Hugging Face's logo

mzx
/
NEvo

Text-to-Video
Diffusers
NevoPipeline
neuroscience
fmri
brain-decoding
stimulus-synthesis
v-jepa
Model card Files
xet
 Community
NEvo / tests

Commit History

  1. Add image-only pipeline mode

    mzx
    81ab95d

  1. Expose encoder input resolution as score_size (default 224)

    dawidtang
    Verified signature
    a29c99b

  2. Per-stage eval budgets image_max_evals/video_max_evals (200/100)

    dawidtang
    Verified signature
    38c35d7

  3. Split into image_num_generations (50) / video_num_generations (25)

    dawidtang
    Verified signature
    2035209

  4. Replace num_candidates/max_evals with num_generations (population_size + num_generations)

    dawidtang
    Verified signature
    5525fdc

  5. Replace num_rounds with population_size (default 20), matching clean_search

    dawidtang
    Verified signature
    23e4cfe

  6. Align two-stage search with canonical: clean scoring, art_data stage-1, image/video batching

    dawidtang
    Verified signature
    dbe598f

  7. Two-stage pipeline (image search then motion search) with per-stage budgets

    dawidtang
    Verified signature
    05094e8

  1. ROI-enhanced search space + docs; EBA caption

    dawidtang
    Verified signature
    920eeb0

  2. Publish self-contained NEVO stimulus-synthesis pipeline + model card

    dawidtang
    Verified signature
    c5e4258