arXiv:2607.25299v1 Announce Type: cross Abstract: Optimization over the Stiefel manifold plays a significant role in various machine learning tasks. Existing methods either use the retraction operators,…
arXiv:2607.26286v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as general-purpose translation systems, but their behavior is usually evaluated under a single prompt…
arXiv:2603.27519v2 Announce Type: replace Abstract: Image-based plant phenotyping depends on dense structural understanding of crops, yet pixel-level annotation remains expensive across species, organs, growth stages, and…
arXiv:2607.25802v2 Announce Type: replace Abstract: Most video editing systems still lack explicit layered video representations, limiting their ability to perform realistic compositing, object reuse, and consistent…
arXiv:2607.26246v1 Announce Type: new Abstract: On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm…
arXiv:2604.09229v2 Announce Type: replace Abstract: von Economo neurons (VENs) are large bipolar projection neurons found exclusively in the anterior cingulate cortex (ACC) and frontal insula of…
arXiv:2607.26458v1 Announce Type: new Abstract: Domain generalization (DG) aims to learn from multiple source domains and generalize to unseen target domains. Most DG methods pursue invariance:…
arXiv:2607.25497v1 Announce Type: cross Abstract: Pathology foundation models are approaching clinical deployment, yet remain vulnerable to systematic non-biological variation across centres. Differences in tissue preparation, staining…
arXiv:2607.26228v1 Announce Type: new Abstract: Instruction hierarchies are a core safety assumption of language model deployment: higher priority inputs, such as system prompts, should override conflicting…
arXiv:2506.22078v3 Announce Type: replace Abstract: Many remote Heart Rate (HR) measurement methods focus on estimating remote photoplethysmography (rPPG) signals from video clips lasting around 10 seconds…
arXiv:2607.26237v1 Announce Type: new Abstract: Pretrained diffusion models generate realistic images but are constrained by the statistical biases of their training data, limiting their ability to…
arXiv:2607.26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use…
arXiv:2607.26467v1 Announce Type: cross Abstract: Traffic prediction is a core task in intelligent transportation systems, supporting applications such as adaptive signal control, route guidance, and ride-hailing…
arXiv:2607.26964v1 Announce Type: new Abstract: We study feature bagging through the lens of algorithmic stability. Feature bagging is an ensemble strategy that aggregates base learners trained…
arXiv:2607.24786v1 Announce Type: cross Abstract: Weak supervision sets a practical regime for audio-visual sound source localization as dense spatial annotations are costly to obtain at scale.…
arXiv:2607.26249v1 Announce Type: new Abstract: Religious radio is a widespread but understudied form of mass communication in the United States, and content-level analysis of it has…
arXiv:2602.21987v3 Announce Type: replace Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but their quality…
arXiv:2607.27205v1 Announce Type: new Abstract: Vision-language-action (VLA) models commonly adopt an LLM-centric $V to L to A$ pathway, where visual observations are projected into the representation…
arXiv:2607.26164v1 Announce Type: new Abstract: Automated molecular structure elucidation from infrared (IR) spectroscopy data has seen significant advancements in recent years, but its broad applicability is…
arXiv:2607.26490v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance heavily relies…
arXiv:2607.26414v1 Announce Type: new Abstract: Latent low-dimensional structure in datasets of natural and engineered systems enables their sparse sensing, or full-state reconstruction from historical data and…
arXiv:2607.24807v1 Announce Type: cross Abstract: We develop the mathematical and physical formulation of cognitive cost optimization that underlies the path-integral model of consciousness. The goal-directed cognitive…
arXiv:2607.26221v1 Announce Type: new Abstract: With the advancement of AI technologies, Generative AI (GenAI) and human written text have become nearly indistinguishable. Additionally, the global standardization…
arXiv:2607.26452v1 Announce Type: cross Abstract: World models must learn the joint dynamics of states, actions, events, and observations, yet existing video, robotics, and simulation datasets usually…