Papers
-
An LP-based Sampling Policy for Multi-Armed Bandits with Side-Observations and Stochastic Availability
-
Vision2Web: A Hierarchical Benchmark for Visual Website Development with Agent Verification
-
PerceptionComp: A Video Benchmark for Complex Perception-Centric Reasoning
-
Tunable Soft Equivariance with Guarantees
-
Zero-Shot Depth from Defocus
-
Ruka-v2: Tendon Driven Open-Source Dexterous Hand with Wrist and Abduction for Robot Learning
-
GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation
-
Weight Tying Biases Token Embeddings Towards the Output Space
-
Learning to Commit: Generating Organic Pull Requests via Online Repository Memory
-
Detailed Geometry and Appearance from Opportunistic Motion
-
TTE-CAM: Built-in Class Activation Maps for Test-Time Explainability in Pretrained Black-Box CNNs
-
Property-Guided Molecular Generation and Optimization via Latent Flows
-
Privacy-Preserving Iris Recognition: Performance Challenges and Outlook
-
Strategic Candidacy in Generative AI Arenas
-
Water-Filling is Universally Minimax Optimal
-
Magic Words or Methodical Work? Challenging Conventional Wisdom in LLM-Based Political Text Annotation
-
Computer Vision with a Superpixelation Camera
-
Are LLMs Good For Quantum Software, Architecture, and System Design?
-
FusionAgent: A Multimodal Agent with Dynamic Model Selection for Human Recognition
-
Comparing Physics-Informed and Neural ODE Approaches for Modeling Nonlinear Biological Systems: A Case Study Based on the Morris-Lecar Model
-
Mimetic Alignment with ASPECT: Evaluation of AI-inferred Personal Profiles
-
Koopman Operator Identification of Model Parameter Trajectories for Temporal Domain Generalization (KOMET)
-
Live Interactive Training for Video Segmentation
-
In your own words: computationally identifying interpretable themes in free-text survey data
-
Tunable Domain Adaptation Using Unfolding
-
Leveraging Avatar Fingerprinting: A Multi-Generator Photorealistic Talking-Head Public Database and Benchmark
-
From 3D Pose to Prose: Biomechanics-Grounded Vision--Language Coaching
-
Multilingual Stutter Event Detection for English, German, and Mandarin Speech
-
Static and Dynamic Approaches to Computing Barycenters of Probability Measures on Graphs
-
Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning
-
Real-time Appearance-based Gaze Estimation for Open Domains
-
Compliance-Aware Predictive Process Monitoring: A Neuro-Symbolic Approach
-
Multimodal Deep Learning for Diabetic Foot Ulcer Staging Using Integrated RGB and Thermal Imaging
-
ASTER -- Agentic Science Toolkit for Exoplanet Research
-
High dimensional theory of two-phase optimizers
-
On the Optimal Number of Grids for Differentially Private Non-Interactive $K$-Means Clustering
-
Neural Approximation of Generalized Voronoi Diagrams
-
Graph Attention Network-Based Detection of Autism Spectrum Disorder
-
Probabilistic Forecasting of Localized Wildfire Spread Based on Conditional Flow Matching
-
Beyond Mortality: Advancements in Post-Mortem Iris Recognition through Data Collection and Computer-Aided Forensic Examination
-
Online Statistical Inference of Constant Sample-averaged Q-Learning
-
Transparency as Architecture: Structural Compliance Gaps in EU AI Act Article 50 II
-
A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
-
A large corpus of lucid and non-lucid dream reports
-
On the Reliability Limits of LLM-Based Multi-Agent Planning
-
ImmSET: Sequence-Based Predictor of TCR-pMHC Specificity at Scale
-
FormalProofBench: Can Models Write Graduate Level Math Proofs That Are Formally Verified?
-
Beyond Freshness and Semantics: A Coupon-Collector Framework for Effective Status Updates
-
AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control
-
PHONOS: PHOnetic Neutralization for Online Streaming Applications
MongoDB - Build AI That Scales
