arXiv:2603.28233v1 Announce Type: cross Abstract: Accurate and efficient perception is essential for autonomous driving, where segmentation tasks such as drivable-area and lane segmentation provide critical cues for motion planning and control. However, achieving high segmentation accuracy while maintaining real-time performance on low-cost hardware remains a challenging problem. To address this issue, we introduce TwinMixing, a […]
AI-ready design of realistic 2D materials and interfaces with Mat3ra-2D
arXiv:2603.27886v1 Announce Type: cross Abstract: Artificial intelligence (AI) and machine learning (ML) models in materials science are predominantly trained on ideal bulk crystals, limiting their transferability to real-world applications where surfaces, interfaces, and defects dominate. We present Mat3ra-2D, an open-source framework for the rapid design of realistic two-dimensional materials and related structures, including slabs and […]
Membership Inference Attacks against Large Audio Language Models
arXiv:2603.28378v1 Announce Type: cross Abstract: We present the first systematic Membership Inference Attack (MIA) evaluation of Large Audio Language Models (LALMs). As audio encodes non-semantic information, it induces severe train and test distribution shifts and can lead to spurious MIA performance. Using a multi-modal blind baseline based on textual, spectral, and prosodic features, we demonstrate […]
Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds
arXiv:2603.18532v2 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs directly in the real world to avoid addressing the sim-to-real gap. While real-world RL circumvents sim-to-real issues, it inherently limits the […]
Next-Token Prediction and Regret Minimization
arXiv:2603.28499v1 Announce Type: cross Abstract: We consider the question of how to employ next-token prediction algorithms in adversarial online decision-making environments. Specifically, if we train a next-token prediction model on a distribution $mathcalD$ over sequences of opponent actions, when is it the case that the induced online decision-making algorithm (by approximately best responding to the […]
Kernel Dynamics under Path Entropy Maximization
arXiv:2603.27880v1 Announce Type: cross Abstract: We propose a variational framework in which the kernel function k : X x X -> R, interpreted as the foundational object encoding what distinctions an agent can represent, is treated as a dynamical variable subject to path entropy maximization (Maximum Caliber, MaxCal). Each kernel defines a representational structure over […]
Dynamic Lookahead Distance via Reinforcement Learning-Based Pure Pursuit for Autonomous Racing
arXiv:2603.28625v1 Announce Type: cross Abstract: Pure Pursuit (PP) is a widely used path-tracking algorithm in autonomous vehicles due to its simplicity and real-time performance. However, its effectiveness is sensitive to the choice of lookahead distance: shorter values improve cornering but can cause instability on straights, while longer values improve smoothness but reduce accuracy in curves. […]
SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG Decoding
arXiv:2603.16739v2 Announce Type: replace-cross Abstract: Decoding the orchestration of neural activity in electroencephalography (EEG) signals is a central challenge in bridging neuroscience with artificial intelligence. Foundation models have made strides in generalized EEG decoding, yet many existing frameworks primarily relying on separate temporal and spectral masking of raw signals during self-supervised pretraining. Such strategies often […]
Synthesis of timeline-based planning strategies avoiding determinization
arXiv:2507.17988v2 Announce Type: replace Abstract: Qualitative timeline-based planning models domains as sets of independent, but interacting, components whose behaviors over time, the timelines, are governed by sets of qualitative temporal constraints (ordering relations), called synchronization rules. Its plan-existence problem has been shown to be PSPACE-complete; in particular, PSPACE-membership has been proved via reduction to the […]
A Revealed Preference Framework for AI Alignment
arXiv:2603.27868v1 Announce Type: cross Abstract: Human decision makers increasingly delegate choices to AI agents, raising a natural question: does the AI implement the human principal’s preferences or pursue its own? To study this question using revealed preference techniques, I introduce the Luce Alignment Model, where the AI’s choices are a mixture of two Luce rules, […]
Autonomous Issue Resolver: Towards Zero-Touch Code Maintenance
arXiv:2512.08492v3 Announce Type: replace Abstract: Recent advances in Large Language Models have revolutionized function-level code generation; however, repository-scale Automated Program Repair (APR) remains a significant challenge. Current approaches typically employ a control-centric paradigm, forcing agents to navigate complex directory structures and irrelevant control logic. In this paper, we propose a paradigm shift from the standard […]
A Unified Variational Principle for Branching Transport Networks: Wave Impedance, Viscous Flow, and Tissue Metabolism
arXiv:2603.14691v3 Announce Type: replace-cross Abstract: The branching geometry of biological transport networks is characterized by a diameter scaling exponent $alpha$. Two structural attractors compete: impedance matching ($alpha sim 2$) for pulsatile flow and viscous-metabolic minimization ($alpha = 3$) for steady flow. Neither predicts the empirically observed $alpha_mathrmexp = 2.70 pm 0.20$ in mammalian arterial trees. […]