Offline Federated RL for O-RAN slice resource management on Colosseum traces

Sentiment Analysis Framework for Researcher with Pytorch

A research framework for implementing and evaluating poisoning attacks on Retrieval-Augmented Generation (RAG) systems, enabling the study of their security vulnerabilities.

DSPy framework for detecting and preventing safety override cascades in LLM systems. Research-grade implementation for studying when completion urgency overrides safety constraints.

Cross-Axis Analysis Framework | 横纵分析法 - 通过纵向时间深度 + 横向竞争格局的交汇分析，快速建立系统性认知

Python research framework for UAV motion planning — YAML-driven ablations with Wilson 95% CIs by default.

Computational framework for Constraint-Driven Stability with scientific toy models and applied AI decision surfaces.

A lightweight Python library for reproducible computational experiments with an ultra-simple, smart API. From idea to insight in under 5 minutes, with zero configuration.

SentinelGuard is a modular anti-cheat research framework focused on detecting integrity violations, memory tampering, and abnormal behavior in FPS-style games. The project emphasizes defensive detection concepts and learning, inspired by modern kernel-assisted anti-cheat architectures.

Truth-first ontological and epistemological framework. Original articles preserved without modification. Focused on reality-aligned AI, knowledge, and responsibility.

Elite-tier research framework for robust Multimodal RAG under stochastic and adversarial noise. Implements Epistemic Gating (ENG), Symmetric Information Bottleneck (SIB) filtering, and Meta-Cognitive Loops to mitigate cascading hallucinations in vision-language retrieval.

Open scientific research framework for EVRT (Emergent Vacuum Response Theory), residual-force metrology, uncertainty-aware diagnostics, simulation-guided analysis, and artifact-aware experimentation in coherent nonequilibrium electromagnetic systems.

🌐 Detect and prevent safety overrides in LLM systems with this DSPy-based framework, ensuring actions align with safety constraints.

AI-Debate is a LangGraph-powered framework designed to orchestrate structured, hierarchical debates between multiple AI agents using OpenAI and Anthropic models. The system guides these agents through iterative presentation and consensus phases to reach unified agreements, providing comprehensive JSON exports for research and behavioral analysis.

Experimental alignment-governance framework for bounded LLM experimentation with attention-direction telemetry and trust-aware evaluation.

Digital Life Primordium（数字生命原基）— 超越工具视角，走向可进化的数字灵魂。概念预研级开源项目，探索下一代智能体的根本性架构。

AURORA is a lightweight research-oriented AI engineering framework for multi-task NLP training, evaluation, and FastAPI deployment.

Mathematical and computational framework for modeling protein free-energy landscapes and thermodynamic state transitions.

Reproducible framework for auditing Global Health Estimates (GHE) using CRVS data, including bias signals, Artificial Smoothness Index (ASI), and a volatility-based reliability lens.

Modular PyTorch lab for running configurable deep-learning experiments, with ready-to-use data loaders, training pipelines, and metric tracking for both vision and NLP benchmarks.