影片模型是零樣本學習者和推理者

Google Google DeepMind

簡要總結

Veo 3展示了在眾多視覺任務中的零樣本能力,表明影片模型正走在成為視覺基礎模型的道路上——就像大語言模型成為語言基礎模型一樣。

感知

建模

操作

推理

摘要

大語言模型(LLM)的卓越零樣本能力已將自然語言處理從特定任務模型推向統一的通用基礎模型。這種轉變源於簡單的基本要素:在網路規模資料上訓練的大型生成模型。有趣的是,同樣的基本要素也適用於當今的生成式影片模型。影片模型會像大語言模型發展出通用語言理解能力一樣,走向通用視覺理解嗎?

這項研究表明,Veo 3可以零樣本解決大量它未經明確訓練的任務:分割物件、檢測邊緣、編輯圖像、理解物理屬性、識別物件功能、模擬工具使用等等。這些感知、建模和操縱視覺世界的能力,使其能夠進行迷宮求解和對稱性求解等早期形式的視覺推理。Veo 3的新興零樣本能力表明,影片模型正走在成為統一通用視覺基礎模型的道路上。

播客概覽

收聽研究論文的生成摘要。

感知

Edge detection

Segmentation

Keypoint localization

Super-resolution

Blind deblurring

Blind denoising

Low-light enhancement

Conjunctive search

Dalmatian illusion understanding

Shape cue-conflict understanding

Rorschach blot interpretation

建模

Material properties (flammability)

Rigid body transform

Soft body transform

Gravity (earth)

Gravity (moon)

Buoyancy (bottle cap)

Buoyancy (rock)

Visual Jenga

Object packing

Material optics (glass)

Material optics (mirror)

Color mixing (additive)

Color mixing (subtractive)

Categorizing objects

Omniglot (recognition)

Omniglot (generation)

Omniglot (parsing)

Memory of world states

操作

Background removal

Style transfer

Colorization

Inpainting

Outpainting

Text manipulation

Image editing with doodles

Scene composition

Novel view synthesis

3D-aware reposing

Transfiguration

Professional headshot

Dexterous manipulation (jar)

Dexterous manipulation (throw/catch)

Dexterous manipulation (baoding balls)

Affordance recognition

Drawing

Visual instruction

推理

Graph traversal

Tree BFS

Sequence (dots)

Sequence (arrows)

Sequence (circles)

Sequence (squares)

Connecting colors

Shape fitting

Sorting numbers

Tool use

Simple sudoku completion

Water puzzle solving

Maze solving (mouse)

Robot navigation

Rule extrapolation

Analogy (color)

Analogy (resize)

Analogy (reflect)

Analogy (rotate)

Maze (5x5)

Maze (7x7)

Maze (9x9)

Maze (irregular)

Symmetry (shape)

Symmetry (random)