Pinned Loading

1. alphazero_llm_trainer alphazero_llm_trainer Public

   AlphaZero-style RL training for LLMs using MCTS on mathematical reasoning tasks (GSM8K). Student model explores reasoning paths guided by teacher ensembles and reward signals.

   Python

2. HyperKuvid-Labs/FrugalSOT HyperKuvid-Labs/FrugalSOT Public

   An adaptive model selection system for efficient on-device NLP inference, enhancing speed, privacy, and resource use on edge devices.

   TypeScript 1

3. HyperKuvid-Labs/AlphaDesign HyperKuvid-Labs/AlphaDesign Public

   Hybrid AI framework combining reinforcement learning and genetic algorithms to optimize Formula 1 front wing aerodynamic designs. Features neural network-guided optimization, CFD analysis, structur…

   Python 1 1

4. HyperKuvid-Labs/energy_throttling_llms HyperKuvid-Labs/energy_throttling_llms Public

   Energy-aware DDPG RL framework that dynamically optimizes LLM speculative decoding parameters based on real-time hardware metrics (CPU/GPU temps, battery). Maintains 95-98% energy utilization to ma…

   Python

5. HyperKuvid-Labs/Gideon HyperKuvid-Labs/Gideon Public

   Emotion-aware LLM chat interface with Ollama, FastAPI, and React, featuring real-time image generation and project automation via Alpha<Stack> agent. Accelerates full-stack and blockchain dev by 60…

   Python

6. HyperKuvid-Labs/elastic_continual_learning HyperKuvid-Labs/elastic_continual_learning Public

   This idea proposes an adaptive optimization framework designed to mitigate catastrophic forgetting in neural network training by dynamically selecting and applying state-of-the-art continual learni…

   Python