This is your work, valued
Specialized in Agentic RL & LLM Fine-tuning | AI Engineer @Huawei | Ph.D. in Computer Science from USTC
LVLM-Hallucinations-Survey. This is the first released survey paper on hallucinations of large vision-language models (LVLMs). To keep track of this field and continuously update our survey, we maintain this repository of relevant references.
llm_chat. TypeScript
minimal-agent-harness. Readable educational LLM agent harness for studying runtime control flow: structured events, streaming tools, approval gates, hooks, sessions, and context compaction.