liqiang
b119135836
Build latest book artifacts / build (push) Canceled after 0s
dependency resolution / resolve (3.11) (push) Canceled after 0s
dependency resolution / resolve (3.13) (push) Canceled after 0s
deploy-pages / build (push) Canceled after 0s
deploy-pages / deploy (push) Canceled after 0s
i18n consistency check / check (push) Canceled after 0s
provider adoption tests / test (chapter2/context-compression) (push) Canceled after 0s
provider adoption tests / test (chapter2/prompt-injection) (push) Canceled after 0s
provider adoption tests / test (chapter2/system-hint) (push) Canceled after 0s
provider adoption tests / test (chapter3/log-sanitization) (push) Canceled after 0s
web-search-agent tests / test (push) Canceled after 0s
web-search-agent tests / agentbook (push) Canceled after 0s
69 lines
13 KiB
XML
69 lines
13 KiB
XML
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 40 940 480" width="940" height="480" style="background:#ffffff">
|
||
<defs><marker id="ah" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-compact" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto" markerUnits="userSpaceOnUse"><polygon points="0 0, 12 4, 0 8" fill="#333333"/></marker><marker id="ah-light" markerWidth="12" markerHeight="8" refX="12" refY="4" orient="auto"><polygon points="0 0, 12 4, 0 8" fill="#999999"/></marker></defs>
|
||
|
||
<rect x="20" y="65" width="220" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
||
<text x="130" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="18.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Observación multimodal</text>
|
||
<rect x="35" y="105" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="130" y="120" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Cámara de cabeza</text>
|
||
<text x="130" y="138" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
|
||
<rect x="35" y="160" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="130" y="175" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Cámara de la muñeca izquierda</text>
|
||
<text x="130" y="193" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
|
||
<rect x="35" y="215" width="190" height="42" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="130" y="230" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Cámara de muñeca derecha</text>
|
||
<text x="130" y="248" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">224×224 RGB</text>
|
||
<rect x="35" y="275" width="190" height="30" rx="4" fill="#f5f5f5" stroke="#999999" stroke-width="2"/>
|
||
<text x="45" y="290" font-family="'Courier New', Courier, monospace" font-size="6.5" fill="#333333" text-anchor="start" dominant-baseline="central">Vector de estado articular de 14 dimensiones</text>
|
||
<rect x="280" y="65" width="310" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
||
<text x="435" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="15.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Modelo de Visión-Lenguaje-Acción (VLA)</text>
|
||
<rect x="295" y="105" width="280" height="50" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
||
<text x="450" y="125" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Codificador de visión</text>
|
||
<text x="450" y="145" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">SigLIP → tokens visuales</text>
|
||
<line x1="435" y1="157" x2="435" y2="168" stroke="#333333" stroke-width="2" marker-end="url(#ah-compact)"/>
|
||
<rect x="295" y="170" width="280" height="50" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="450" y="190" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Modelo de lenguaje</text>
|
||
<text x="450" y="210" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Backbone Llama 2 7B</text>
|
||
<line x1="435" y1="222" x2="435" y2="233" stroke="#333333" stroke-width="2" marker-end="url(#ah-compact)"/>
|
||
<rect x="295" y="235" width="280" height="78" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
||
<text x="435" y="252" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Decodificador de acciones</text>
|
||
<text x="435" y="272" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">→ Vector de control continuo de 14 dimensiones</text>
|
||
<text x="435" y="298" font-family="'Courier New', Courier, monospace" font-size="6.5" fill="#333333" text-anchor="middle" dominant-baseline="central">Agrupamiento de acciones: generar 25 acciones consecutivas a la vez</text>
|
||
<line x1="240" y1="132" x2="278" y2="132" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<line x1="240" y1="257" x2="278" y2="257" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<rect x="300" y="345" width="260" height="32" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="430" y="361" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Instrucción: "Pon la lata en la olla"</text>
|
||
<line x1="430" y1="345" x2="430" y2="315" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<rect x="690" y="65" width="230" height="250" rx="6" fill="#ffffff" stroke="#333333" stroke-width="2" stroke-dasharray="8,4"/>
|
||
<text x="805" y="88" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Motor de física SAPIEN</text>
|
||
<rect x="705" y="105" width="200" height="55" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="805" y="125" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Robot de dos brazos</text>
|
||
<text x="805" y="145" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">7 DOF cada uno = acción de 14 dimensiones</text>
|
||
<rect x="705" y="175" width="200" height="55" rx="6" fill="#d0d0d0" stroke="#333333" stroke-width="2"/>
|
||
<text x="805" y="195" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="15" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Aleatorización del entorno</text>
|
||
<text x="805" y="215" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Posición 60cm / orientación ±22.5°</text>
|
||
<rect x="705" y="245" width="200" height="55" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="805" y="265" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="9" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Detección de colisiones + simulación física</text>
|
||
<text x="805" y="285" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="10.5" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Cuerpo rígido / cuerpo blando / fricción</text>
|
||
<line x1="590" y1="220" x2="688" y2="220" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<text x="640" y="210.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Acción</text>
|
||
<line x1="690" y1="130" x2="592" y2="130" stroke="#333333" stroke-width="2" marker-end="url(#ah)"/>
|
||
<text x="640" y="120.0" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#666666" text-anchor="middle">Observación</text>
|
||
<line x1="20" y1="385" x2="920" y2="385" stroke="#999999" stroke-width="2" stroke-dasharray="8,4"/>
|
||
<text x="440.0" y="408" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="20" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Métricas de evaluación</text>
|
||
<rect x="60" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="150" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Tasa de éxito</text>
|
||
<text x="150" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Lata dentro de la olla</text>
|
||
<text x="150" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">y no caído</text>
|
||
<rect x="260" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="350" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Tiempo de finalización</text>
|
||
<text x="350" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">25 pasos × 25 acciones</text>
|
||
<text x="350" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">= 625 pasos de control</text>
|
||
<rect x="460" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="550" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="12.5" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Capacidad de generalización</text>
|
||
<text x="550" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="13" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Posición/orientación cruzada</text>
|
||
<text x="550" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">/Variante de apariencia</text>
|
||
<rect x="660" y="425" width="180" height="75" rx="6" fill="#f0f0f0" stroke="#333333" stroke-width="2"/>
|
||
<text x="750" y="445" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="16" fill="#333333" text-anchor="middle" dominant-baseline="central" font-weight="bold">Sim-to-Real</text>
|
||
<text x="750" y="465" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">Aleatorización del dominio</text>
|
||
<text x="750" y="483" font-family="Arial, 'Helvetica Neue', Helvetica, 'PingFang SC', 'Microsoft YaHei', sans-serif" font-size="14" fill="#666666" text-anchor="middle" dominant-baseline="central" font-weight="normal">→ Migración real</text>
|
||
</svg> |