AI Research 技术调研

标签: instruction-tuning

此标签下有5条笔记。

  • 2026年7月16日

    Pandora: Towards General World Model with Natural Language Actions and Video States

    • world-model
    • autoregressive-diffusion-hybrid
    • natural-language-action-control
    • video-generation
    • llm-video-alignment
    • instruction-tuning
    • cross-domain-action-transfer
    • staged-training
    • chat-univi
    • dynamicrafter
  • 2026年6月25日

    AnyMAL: An Efficient and Scalable Any-Modality Augmented Language Model

    • any-modality
    • multimodal-llm
    • llama-2
    • perceiver-resampler
    • frozen-llm
    • audio
    • video
    • imu
    • instruction-tuning
    • understanding
  • 2026年6月25日

    CM3Leon: Scaling Autoregressive Multi-Modal Models (Pretraining and Instruction Tuning)

    • autoregressive
    • token-based
    • retrieval-augmented
    • text-to-image
    • image-to-text
    • instruction-tuning
    • contrastive-decoding
    • cm3
    • chameleon-lineage
  • 2026年6月25日

    NExT-GPT: Any-to-Any Multimodal LLM

    • any-to-any
    • mm-llm
    • omni
    • diffusion-decoder
    • imagebind
    • vicuna
    • instruction-tuning
    • mosit
    • projection-layer
  • 2026年6月25日

    MetaMorph: Multimodal Understanding and Generation via Instruction Tuning

    • unified
    • mllm
    • instruction-tuning
    • vpit
    • continuous-visual-tokens
    • autoregressive
    • diffusion-autoencoder
    • llama-3

  • GitHub