PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
arXiv:2602.23161v3 Announce Type: replace Abstract: Time series reasoning demands both the perception of complex dynamics and logical depth. However, existing…
From Baselines to Transport Geodesics: Axiomatic Attribution via Optimal Generative Flows
arXiv:2603.05093v2 Announce Type: replace-cross Abstract: Feature attributions often hide a critical modeling choice: they explain a prediction along a counterfactual…
On the Sample Complexity of Differentially Private Policy Optimization
arXiv:2510.21060v3 Announce Type: replace-cross Abstract: Policy optimization (PO) is a cornerstone of modern reinforcement learning (RL), with diverse applications spanning…
AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents
arXiv:2605.06607v3 Announce Type: replace-cross Abstract: Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning…
Zatom-1: Towards a Multimodal Foundation Model for 3D Molecules and Materials
arXiv:2602.22251v4 Announce Type: replace-cross Abstract: General-purpose 3D modeling in chemistry encompasses molecules and materials, requiring both generative and predictive capabilities.…
COGNOS: Universal Enhancement for Time Series Anomaly Detection via Constrained Gaussian-Noise Optimization and Smoothing
arXiv:2511.06894v3 Announce Type: replace-cross Abstract: Reconstruction-based methods are a dominant paradigm in time series anomaly detection (TSAD), however, their near-universal…
Ister: Linear Transformer for Efficient Multivariate Time Series Forecasting
arXiv:2412.18798v3 Announce Type: replace-cross Abstract: Transformer-based models have achieved remarkable success in multivariate time series forecasting (MTSF) by capturing long-range…
TiledAttention: a CUDA Tile SDPA Kernel for PyTorch
arXiv:2603.01960v2 Announce Type: replace-cross Abstract: TiledAttention is a scaled dot-product attention (SDPA) forward operator for SDPA research on NVIDIA GPUs.…
Operating Within the Operational Design Domain: Zero-Shot Perception with Vision-Language Models
arXiv:2605.07649v2 Announce Type: replace-cross Abstract: Over the last few years, research on autonomous systems has matured to such a degree…
One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policy
arXiv:2605.07931v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models increasingly rely on auxiliary world modules to plan over long horizons, yet…