Papers
-
TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Driving
-
DC-Merge: Improving Model Merging with Directional Consistency
-
Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions
-
Hierarchical Collaborative Fusion for 3D Instance-aware Referring Expression Segmentation
-
SPPCSO: Adaptive Penalized Estimation Method for High-Dimensional Correlated Data
-
Synthetic Monitoring Environments for Reinforcement Learning
-
Implementation of Quantum Implicit Neural Representation in Deterministic and Probabilistic Autoencoders for Image Reconstruction/Generation Tasks
-
NOVA: Next-step Open-Vocabulary Autoregression for 3D Multi-Object Tracking in Autonomous Driving
-
GazeMoE: Perception of Gaze Target with Mixture-of-Experts
-
Robust support vector model based on bounded asymmetric elastic net loss for binary classification
-
Learning to Solve Orienteering Problem with Time Windows and Variable Profits
-
Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
-
ODD-SEC: Onboard Drone Detection with a Spinning Event Camera
-
HiPP-Prune: Hierarchical Preference-Conditioned Structured Pruning for Vision-Language Models
-
Agentic retrieval-augmented reasoning reshapes collective reliability under model variability in radiology question answering
-
Looking Through Glass Box
-
Stem: Rethinking Causal Information Flow in Sparse Attention
-
Spectral and Trajectory Regularization for Diffusion Transformer Super-Resolution
-
Artificial Intelligence for Climate Adaptation: Reinforcement Learning for Climate Change-Resilient Transport
-
Can we Trust Unreliable Voxels? Exploring 3D Semantic Occupancy Prediction under Label Noise
-
Attribute Distribution Modeling and Semantic-Visual Alignment for Generative Zero-shot Learning
-
Learning Unbiased Cluster Descriptors for Interpretable Imbalanced Concept Drift Detection
-
Enhancing SHAP Explainability for Diagnostic and Prognostic ML Models in Alzheimer Disease
-
Learning Where the Physics Is: Probabilistic Adaptive Sampling for Stiff PDEs
-
FlowMotion: Training-Free Flow Guidance for Video Motion Transfer
-
The EpisTwin: A Knowledge Graph-Grounded Neuro-Symbolic Architecture for Personal AI
-
Enhanced Protein Intrinsic Disorder Prediction Through Dual-View Multiscale Features and Multi-objective Evolutionary Algorithm
-
3D CBCT Artefact Removal Using Perpendicular Score-Based Diffusion Models
-
DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models
-
Polarized Direct Cross-Attention Message Passing in GNNs for Machinery Fault Diagnosis
-
Continual Adaptation for Pacific Indigenous Speech Recognition
-
Latent Transfer Attack: Adversarial Examples via Generative Latent Spaces
-
WMoE-CLIP: Wavelet-Enhanced Mixture-of-Experts Prompt Learning for Zero-Shot Anomaly Detection
-
Gradient-based Nested Co-Design of Aerodynamic Shape and Control for Winged Robots
-
From Entropy to Calibrated Uncertainty: Training Language Models to Reason About Uncertainty
-
P-SLCR: Unsupervised Point Cloud Semantic Segmentation via Prototypes Structure Learning and Consistent Reasoning
-
The Art That Poses Back: Assessing AI Pastiches after Contemporary Artworks
-
Diversity-Aware Adaptive Collocation for Physics-Informed Neural Networks via Sparse QUBO Optimization and Hybrid Coresets
-
Prediction of Steady-State Flow through Porous Media Using Machine Learning Models
-
Metalearning traffic assignment for network disruptions with graph convolutional neural networks
-
Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions
-
WorldCache: Accelerating World Models for Free via Heterogeneous Token Caching
-
SAHOO: Safeguarded Alignment for High-Order Optimization Objectives in Recursive Self-Improvement
-
AI End-to-End Radiation Treatment Planning Under One Second
-
K-MaT: Knowledge-Anchored Manifold Transport for Cross-Modal Prompt Learning in Medical Imaging
-
Transparent AI for Mathematics: Transformer-Based Large Language Models for Mathematical Entity Relationship Extraction with XAI
-
MoEless: Efficient MoE LLM Serving via Serverless Computing
-
Dynamic Chunking Diffusion Transformer
-
Frequency-Separable Hamiltonian Neural Network for Multi-Timescale Dynamics
-
LATO: 3D Mesh Flow Matching with Structured TOpology Preserving LAtents
