Gianfranco's Notes
  • GitHub

    Machine Learning/NLP & LLMs

    A Human-Inspired Reading Agent With GistMemory Of Very Long Contexts →
    Action-Driven LLMs →
    Constitutional AI →
    Cost Of Fine-Tuning LLMs →
    Does Fine-Tuning LLMs On New Knowledge Encourage Hallucinations? →
    DPO - Direct Preference Optimization →
    Fixie.AI →
    FrugalGPT →
    GRPO - Group Relative Policy Optimization →
    HuggingGPT →
    Human-In-The-Loop LLM Agents →
    Instruction Tuning For Large Language Models- A Survey →
    KTO - Kahneman-Tversky Optimization →
    LangChain →
    Large Language Models (Llms) →
    LLamaIndex →
    LLM Training And Alignment Evolution →
    LoRA - Low-Rank Adaptation Of LLMs →
    Masked LM Vs Causal LM →
    MemGPT - Towards LLMs As Operating Systems →
    PEFT - Parameter-Efficient Fine-Tuning →
    Quantization →
    ReAct - Synergizing Reasoning And Acting In Language Models →
    Reasoning LLMs →
    RLHF - Reinforcement Learning From Human Feedback →
    RLVF - Reinforcement Learning From Verifiable Feedback →
    RNN →
    Router Ideas →
    SPIN - Self-Play Fine-Tuning →
    Synthetic Data For LLM Training →
    Transformer →
    Unlock LLMs' Potential →
    Adaptive Machine Translation →
    Adaptive Machine Translation With LLMs →
    An Empirical Comparison Of Domain Adaptation Methods For NMT →
    Domain-Specific Text Generation For Machine Translation →
    Fuzzy Matches →
    Tagged Back-Translation →
    Translation Memories →