arXiv:2512.20675v1 Announce Type: cross Abstract: Learning generalizable reward functions is a core challenge in embodied intelligence. Recent work leverages contrastive vision language models (VLMs) to obtain dense, domain-agnostic rewards without human supervision. These methods adapt VLMs into reward models through increasingly complex learning objectives, yet meaningful comparison remains difficult due to differences in training data, […]
Forecasting N-Body Dynamics: A Comparative Study of Neural Ordinary Differential Equations and Universal Differential Equations
arXiv:2512.20643v1 Announce Type: cross Abstract: The n body problem, fundamental to astrophysics, simulates the motion of n bodies acting under the effect of their own mutual gravitational interactions. Traditional machine learning models that are used for predicting and forecasting trajectories are often data intensive black box models, which ignore the physical laws, thereby lacking interpretability. […]
Nemotron 3 Nano: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
arXiv:2512.20848v1 Announce Type: cross Abstract: We present Nemotron 3 Nano 30B-A3B, a Mixture-of-Experts hybrid Mamba-Transformer language model. Nemotron 3 Nano was pretrained on 25 trillion text tokens, including more than 3 trillion new unique tokens over Nemotron 2, followed by supervised fine tuning and large-scale RL on diverse environments. Nemotron 3 Nano achieves better accuracy […]
Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits
arXiv:2512.20755v1 Announce Type: cross Abstract: Ensuring the safety and efficiency of AI systems is a central goal of modern research. Formal verification provides guarantees of neural network robustness, while early exits improve inference efficiency by enabling intermediate predictions. Yet verifying networks with early exits introduces new challenges due to their conditional execution paths. In this […]
NULLBUS: Multimodal Mixed-Supervision for Breast Ultrasound Segmentation via Nullable Global-Local Prompts
arXiv:2512.20783v1 Announce Type: cross Abstract: Breast ultrasound (BUS) segmentation provides lesion boundaries essential for computer-aided diagnosis and treatment planning. While promptable methods can improve segmentation performance and tumor delineation when text or spatial prompts are available, many public BUS datasets lack reliable metadata or reports, constraining training to small multimodal subsets and reducing robustness. We […]
DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction
arXiv:2512.20898v1 Announce Type: cross Abstract: Lung cancer continues to be the leading cause of cancer-related deaths globally. Early detection and diagnosis of pulmonary nodules are essential for improving patient survival rates. Although previous research has integrated multimodal and multi-temporal information, outperforming single modality and single time point, the fusion methods are limited to inefficient vector […]
Managing the Stochastic: Foundations of Learning in Neuro-Symbolic Systems for Software Engineering
arXiv:2512.20660v1 Announce Type: cross Abstract: Current approaches to AI coding agents appear to blur the lines between the Large Language Model (LLM) and the agent itself, asking the LLM to make decisions best left to deterministic processes. This leads to systems prone to stochastic failures such as gaming unit tests or hallucinating syntax. Drawing on […]
Mixture of Attention Schemes (MoAS): Learning to Route Between MHA, GQA, and MQA
arXiv:2512.20650v1 Announce Type: new Abstract: The choice of attention mechanism in Transformer models involves a critical trade-off between modeling quality and inference efficiency. Multi-Head Attention (MHA) offers the best quality but suffers from large Key-Value (KV) cache memory requirements during inference. Multi-Query Attention (MQA) and Grouped-Query Attention (GQA) reduce memory usage but often at the […]
Disentangling Fact from Sentiment: A Dynamic Conflict-Consensus Framework for Multimodal Fake News Detection
arXiv:2512.20670v1 Announce Type: cross Abstract: Prevalent multimodal fake news detection relies on consistency-based fusion, yet this paradigm fundamentally misinterprets critical cross-modal discrepancies as noise, leading to over-smoothing, which dilutes critical evidence of fabrication. Mainstream consistency-based fusion inherently minimizes feature discrepancies to align modalities, yet this approach fundamentally fails because it inadvertently smoothes out the subtle […]
Enzyme-Substrate Complex Formation Modulates Diffusion-Driven Patterning In Metabolic Pathways
arXiv:2512.15737v2 Announce Type: replace Abstract: We investigate how enzymatic binding kinetics regulate diffusion-driven instabilities in a two-step metabolic pathway. Starting from a mechanistic description in which the substrate reversibly binds to the first enzyme before catalytic conversion, we formulate two reaction-diffusion models: a simplified system with effective kinetics and an extended model that explicitly includes […]