-width and LoRA rank....
CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learning
arXiv:2602.22269v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative model training without sharing raw data. However, shared local model updates remain vulnerable to inference and poisoning attacks. Secure aggregation schemes have been proposed to mitigate these attacks. In this...
Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction
arXiv:2602.22274v1 Announce Type: new Abstract: Traffic flow forecasting has emerged as an indispensable mission for daily life, which is required to utilize the spatiotemporal relationship between each location within a time period under a graph structure to predict future flow....
X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation
arXiv:2602.22277v1 Announce Type: new Abstract: AI-native architectures are vital for 6G wireless communications. The black-box nature and high complexity of deep learning models employed in critical applications, such as channel estimation, limit their practical deployment. While perturbation-based XAI solutions offer...
Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion
arXiv:2602.22280v1 Announce Type: new Abstract: Cardiovascular disease is the primary cause of death globally, necessitating early identification, precise risk classification, and dependable decision-support technologies. The advent of large language models (LLMs) provides new zero-shot and few-shot reasoning capabilities, even though...
BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning
arXiv:2602.22284v1 Announce Type: new Abstract: Recent advancements in deep learning have actively addressed complex challenges within the Computer-Aided Design (CAD) domain.However, most existing approaches rely on task-specifi c models requiring structural modifi cations for new tasks, and they predominantly focus...
Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning
arXiv:2602.22285v1 Announce Type: new Abstract: Objective: The objective of this study is to develop a machine learning (ML)-based framework for early risk stratification of clinical trials (CTs) according to their likelihood of exhibiting a high rate of dosing errors, using...
OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
arXiv:2602.22286v1 Announce Type: new Abstract: Lossless compression is essential for efficient data storage and transmission. Although learning-based lossless compressors achieve strong results, most of them are designed for a single modality, leading to redundant compressor deployments in multi-modal settings. Designing...
Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy
arXiv:2602.22288v1 Announce Type: new Abstract: Sudden cardiac death (SCD) is unpredictable, and its prediction in Chagas cardiomyopathy (CC) remains a significant challenge, especially in patients not classified as high risk. While AI and machine learning models improve risk stratification, their...
Manifold of Failure: Behavioral Attraction Basins in Language Models
arXiv:2602.22291v1 Announce Type: new Abstract: While prior work has focused on projecting adversarial examples back onto the manifold of natural data to restore safety, we argue that a comprehensive understanding of AI safety requires characterizing the unsafe regions themselves. This...
When Should a Model Change Its Mind? An Energy-Based Theory and Regularizer for Concept Drift in Electrocardiogram (ECG) Signals
arXiv:2602.22294v1 Announce Type: new Abstract: Models operating on dynamic physiologic signals must distinguish benign, label-preserving variability from true concept change. Existing concept-drift frameworks are largely distributional and provide no principled guidance on how much a model's internal representation may move...
UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMs
arXiv:2602.22296v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has improved the reasoning abilities of large language models (LLMs) on mathematics and programming tasks, but standard approaches that optimize single-attempt accuracy can inadvertently suppress response diversity across repeated...
Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault Detection
arXiv:2602.22297v1 Announce Type: new Abstract: Reinforcement learning (RL) offers significant promise for machinery fault detection (MFD). However, most existing RL-based MFD approaches do not fully exploit RL's sequential decision-making strengths, often treating MFD as a simple guessing game (Contextual Bandits)....
Training Agents to Self-Report Misbehavior
arXiv:2602.22303v1 Announce Type: new Abstract: Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to...