arXiv Scientific Papers
π arxiv.com
Articles from arXiv Scientific Papers (81)
TimeSearch-R: Adaptive Temporal Search for Long-Form Video Understanding via Self-Verification Reinforcement Learning
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works atte
DGTN: Graph-Enhanced Transformer with Diffusive Attention Gating Mechanism for Enzyme DDG Prediction
Predicting the effect of amino acid mutations on enzyme thermodynamic stability (DDG) is fundamental to protein engineering and drug design. While recent deep learning approaches have shown promise, t
SoilX: Calibration-Free Comprehensive Soil Sensing Through Contrastive Cross-Component Learning
Precision agriculture demands continuous and accurate monitoring of soil moisture (M) and key macronutrients, including nitrogen (N), phosphorus (P), and potassium (K), to optimize yields and conserve
On Flow Matching KL Divergence
We derive a deterministic, non-asymptotic upper bound on the Kullback-Leibler (KL) divergence of the flow-matching distribution approximation. In particular, if the $L_2$ flow-matching loss is bounded
A Metamorphic Testing Perspective on Knowledge Distillation for Language Models of Code: Does the Student Deeply Mimic the Teacher?
Transformer-based language models of code have achieved state-of-the-art performance across a wide range of software analytics tasks, but their practical deployment remains limited due to high computa
AI Literacy Assessment Revisited: A Task-Oriented Approach Aligned with Real-world Occupations
As artificial intelligence (AI) systems become ubiquitous in professional contexts, there is an urgent need to equip workers, often with backgrounds outside of STEM, with the skills to use these tools
Precipitation nowcasting of satellite data using physically conditioned neural networks
Accurate short-term precipitation forecasts predominantly rely on dense weather-radar networks, limiting operational value in places most exposed to climate extremes. We present TUPANN (Transferable a
SiamMM: A Mixture Model Perspective on Deep Unsupervised Learning
Recent studies have demonstrated the effectiveness of clustering-based approaches for self-supervised and unsupervised learning. However, the application of clustering is often heuristic, and the opti
Synapse: Adaptive Arbitration of Complementary Expertise in Time Series Foundational Models
Pre-trained Time Series Foundational Models (TSFMs) represent a significant advance, capable of forecasting diverse time series with complex characteristics, including varied seasonalities, trends, an
SWE-Compass: Towards Unified Evaluation of Agentic Coding Abilities for Large Language Models
Evaluating large language models (LLMs) for software engineering has been limited by narrow task coverage, language bias, and insufficient alignment with real-world developer workflows. Existing bench
Parameter-Efficient Conditioning for Material Generalization in Graph-Based Simulators
Graph network-based simulators (GNS) have demonstrated strong potential for learning particle-based physics (such as fluids, deformable solids, and granular flows) while generalizing to unseen geometr
Self-adaptive weighting and sampling for physics-informed neural networks
Physics-informed deep learning has emerged as a promising framework for solving partial differential equations (PDEs). Nevertheless, training these models on complex problems remains challenging, ofte
How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?
Recent advances in 3D point cloud transformers have led to state-of-the-art results in tasks such as semantic segmentation and reconstruction. However, these models typically rely on dense token repre
APP: Accelerated Path Patching with Task-Specific Pruning
Circuit discovery is a key step in many mechanistic interpretability pipelines. Current methods, such as Path Patching, are computationally expensive and have limited in-depth circuit analysis for sma
"I Like That You Have to Poke Around": Instructors on How Experiential Approaches to AI Literacy Spark Inquiry and Critical Thinking
As artificial intelligence (AI) increasingly shapes decision-making across domains, there is a growing need to support AI literacy among learners beyond computer science. However, many current approac
ProDER: A Continual Learning Approach for Fault Prediction in Evolving Smart Grids
As smart grids evolve to meet growing energy demands and modern operational challenges, the ability to accurately predict faults becomes increasingly critical. However, existing AI-based fault predict
Multi-modal Loop Closure Detection with Foundation Models in Severely Unstructured Environments
Robust loop closure detection is a critical component of Simultaneous Localization and Mapping (SLAM) algorithms in GNSS-denied environments, such as in the context of planetary exploration. In these
Dark Energy Survey Year 3 results: Simulation-based $w$CDM inference from weak lensing and galaxy clustering maps with deep learning. I. Analysis design
Data-driven approaches using deep learning are emerging as powerful techniques to extract non-Gaussian information from cosmological large-scale structure. This work presents the first simulation-base
X-Diffusion: Training Diffusion Policies on Cross-Embodiment Human Demonstrations
Human videos can be recorded quickly and at scale, making them an appealing source of training data for robot learning. However, humans and robots differ fundamentally in embodiment, resulting in mism
Multi-Method Analysis of Mathematics Placement Assessments: Classical, Machine Learning, and Clustering Approaches
This study evaluates a 40-item mathematics placement examination administered to 198 students using a multi-method framework combining Classical Test Theory, machine learning, and unsupervised cluster
Forgetting is Everywhere
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of f
Real-to-Sim Robot Policy Evaluation with Gaussian Splatting Simulation of Soft-Body Interactions
Robotic manipulation policies are advancing rapidly, but their direct evaluation in the real world remains costly, time-consuming, and difficult to reproduce, particularly for tasks involving deformab
VeriCoT: Neuro-symbolic Chain-of-Thought Validation via Logical Consistency Checks
LLMs can perform multi-step reasoning through Chain-of-Thought (CoT), but they cannot reliably verify their own logic. Even when they reach correct answers, the underlying reasoning may be flawed, und
Nowcast3D: Reliable precipitation nowcasting via gray-box learning
Extreme precipitation nowcasting demands high spatiotemporal fidelity and extended lead times, yet existing approaches remain limited. Numerical Weather Prediction (NWP) and its deep-learning emulatio
TT-Prune: Joint Model Pruning and Resource Allocation for Communication-efficient Time-triggered Federated Learning
Federated learning (FL) offers new opportunities in machine learning, particularly in addressing data privacy concerns. In contrast to conventional event-based federated learning, time-triggered feder
Optimal Inference Schedules for Masked Diffusion Models
A major bottleneck of standard auto-regressive large language models is that their inference process is inherently sequential, resulting in very long and costly inference times. To circumvent this, pr
DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration
Cooperative multi-agent planning requires agents to make joint decisions with partial information and limited communication. Coordination at the trajectory level often fails, as small deviations in ti
Efficient probabilistic surrogate modeling techniques for partially-observed large-scale dynamical systems
This paper is concerned with probabilistic techniques for forecasting dynamical systems described by partial differential equations (such as, for example, the Navier-Stokes equations). In particular,
Addressing divergent representations from causal interventions on neural networks
A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask wheth
Question the Questions: Auditing Representation in Online Deliberative Processes
A central feature of many deliberative processes, such as citizens' assemblies and deliberative polls, is the opportunity for participants to engage directly with experts. While participants are typic
Are We Asking the Right Questions? On Ambiguity in Natural Language Queries for Tabular Data Analysis
Natural language interfaces to tabular data must handle ambiguities inherent to queries. Instead of treating ambiguity as a deficiency, we reframe it as a feature of cooperative interaction, where the
Jr. AI Scientist and Its Risk Report: Autonomous Scientific Exploration from a Baseline Paper
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the acade
Integrating Temporal and Structural Context in Graph Transformers for Relational Deep Learning
In domains such as healthcare, finance, and e-commerce, the temporal dynamics of relational data emerge from complex interactions-such as those between patients and providers, or users and products ac
Optimizing Sensor Placement in Urban Storm Sewers: A Data-Driven Sparse Sensing Approach
Urban surface water flooding, triggered by intense rainfall overwhelming drainage systems, is increasingly frequent and widespread. While flood prediction and monitoring in high spatial-temporal resol
LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems
Modeling user preferences across domains remains a key challenge in slate recommendation (i.e. recommending an ordered sequence of items) research. We investigate how Large Language Models (LLM) can e
Supersonic and Superluminal Energy and Speed of Information via Temporal Interference in a Dispersionless Environment
Numerical implementation of a theory yields acoustic wave packets whose peak-to-peak speeds, $c_{3d}$, are supersonic in a dispersionless medium due to temporal interference between direct and boundar
The swinging counterweight trebuchet. On internal forces
The forces that act internally in a trebuchet as it delivers a shot depend on the motions of throwing arm, counterweight and sling. These motions are considered known experimentally or theoretically a
Light Propagation in $ΞΊ$-Minkowski Space-Time: Gauge Ambiguities and Invariance
We study the noncommutative $U(1)$ gauge theory on the $\kappa$-Minkowski space-time at the semiclassical approximation. We construct exact solutions of the deformed Maxwell equations in vacuum, descr
Mechanics as a general-relativistic gauge field theory, and Relational Quantization
We treat Mechanics as a 1-dimensional general-relativistic gauge field theory, Mechanical Field Theory (MFT), introducing what we call the Mechanical Field Space (MFS) and exploiting its bundle geomet
Optimal control approach to Olympic weightlifting exercise: Minimal model of the snatch pull
We theoretically investigate the biomechanical aspects of Olympic weightlifting within the framework of optimal control theory. The squared force and the rate of force development (RFD) defined by the
Polaron versus Anderson Localization
We compare two kinds of affine localizations in physics: the localization in a short range polaron and the one in a Wick rotated Anderson stochastic model. The conditions on the interaction potential
Temperature of the Vacuum
In a recent trilogy we proposed a Statistical Theory of General Relativity spacetime. Here we apply our new theory to determine the (energy) ``density'' and (virial) ``temperature'' dependence of the
The Sun's magnetic midlife crisis
The Sun is just one of a hundred billion stars in the Milky Way galaxy. Our front-row seat on Earth allows us to observe it in much greater detail than we can for other stars. However, those observati
Reply to Hofer-SzabΓ³: the PBR theorem hasn't been saved
Recently, in Found. Phys. 53: 64 (2023), it has been argued that there is no reality to the PBR theorem. In Found. Phys. 54: 36 (2024), Hofer-Szab\'o has commented that the argument is flawed and that
Estimation of $Ο$ via experiment
In this study, we conducted an experiment to estimate $\pi$ using body-to-body and body-to-wall collisions. By geometrically analyzing the system's motion, we first review how the collision count corr