Mohammed Alshehri

RLM-implementation. RVAA: Recursive Vision-Action Agent for Long Video Understanding. Implementation of the RLM paradigm (Zhang, Kraska, Khattab 2025)

Water-Quality-Prediction-machine-learning-python. predicting if the water is safe to consume with given dataset

autoresearch-explorer. RL agent for document exploration via GRPO, inspired by Karpathy's autoresearch. Built on Tinker.

Tumor-Detection-openai-oss. Python

paper_talk. Python

RLM-RAG. Python

trace2evolve-autoresearch. Trace2Evolve: a Karpathy-style AutoResearch loop for customer-support agents

VoiceChat-GPT-OSS. Trying out GPT-OSS

the-exploration-phase. Just having fun with RL meeeeeeh

reward-hacking-detector. Reward-Hacking Detection via RL-Post-Training of LLMs - Detecting reward hacking in RL agents using language models as trajectory auditors

Qwen3-TTS. Qwen3-TTS is an open-source series of TTS models developed by the Qwen team at Alibaba Cloud, supporting stable, expressive, and streaming speech generation, free-form voice design, and vivid voice cloning.