Plug-and-play spatial pruning framework for efficient 3D Visual Grounding.

CUDA-accelerated differentiable 2D Gaussian renderer for video prediction.

Attention Dynamics Alignment with Preference Tuning for reducing MLLM hallucinations.

Code for a framework that uses therapeutic judges and multi-agent systems for human-aligned mental health support.

A framework for zero-shot pseudo-label pruning to reduce hallucinations in foundation models.

Depth-wise gradient augmentation for improved optimization and generalization in DNNs.

A browser plug-in for secure, on-device audio deepfake detection.

Benchmark for evaluating security of agentic computer systems and AI agents.

A self-evolving multi-agent system for automated generation and execution of biological protocols.

Reflection-Augmented Policy Optimization framework for improving tool-using agent correction and robustness.

A unified benchmark suite of realistic agentic healthcare environments for evaluating AI agents.

A pipeline for generating autonomous driving test scenarios from real-world crash records.

A controlled student-teacher evaluation framework to analyze feedback-based agent improvement.

An open standard for integrating AI models with data sources and tools.

A framework for mitigating reward hacking in reinforcement learning agents.

A tool for transforming and moving code between repositories.

Framework for human-to-robot transfer via constraint-aware compositional planning.

An agent-focused evaluation framework for sovereign AI in Southeast Asian languages.

Implementation of DBCC for structural and semantic compression of database schemas for Text-to-SQL.

A training framework for adaptive memory management in software engineering agents.