Kuiz berkaitan panduan · Keras Tahap
Mengapa Video AI Mendapat Kuiz Fizik Salah
Menguji sebab model video mempelajari rupa dan bukannya fizik, cara memori terhad memecahkan keabadian objek, dan sebab pengiraan menjadikan klip pendek.
soalan 1 daripada 8
Apakah yang diutamakan oleh objektif latihan penjana video biasa?
Pratonton setiap soalan8 soalan
Jawapan dan penjelasan muncul semasa anda mengambil kuiz.
- Apakah yang diutamakan oleh objektif latihan penjana video biasa?
- Obeying conservation of momentum
- Producing output that resembles real video
- Matching a built-in physics engine
- Minimizing the number of frames
- Mengapakah peristiwa yang jarang berlaku seperti kaca pecah terutamanya sukar untuk model video?
- They are forbidden in training data by law
- They appear less often in training data and involve complex dynamics
- They require audio to generate
- Models cannot render transparent objects at all
- Panduan ini menerangkan kegagalan kekal objek terutamanya sebagai jenis masalah?
- A color-grading problem
- A memory problem involving limited context
- A frame-rate problem
- A problem with the text prompt's language
- Apakah sebab utama klip video AI selalunya hanya beberapa saat sahaja?
- Copyright rules limit clip length
- Attention cost rises steeply as the number of spacetime tokens grows
- Displays cannot play longer AI clips
- Longer clips require a different file format
- Pernyataan yang manakah menggambarkan salah tanggapan tentang penjana video?
- They may learn some implicit physical regularities
- They contain a built-in physics engine
- They can make rare interactions look wrong
- Their clips are often extended by chaining generations
- What did benchmarks such as Physics-IQ suggest?
- Visual realism reliably indicates physical understanding
- Visually realistic output does not mean physical understanding
- All current models pass basic physics tests
- Physics cannot be tested in video
- Why can a small ball's wrong trajectory go uncorrected during training?
- It takes up few tokens, so the error adds little to the reconstruction loss
- Balls are removed from training data
- The model is never shown moving objects
- Trajectories are handled by a separate audio model
- How does Meta's V-JEPA approach differ from pixel-level video generation?
- It predicts in an abstract representation space instead of pixels
- It uses only text with no video
- It relies entirely on a game engine to render output
- It generates audio instead of video