Open-source JSON Schema editor extended for AI-assisted RDF authoring and semantic interoperability.

A defensive framework that injects dummy playlists to mitigate PII inference attacks.

Project page for a simplified and more stable variant of forward-backward representation learning in RL.

Tool for obtaining better insights and analytics from GitHub repositories.

A public-calibrated, dependency-free, closed-loop benchmark for online truckload bid acceptance.

A zero-shot benchmark and dataset for dense crowd counting in Hajj video footage.

Code for audio sentiment analysis via distillation and cross-modal integration of multilingual transcripts.

A benchmark of 20 computational imaging tasks evaluating the physics-grounded performance of agentic AI.

A benchmark for minimal information requesting and mathematical reasoning.

A parameterized suite of multi-agent gridworld environments to study bystander disempowerment.

Modular framework for evaluating sabotage and control in automated AI R&D.

A low-cost three-stage cascade (retrieval, rerank, reason) for semantic search over KOL profiles.

An agentic tutor for learning prompt engineering in software development through IDE-embedded guidance.

Implementation of the few-medoids coreset selection method for knowledge distillation

A tool for rendering guitar tabs as you type.

A framework for classifying facial phenotypic descriptors aligned with the Human Phenotype Ontology.

Study comparing LLM evaluation robustness across objective and subjective datasets.

A reference monitor for revocable resource-and-effect capabilities for coding agents.

An API and UI-driven RL Gym environment for building and evaluating scalable agentic RL

A federated learning platform for collaborative AI training without data centralization.