research-framework

Methods, workflows, and checks for AI-assisted research reports. 研究工具箱：研究方法、工作流程与检查工具。

Sentiment Analysis Framework for Researcher with Pytorch

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

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

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

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

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.

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

Universal thermodynamic framework for predicting viability and collapse across couples, organizations, consciousness, therapy, leadership, and AI systems

Cost-aware quantitative research and execution-simulation framework. Paper-only by construction.

Agentic, visualization-first ML/Math research framework for actuaries & data scientists — a reconnaissance aircraft for research

Contract and claim-boundary tooling for empirical AI-system experiments. Turns retained evidence into falsifiable, condition-specific decisions.

Multi-agent civilization simulation framework — emergent social behavior, governance systems, economic modeling, cultural evolution, and statistical emergence detection for cognitive agent populations.

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.

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

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

A research-grade AI-assisted market observation and evidence evaluation framework built through human-AI collaboration.

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.

An institutional-grade, event-driven backtesting project that systematically tests an objective (Donchian / turtle-style) breakout trend strategy on gold (XAUUSD), and rigorously evaluates its risk and validity with Monte-Carlo simulation, controlled exit/filter experiments, and walk-forward analysis — honestly enough to falsify it rather than flat

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.