1273993 results (page 135 of 50960)
-
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting
As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity to a strict operational requirement. Our work is motivated by the explanations of autoregressive neural predictions on dynamic physical fields, as in weather forecasting. Gradient-based feature attrib…
-
Useful nonrobust features are ubiquitous in biomedical images
We study whether deep networks for medical imaging learn useful nonrobust features - predictive input patterns that are not human interpretable and highly susceptible to small adversarial perturbations - and how these features impact test performance. We show that models trained only on nonrobust features achieve well above chance accuracy across five MedMNIST classification tasks, confirming thei…
-
QuantClaw: Precision Where It Matters for OpenClaw
Autonomous agent systems such as OpenClaw introduce significant efficiency challenges due to long-context inputs and multi-turn reasoning. This results in prohibitively high computational and monetary costs in real-world development. While quantization is a standard approach for reducing cost and latency, its impact on agent performance in realistic scenarios remains unclear. In this work, we anal…
-
A Comparison of ROS 2 and AUTOSAR Adaptive Platform Against Industry-Elicited Automotive Middleware Requirements
In software-defined vehicles, automotive middleware plays a fundamental role in enabling efficient communication, integration, and coordination among software components. This paper examines how well two of the currently most popular middleware frameworks, ROS 2 Jazzy and AUTOSAR Adaptive Platform R24-11, meet practical requirements elicited from automotive software engineers at one of the major a…
-
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference
Scaling context length is reshaping large-model development, yet full-attention Transformers suffer from prohibitive computation and inference bottlenecks at long sequences. A key challenge is to design foundation models that maintain performance and long-context efficiency with minimal training overhead. We introduce SpikingBrain2.0 (SpB2.0), a 5B model that advances both architecture and trainin…
-
A homogeneous three-dimensional view of Molecular Cloud kinematics out to 2.5 kpc. Using Young Stellar Objects and Open Clusters as complementary tracers
Understanding the large-scale dynamics of molecular clouds (MCs) is crucial for constraining the processes that govern star formation and the structure and evolution of the Galaxy. While gas tracers have traditionally been used to map MC kinematics, stellar tracers such as young stellar objects (YSOs) and open clusters (OCs) provide a complementary approach that enables direct comparisons between …
-
Design, Cups, and Blankets. A Free-Energy-Principle-Based Approach to Product Design
We formalize a new inference problem: requirement-steered interface type inference. Given spatiotemporal observations of a physical system and functional requirements, the task is to infer what kind of interface must separate the system's interior from its environment for those requirements to be satisfiable. Unlike classical constrained design, which optimizes parameters within a pre-specified ob…
-
LARA: Validation-Driven Agentic Supercomputer Workflows for Atomistic Modeling
Large language models (LLMs) and agentic systems have recently demonstrated potential for automating scientific workflows, including atomistic simulations. However, their deployment in high-performance computing (HPC) environments remains limited by the lack of mechanisms ensuring correctness, reproducibility, and safe interaction with computational resources. Generated workflows suffer from incon…
-
Acyclic Monotone Operators Are Not Closed Under Addition
Borwein and Wiersma [SIAM J. Optim. 18(3) (2007), 946-960] asked if the set of acyclic monotone operators is closed under addition. We answer this question in the negative.
-
Adversarial Co-Evolution of Malware and Detection Models: A Bilevel Optimization Perspective
Machine learning-based malware detectors are increasingly vulnerable to adversarial examples. Traditional defenses, such as one-shot adversarial training, often fail against adaptive attackers who use reinforcement learning to bypass detection. This paper proposes a robust defense framework based on bilevel optimization, explicitly modeling the strategic interaction between a defender and an attac…
-
Learning Evidence Highlighting for Frozen LLMs
Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers. HiLight avoids compressing or rewriting the input, which can discard or distort evidence, by training a lightweight Emphasis Actor to insert minimal hig…
-
Accelerating Frequency Domain Diffusion Models with Error-Feedback Event-Driven Caching
Diffusion models achieve remarkable success in time series generation. However, slow inference limits their practical deployment. We propose E$^2$-CRF (Error-Feedback Event-Driven Cumulative Residual Feature caching) to accelerate frequency domain diffusion models. Our method exploits two structural properties: (1) spectral localization, where signal energy concentrates in low frequencies, and (2)…
-
Relational Archetypes: A Comparative Analysis of AV-Human and Agent-Human Interactions
Over the last couple of years, AI Agents have gained significant traction due to substantial progress in the capabilities of underlying General Purpose AI (GPAI) models, enhanced scaffolding techniques, and the promise to drive societal transformation. Companies, researchers, and policy makers have started to consider the different effects that AI agents may have across different dimensions of our…
-
Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy
Client contribution estimation in Federated Learning is necessary for identifying clients' importance and for providing fair rewards. Current methods often rely on server-side validation data or self-reported client information, which can compromise privacy or be susceptible to manipulation. We introduce a data-free signal based on the matrix von Neumann (spectral) entropy of the final-layer updat…
-
Cross-Stage Coherence in Hierarchical Driving VQA: Explicit Baselines and Learned Gated Context Projectors
Graph Visual Question Answering (GVQA) for autonomous driving organizes reasoning into ordered stages, namely Perception, Prediction, and Planning, where planning decisions should remain consistent with the model's own perception. We present a comparative study of cross-stage context passing on DriveLM-nuScenes using two complementary mechanisms. The explicit variant evaluates three prompt-based c…
-
Module Lattice Security (Part II): Module Lattice Reduction via Optimal Sign Selection
We extend the CDPR lattice reduction algorithm from ideal to module lattices, leveraging the trace orthogonality of the power basis to decompose the module into rank-1 submodules and applying CDPR independently to each. This base module reduction achieves a Hermite factor $\exp(\tilde{O}(\sqrt{n}))$ matching the ideal case, with a module reduction factor $O(1)$ independent of the rank, under a bal…
-
A Quasar--Companion System Without AGN Outflow at $z \sim 6$: The Case of PSO J083+11
PSO J083.8371+11.8482, a quasar at $z = 6.34$ with a nearby companion galaxy, provides an opportunity to study the impact of active galactic nucleus (AGN) activity on the surrounding environment during the epoch of reionization. We analyze ALMA observations of the [C\,\textsc{ii}] 158~$μ$m emission line and the far-infrared (FIR) continuum, which trace cold interstellar gas and dust-reprocessed ra…
-
SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning
As Multimodal Large Language Models (MLLMs) mature, GUI agents are evolving from static interactions to complex navigation. While Reinforcement Learning (RL) has emerged as a promising paradigm for training MLLM agents on dynamic GUI tasks, its effective application faces a dilemma. Standard Offline RL often relies on static step-level data, neglecting global trajectory semantics such as task comp…
-
Are Natural-Domain Foundation Models Effective for Accelerated Cardiac MRI Reconstruction?
The emergence of large-scale pretrained foundation models has transformed computer vision, enabling strong performance across diverse downstream tasks. However, their potential for physics-based inverse problems, such as accelerated cardiac MRI reconstruction, remains largely underexplored. In this work, we investigate whether natural-domain foundation models can serve as effective image priors fo…
-
Using Embedding Models to Improve Probabilistic Race Prediction
Estimating racial disparity requires individual-level race data, which are often unavailable due to the sensitivity of collecting such information. To address this problem, many researchers utilize Bayesian Improved Surname Geocoding (BISG), which have critically relied on Census surname data. Unfortunately, these data capture race-surname relationships only for common surnames, omitting approxima…
-
Video Analysis and Generation via a Semantic Progress Function
Transformations produced by image and video generation models often evolve in a highly non-linear manner: long stretches where the content barely changes are followed by sudden, abrupt semantic jumps. To analyze and correct this behavior, we introduce a Semantic Progress Function, a one-dimensional representation that captures how the meaning of a given sequence evolves over time. For each frame, …
-
Transferable Physical-World Adversarial Patches Against Pedestrian Detection Models
Physical adversarial patch attacks critically threaten pedestrian detection, causing surveillance and autonomous driving systems to miss pedestrians and creating severe safety risks. Despite their effectiveness in controlled settings, existing physical attacks face two major limitations in practice: they lack systematic disruption of the multi-stage decision pipeline, enabling residual modules to …
-
QDTraj: Exploration of Diverse Trajectory Primitives for Articulated Objects Robotic Manipulation
Thanks to the latest advances in learning and robotics, domestic robots are beginning to enter homes, aiming to execute household chores autonomously. However, robots still struggle to perform autonomous manipulation tasks in open-ended environments. In this context, this paper presents a method that enables a robot to manipulate a wide spectrum of articulated objects. In this paper, we automati…
-
ArmSSL: Adversarial Robust Black-Box Watermarking for Self-Supervised Learning Pre-trained Encoders
Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurrently satisfy the following two practical requirements: (1) provide ownership verification capability under black-box suspect model access once the stolen encoders are used in downstream tasks; (2) be robust under adversarial watermark detection or r…
-
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show that this challenge stems from a bias in traditional recommendation objectives, which induces a spectral phenomenon termed low-frequency explosion, thereby fundamentally hindering the effective learning of graph filters. T…