127,664Total entries

60Added by human

127,604Found by agent

13Categories

Knowledge catalogue

Search: “papers”

16,517 results

Safety

Conditioned Initialization for Attention

DGX agent

arXiv:2609.07086v1 Announce Type: cross Abstract: Transformers are a dominant architecture in modern machine learning, powering applications across vision, language, and beyond. At the core of their s

safetyarxiv-cs-cv

9 Sept 2026

Research

Search: “papers”

Conditioned Initialization for Attention

Constrained Bayesian Optimization for Hierarchical Federated Learning in IoT Networks for Plant Disease Classification

Context-Aware System Synthesis, Task Assignment, and Routing

Coverage Path Planning for Redundant Manipulators using Generalized Spanning Trees

CRISP: Corneal Confocal Microscopy Real-Time Image Stitching Pipeline

CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation

CVT-GS: Learning to Simplify 3D Gaussian Splatting with Centroidal Voronoi Tessellation

D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot Systems

Damage-Aware Bandit Pruning for Vision and Language Transformers

Data Quality Rule Generation with LLMs

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

DDPM Score Matching and Distribution Learning

Deep Learning for Biopsy-Free Subtyping of Basal Cell Carcinoma from Dermatoscopic Images

Depth-to-Image Synthesis-Driven Generative Unguided Depth Completion

DISEIL: Demonstration Distillation for Sample-Efficient Imitation Learning

Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent Transformers

Distribution-free inference on the number of changepoints

DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language Models

EcoFair: Energy-Efficient Inference Routing for Edge AI under Data Degradation

Efficient and Microphone-Fault-Tolerant 3D Sound Source Localization

Efficient Learning and Symmetry Discovery under Exact Invariances

Enhancing Table Structure Recognition via Bounding Box Guidance

Evaluating Vision-Language Models for Image Quality Assessment using Psychophysical Data

Event-Based De-Snowing for Autonomous Driving

Evolution of Multimodal Question Answering: From Modality-Adaptive Extraction to Unified Language Representation

EvoNav-Bench: Benchmarking Lifelong Navigation in Evolving Environments

extbf{PLATO}: Preintegration Learning from Accurate Trajectory Observations for Neural Inertial Odometry

Flow-Matching Guided Deep Unfolding for Hyperspectral Image Reconstruction

FMMO: Detecting the Divergence Between Local Attribution and Global Drift

Gaussian Linear Functional Manifold Method for Massive Point Cloud Data

Generalist Open-World Temporal Perception

Generating from Discrete Distributions Using Diffusions: Insights from Random Constraint Satisfaction Problems

Generation of Vectorized Maps Beyond Vehicle View

Geometry-Aware Bayesian Parameter-Efficient Fine-Tuning on the Stiefel Manifold via Stein Variational Gradient Descent

Hardware Trojan Threats to Multi-Chiplet Photonic Neural Network Accelerators

How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

How to Learn from What a Human Would Avoid? Intervention-Aware World Models with Real-World RL for Dexterous Manipulation

Hyperspectral Anomaly Detection via Group Sparse Low-Rank Tensor Factorization With Automatic Anomaly Grouping

HypLTSF: A Hyperbolic Geometric View of Multi-Scale Hierarchies for Long-Term Time Series Forecasting

IIns-VAE+: A Robust Transfer Learning Framework for Environmental Identification in Wireless Sensing

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models

KDFlow: A User-Friendly and Efficient Knowledge Distillation Framework for Large Language Models

L2G-Map: Local-to-Global Mapping via Hierarchical Diffusion Refinement and Elliptical Bayesian Fusion

Length Generalization for Transformers via Compression

Leveraging contextual events on structure-aware next activity prediction

Lightweight Dynamic Modeling of Cable-Driven Continuum Robots Based on Actuation-Space Energy Formulation

Localized Visual Feature Aggregation via Focus Pooling for Visuomotor Policies

MAC-I^2: Learned Metrics-Aware Covariance for Robust Visual-Inertial Fusion in Initialization and Calibration