10,277,557 results
Showing 961–980 · 1.51 seconds · RSS
-
Preprint Full text
UniQueR: Unified Query-based Feedforward 3D Reconstruction
We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT, and AnySplat typically predict per-pixel point maps or pixel-aligned Gaussians, which remain fundamentally 2.5D and…
-
Preprint Full text
Gau-Occ: Geometry-Completed Gaussians for Multi-Modal 3D Occupancy Prediction
3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a multi-modal framework that bypasses dense volumetric processing…
-
Preprint Full text
Agent Audit: A Security Analysis System for LLM Agent Applications
What should a developer inspect before deploying an LLM agent: the model, the tool code, the deployment configuration, or all three? In practice, many security failures in agent systems arise not from model weights alone, but from the surrounding software stack: tool functions that pass untrusted…
-
Preprint Full text
Avoiding Over-smoothing in Social Media Rumor Detection with Pre-trained Propagation Tree Transformer
Deep learning techniques for rumor detection typically utilize Graph Neural Networks (GNNs) to analyze post relations. These methods, however, falter due to over-smoothing issues when processing rumor propagation structures, leading to declining performance. Our investigation into this issue…
-
Preprint Full text
TorR: Towards Brain-Inspired Task-Oriented Reasoning via Cache-Oriented Algorithm-Architecture Co-design
Task-oriented object detection (TOOD) atop CLIP offers open-vocabulary, prompt-driven semantics, yet dense per-window computation and heavy memory traffic hinder real-time, power-limited edge deployment. We present \emph{TorR}, a brain-inspired \textbf{algorithm--architecture co-design} that…
-
Preprint Full text
Retrieval-Guided Photovoltaic Inventory Estimation from Satellite Imagery for Distribution Grid Planning
The rapid expansion of distributed rooftop photovoltaic (PV) systems introduces increasing uncertainty in distribution grid planning, hosting capacity assessment, and voltage regulation. Reliable estimation of rooftop PV deployment from satellite imagery is therefore essential for accurate modeling…
-
Preprint Full text
Secure Two-Party Matrix Multiplication from Lattices and Its Application to Encrypted Control
In this study, we propose a two-party computation protocol for approximate matrix multiplication of fixed-point numbers. The proposed protocol is provably secure under standard lattice-based cryptographic assumptions and enables matrix multiplication at a desired approximation level within a single…
-
Preprint Full text
The Coordinate System Problem in Persistent Structural Memory for Neural Architectures
We introduce the Dual-View Pheromone Pathway Network (DPPN), an architecture that routes sparse attention through a persistent pheromone field over latent slot transitions, and use it to discover two independent requirements for persistent structural memory in neural networks. Through five…
-
Preprint Full text
Who Sits Where? Automated Detection of Director Interlocks in Indian Companies
Interlocking directorships-where individuals simultaneously serve on the boards of multiple corporations-can facilitate the exchange of expertise and strategic alignment but also present risks, including conflicts of interest, economic 'oligarchy', and regulatory non-compliance. In contexts such as…
-
Preprint Full text
A Feature Shuffling and Restoration Strategy for Universal Unsupervised Anomaly Detection
Unsupervised anomaly detection is vital in industrial fields, with reconstruction-based methods favored for their simplicity and effectiveness. However, reconstruction methods often encounter an identical shortcut issue, where both normal and anomalous regions can be well reconstructed and fail to…
-
Preprint Full text
The Fate of the Milky Way--Andromeda System: To Merge or Not?
It has long been predicted that the Milky Way (MW) will eventually merge with Andromeda (M31), a view reinforced by \textit{HST} measurements indicating a small M31 transverse velocity. However, using updated \textit{Gaia}-based proper motions (PMs) and including the dynamical influence of the…
-
Preprint Full text
A search for heavy axion-like particles in light-by-light scattering at the FCC-hh
A virtual production of heavy axion-like particles (ALPs) via light-by-light scattering in pp, pPb and Pb collisions at the future 100 TeV collider FCC-hh is studied. Both differential and total cross sections are calculated. The 95\% C.L. exclusion limits, as well as $3σ$ and $5σ$ discovery limits…
-
Preprint Full text
Electron scattering by a magnetic monopole in solid-state experiments
The scheme of experiment for studying electron scattering in the field of a magnetic monopole in two dimensional electron gas is proposed. The differential scattering cross section is obtained in the eikonal approximation. For unpolarized initial electron, the differential cross section coincides…
-
Preprint Full text
Aerial Agentic AI: Synergizing LLM and SLM for Low-Altitude Wireless Networks
Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and mobile terminals, are emerging as a critical extension of 6G. However, applying Large Language Models in LAWNs faces three major challenges: 1) Computational and energy constraints; 2) Communication and…
-
Preprint Full text
TRINE: A Token-Aware, Runtime-Adaptive FPGA Inference Engine for Multimodal AI
Multimodal stacks that mix ViTs, CNNs, GNNs, and transformer NLP strain embedded platforms because their compute/memory patterns diverge and hard real-time targets leave little slack. TRINE is a single-bitstream FPGA accelerator and compiler that executes end-to-end multimodal inference without…
-
Preprint Full text
Agent-Sentry: Bounding LLM Agents via Execution Provenance
Agentic computing systems, which autonomously spawn new functionalities based on natural language instructions, are becoming increasingly prevalent. While immensely capable, these systems raise serious security, privacy, and safety concerns. Fundamentally, the full set of functionalities offered by…
-
Preprint Full text
Designing to Forget: Deep Semi-parametric Models for Unlearning
Recent advances in machine unlearning have focused on developing algorithms to remove specific training samples from a trained model. In contrast, we observe that not all models are equally easy to unlearn. Hence, we introduce a family of deep semi-parametric models (SPMs) that exhibit…
-
Preprint Full text
Dynamical Systems Theory Behind a Hierarchical Reasoning Model
Current large language models (LLMs) primarily rely on linear sequence generation and massive parameter counts, yet they severely struggle with complex algorithmic reasoning. While recent reasoning architectures, such as the Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM)…
-
Preprint Full text
ForeSea: AI Forensic Search with Multi-modal Queries for Video Surveillance
Despite decades of work, surveillance still struggles to find specific targets across long, multi-camera video. Prior methods -- tracking pipelines, CLIP based models, and VideoRAG -- require heavy manual filtering, capture only shallow attributes, and fail at temporal reasoning. Real-world…
-
Preprint Full text
A Lavrentiev phenomenon in the neo-Hookean model
We exhibit a Lavrentiev gap phenomenon for the neo-Hookean energy in three-dimensional nonlinear elasticity. More precisely, we construct boundary data for which the infimum of the neo-Hookean energy over deformations satisfying a natural regularity and invertibility condition is strictly larger…
Showing at most 50 pages. Narrow your search with filters for more specific results.