Masked point learning framework for robust 3D representation learning.

An agentic system for end-to-end data analysis with sandboxed execution and action traces.

Gated Graph Attention Network for Alzheimer's Disease detection using speech biomarkers.

A benchmark of 120 PowerPoint tasks to evaluate computer-use agents.

A Ruby web framework for building secure, fast, and maintainable applications.

A benchmark for measuring the trade-off between security and fidelity in prompt injection defenses.

A framework and benchmark for evaluating LM-integrated database systems.

An entropy-adaptive token filtering method for RLVR to improve LLM reasoning accuracy.

A 111B-parameter hybrid reasoning model for multilingual tool-using agents.

A plug-in memory controller for selective updates in sequentially evolving LLM memory.

A MARL framework guided by hyperproperties and temporal logic HyperLTL.

A platform for studying open-world artificial life using autonomous LLM agents.

An interactive benchmark for evaluating agents' ability to help users construct preferences.

Memory-aware uncertainty filter for robust monocular Gaussian mapping in dynamic environments.

A modular framework for diverse pseudo-anomaly synthesis in unsupervised 3D anomaly detection.

Feature-Modulated Bidirectional Label Smoothing for Neural Network Calibration.

Semantics-Guided Deformation Regularization for Dynamic 3D Gaussian Splatting.

A systematic study and dataset for sensory-vector prompt injection attacks on LLM-controlled ROS 2 robots.

Code and data for measuring ideological plasticity in LLM political behavior.

A framework for dynamic skill-tool evolution in Vision-Language Agents.