AI Research 技术调研

标签: perceiver-resampler

此标签下有3条笔记。

  • 2026年7月16日

    Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

    • gr-1
    • video-generative-pretraining
    • gpt-style-transformer
    • ego4d
    • calvin
    • future-frame-prediction
    • action-token
    • mae-vit
    • clip-text-encoder
    • perceiver-resampler
  • 2026年7月16日

    Vid2Robot: End-to-end Video-conditioned Policy Learning with Cross-Attention Transformers

    • video-conditioned-policy
    • cross-attention-transformer
    • one-shot-imitation
    • human-video-imitation
    • perceiver-resampler
    • contrastive-loss
    • temporal-cycle-consistency
    • cross-object-motion-transfer
    • action-chunking
  • 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

  • GitHub