arXiv:2603.07184v1 Announce Type: cross Abstract: Analyzing creative activity traces requires capturing activity at appropriate granularity and interpreting it in ways that reflect the structure of creative practice. However, existing approaches record state changes without preserving the intent or relationships that define higher-level creative moves. This decoupling manifests differently across domains: GenAI tools lose non-linear exploration […]
MAviS: A Multimodal Conversational Assistant For Avian Species
arXiv:2603.07294v1 Announce Type: cross Abstract: Fine-grained understanding and species-specific multimodal question answering are vital for advancing biodiversity conservation and ecological monitoring. However, existing multimodal large language models face challenges when it comes to specialized topics like avian species, making it harder to provide accurate and contextually relevant information in these areas. To address this limitation, […]
Scaling Laws in the Tiny Regime: How Small Models Change Their Mistakes
arXiv:2603.07365v1 Announce Type: cross Abstract: Neural scaling laws describe how model performance improves as a power law with size, but existing work focuses on models above 100M parameters. The sub-20M regime — where TinyML and edge AI operate — remains unexamined. We train 90 models (22K–19.8M parameters) across two architectures (plain ConvNet, MobileNetV2) on CIFAR-100, […]
Weakly nonlinear analysis of a reaction-diffusion model for demyelinating lesions in Multiple Sclerosis
arXiv:2603.06628v1 Announce Type: new Abstract: Multiple Sclerosis is a chronic autoimmune disorder characterized by the degradation of the myelin sheath in the central nervous system, leading to neurological impairments. In this work, we analyze a reaction-diffusion model derived from kinetic theory to study the formation of demyelinating lesions. We perform a Turing instability analysis and […]
Tree-based Dialogue Reinforced Policy Optimization for Red-Teaming Attacks
arXiv:2510.02286v2 Announce Type: replace-cross Abstract: Despite recent rapid progress in AI safety, current large language models remain vulnerable to adversarial attacks in multi-turn interaction settings, where attackers strategically adapt their prompts across conversation turns and pose a more critical yet realistic challenge. Existing approaches that discover safety vulnerabilities either rely on manual red-teaming with human […]
Maximum Principle of Optimal Probability Density Control
arXiv:2505.18362v3 Announce Type: replace-cross Abstract: We develop a general theoretical framework for optimal probability density control on standard measure spaces, aimed at addressing large-scale multi-agent control problems. In particular, we establish a maximum principle (MP) for control problems posed on infinite-dimensional spaces of probability distributions and control vector fields. We further derive the Hamilton–Jacobi–Bellman equation […]
AltNet: Addressing the Plasticity-Stability Dilemma in Reinforcement Learning
arXiv:2512.01034v3 Announce Type: replace-cross Abstract: Artificial neural networks have shown remarkable success in supervised learning when trained on a single task using a fixed dataset. However, when neural networks are trained on a reinforcement learning task, their ability to continue learning from new experiences declines over time. This decline in learning ability is known as […]
Goal Alignment in LLM-Based User Simulators for Conversational AI
arXiv:2507.20152v2 Announce Type: replace-cross Abstract: User simulators are essential to conversational AI, enabling scalable agent development and evaluation through simulated interactions. While current Large Language Models (LLMs) have advanced user simulation capabilities, we reveal that they struggle to consistently demonstrate goal-oriented behavior across multi-turn conversations–a critical limitation that compromises their reliability in downstream applications. We […]
Vectorized Online POMDP Planning
arXiv:2510.27191v3 Announce Type: replace-cross Abstract: Planning under partial observability is an essential capability of autonomous robots. The Partially Observable Markov Decision Process (POMDP) provides a powerful framework for planning under partial observability problems, capturing the stochastic effects of actions and the limited information available through noisy observations. POMDP solving could benefit tremendously from massive parallelization […]
Multi-Domain Audio Question Answering Benchmark Toward Acoustic Content Reasoning
arXiv:2505.07365v2 Announce Type: replace-cross Abstract: We present Task 5 of the DCASE 2025 Challenge: an Audio Question Answering (AQA) benchmark spanning multiple domains of sound understanding. This task defines three QA subsets (Bioacoustics, Temporal Soundscapes, and Complex QA) to test audio-language models on interactive question-answering over diverse acoustic scenes. We describe the dataset composition (from […]
Parameter Identifiability Under Limited Experimental Data in Age-Structured Models of the Cell Cycle
arXiv:2603.06751v1 Announce Type: new Abstract: The mitotic cell cycle governs DNA replication and cell division. The effectiveness of radiotherapy and chemotherapy depends on cell-cycle position, with increased resistance during DNA replication and mitosis. Thus, accurate mathematical models of the cell cycle are essential for understanding and predicting treatment response. However, mathematical modellers often face the […]
Test-Time Meta-Adaptation with Self-Synthesis
arXiv:2603.03524v2 Announce Type: replace-cross Abstract: As strong general reasoners, large language models (LLMs) encounter diverse domains and tasks, where the ability to adapt and self-improve at test time is valuable. We introduce MASS, a meta-learning framework that enables LLMs to self-adapt by generating problem-specific synthetic training data and performing targeted self-updates optimized for downstream performance […]