1273993 results (page 140 of 50960)
-
Pliable rejection sampling
Rejection sampling is a technique for sampling from difficult distributions. However, its use is limited due to a high rejection rate. Common adaptive rejection sampling methods either work only for very specific distributions or without performance guarantees. In this paper, we present pliable rejection sampling (PRS), a new approach to rejection sampling, where we learn the sampling proposal usi…
-
Simulation-based Inference for Gravitational Waves from Binary Neutron Stars: Application of Summary Data from Heterodyning
Gravitational-wave parameter estimation for binary neutron star (BNS) systems poses severe computational challenges due to the extended signal duration, which can reach several minutes in current detectors. Neural posterior estimation (NPE), a simulation-based inference approach, offers dramatic speedups but requires effective dimensionality reduction of the high-dimensional input data. We present…
-
Efficient Diffusion Distillation via Embedding Loss
Recent advances in distilling expensive diffusion models into efficient few-step generators show significant promise. However, these methods typically demand substantial computational resources and extended training periods, limiting accessibility for resource-constrained researchers, and existing supplementary loss functions have notable limitations. Regression loss requires pre-generating large …
-
Adaptive vs. Static Robot-to-Human Handover: A Study on Orientation and Approach Direction
Robot-to-human handovers often rely on static, open-loop strategies (or, at best, approaches that adapt only the position), which generally do not consider how the object will be grasped by the human, thus requiring the user to adapt. This work presents a novel adaptive framework that dynamically adjusts the object's delivery pose in real time based on the user's hand pose and the intended downstr…
-
Selective Contrastive Learning For Gloss Free Sign Language Translation
Sign language translation (SLT) converts continuous sign videos into spoken-language text, yet it remains challenging due to the intrinsic modality mismatch between visual signs and written text, particularly in gloss-free settings. Recent SLT systems increasingly adopt CLIP-like Vision-Language pretraining (VLP) for cross-modal alignment, but the random in-batch contrast provides few, batch-depen…
-
RouteGuard: Internal-Signal Detection of Skill Poisoning in LLM Agents
Agent skills introduce a new and more severe form of indirect injection for LLM agents: unlike traditional indirect prompt injection, attackers can hide malicious instructions inside a dense, action-oriented skill that already functions as a legitimate instruction source. We study pre-execution skill-poison detection and show that successful skill poisoning induces a structured internal effect, at…
-
Testing $Λ$CDM with ANN-Reconstructed Expansion History from Cosmic Chronometers
In modern cosmology, the rapid growth of high-precision observational data, along with significant theoretical advances, has intensified the challenge of identifying a robust, model-independent framework to probe the expansion history of the Universe. In this work, we propose a novel artificial neural network (ANN)-based framework for the non-parametric reconstruction of the late-time cosmic expan…
-
CNSL-bench: Benchmarking the Sign Language Understanding Capabilities of MLLMs on Chinese National Sign Language
Sign language research has achieved significant progress due to the advances in large language models (LLMs). However, the intrinsic ability of LLMs to understand sign language, especially in multimodal contexts, remains underexplored. To address this limitation, we introduce CNSL-bench, the first comprehensive Chinese em{National Sign Language benchmark designed for evaluating multimodal large la…
-
Statistical Estimation of Monge Transport Maps via Brenier Potentials
We introduce and analyze a statistical estimator for Monge transport maps: solutions to the quadratic optimal transport problem in Euclidean space. For absolutely continuous source measures, this map is uniquely defined as the gradient of a convex function, a result known as Brenier's theorem. Without absolute continuity, the problem is relaxed, maps are replaced by coupling measures, and optimal …
-
Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement
Thermal infrared image enhancement aims to restore high-quality images from complex compound degradations. Existing all-in-one approaches typically employ a single shared backbone to handle diverse degradations, which causes gradient interference and parameter competition. To address this, we propose a Structural Entropy-Guided Decoupled (SEGD) Framework. Unlike unified modeling paradigms, SEGD de…
-
LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios
Household environments present one of the most common, impactful yet challenging application domains for robotics. Within household scenarios, manipulating deformable objects is particularly difficult, both in simulation and real-world execution, due to varied categories and shapes, complex dynamics, and diverse material properties, as well as the lack of reliable deformable-object support in exis…
-
Ownership Refinement Types for Pointer Arithmetic and Nested Arrays
Tanaka et al. proposed a type system for verifying functional correctness properties of programs that use arrays and pointer arithmetic. Their system extends ConSORT -- a type system combining fractional ownership and refinement types for imperative program verification -- with support for pointer arithmetic. Their idea was to extend fractional ownership so that it can depend on an array index. Th…
-
Revisiting Neural Activation Coverage for Uncertainty Estimation
Neural activation coverage (NAC) is a recently-proposed technique for out-of-distribution detection and generalization. We build upon this promising foundation and extend the method to work as an uncertainty estimation technique for already-trained artificial neural networks in the domain of regression. Our experiments confirm NAC uncertainty scores to be more meaningful than other techniques, e.g…
-
A study of the spatial evolution of the Radcliffe wave in a sample of young open star clusters
A sample of 139 young open star clusters closely associated with the Radcliffe wave is considered. Modeling their spatial distribution and kinematics over a time interval of 30 Myrs ago and 30 Myrs into the future revealed that they exhibit the main properties characteristic of a Radcliffe wave over the past 10-15 Myr. They are distributed on the galactic XY plane as a long and narrow chain inclin…
-
Large Language Model Counterarguments in Older Adults: Cognitive Offloading or Vulnerability to Moral Persuasion?
This study examined whether counterarguments generated by large language models (LLMs) influence the moral judgments of younger and older adults and whether these effects vary as a function of dilemma type, cognitive functioning, trust in AI, and prior experience using LLMs. Using the switch and footbridge trolley dilemmas, 130 participants (56 younger adults and 74 older adults) were presented wi…
-
SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
Classical ReLU-based Input Convex Neural Networks (ICNNs) are equivalent to the optimal value functions of Linear Programming (LP). This intrinsic structural equivalence restricts their representational capacity to piecewise-linear polyhedral functions. To overcome this representational bottleneck, we propose the SOC-ICNN, an architecture that generalizes the underlying optimization class from LP …
-
One Shot Learning for Edge Detection on Point Clouds
Each scanner possesses its unique characteristics and exhibits its distinct sampling error distribution. Training a network on a dataset that includes data collected from different scanners is less effective than training it on data specific to a single scanner. Therefore, we present a novel one-shot learning method allowing for edge extraction on point clouds, by learning the specific data distri…
-
PoseFM: Relative Camera Pose Estimation Through Flow Matching
Monocular visual odometry (VO) is a fundamental computer vision problem with applications in autonomous navigation, augmented reality and more. While deep learning-based methods have recently shown superior accuracy compared to traditional geometric pipelines, particularly in environments where handcrafted features struggle due to poor structure or lighting conditions, most rely on deterministic r…
-
Thermal background reduction for mid-infrared imaging by low-rank background and sparse point-source modelling
Mid-infrared astronomy from the ground faces critical challenges in accurately detecting and quantifying sources due to the dominant spatially and time-variable background noise. Moreover, chopping and nodding, the traditional methods for dealing with these background issues, will not be technically feasible on the next generation of extremely large telescopes. This limitation requires the develop…
-
A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency
Clinical risk prediction using longitudinal medical data supports individualized care. Self-supervised foundation models have emerged as a promising approach for leveraging large-scale unlabeled healthcare records. In natural language processing, scaling laws suggest that larger models achieve predictably lower pretraining losses, supporting the foundation model paradigm. However, for structured m…
-
Federated Cross-Modal Retrieval with Missing Modalities via Semantic Routing and Adapter Personalization
Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modalities. Under such heterogeneity, a single global model is often insufficient to capture both shared cross-modal knowledge and client-specific characteristics. We propose RCSR, a personalization-friendly federated framework that integrates prototype an…
-
A Morphological Identification and Study of Radio Galaxies from LoTSS DR2. I. The "Winged'' Radio Galaxies
We conducted an extensive identification and analysis of various morphological classes and subclasses of radio galaxies using the latest high-resolution data from the second data release of the LOFAR Two-Metre Sky Survey (LoTSS DR2). This paper presents the first results of our large-scale investigation: a new catalog of ``winged" radio galaxies (WRGs). These objects represent a fascinating class …
-
Preference Heads in Large Language Models: A Mechanistic Framework for Interpretable Personalization
Large Language Models (LLMs) exhibit strong implicit personalization ability, yet most existing approaches treat this behavior as a black box, relying on prompt engineering or fine tuning on user data. In this work, we adopt a mechanistic interpretability perspective and hypothesize the existence of a sparse set of Preference Heads, attention heads that encode user specific stylistic and topical p…
-
Dynamic Moiré Potentials and Robust Wigner Crystallization in Large-Scale Twisted Transition Metal Dichalcogenides
Understanding the dynamical evolution of large-scale moiré systems is crucial for connecting theoretical predictions with experimental observations. Here we develop a machine-learning-based workflow, integrating DeePMD and DeepH frameworks with first-principles calculations, to efficiently investigate time-dependent structural and electronic responses in twisted bilayer transition metal dichalcoge…
-
The Leiden/ESA Astrophysics Program for Summer Students (LEAPS)
International student mobility plays a critical role in shaping future research careers, particularly in highly globalized fields such as astrophysics. The Leiden/ESA Astrophysics Program for Summer Students (LEAPS) offers a 10-week, fully funded research program at Leiden Observatory and the European Space Agency's ESTEC centre for undergraduate and master's students. Designed to foster early res…