https://w.ryanyang.kr/index.php?action=history&feed=atom&title=VLA 2026-04-13T18:02:59Z 이 문서의 편집 역사 MediaWiki 1.37.1 https://w.ryanyang.kr/index.php?title=VLA&diff=3941&oldid=prev 2026-02-15T11:54:44Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="ko"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← 이전 판</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2026년 2월 15일 (일) 20:54 판</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l5">5번째 줄:</td> <td colspan="2" class="diff-lineno">5번째 줄:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br/></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>&#039;&#039;&#039;VLA 모델(Vision-Language-Action Model)&#039;&#039;&#039;은 텍스트, 비디오, 시연(Demonstration)등의 인풋을 받아 액션을 생성하는 로봇 파운데이션 모델들을 일컫는다. 즉, 인공지능 로봇에 들어가는 일종의 생성형 인공지능이다. (출처: https://namu.wiki/w/VLA)</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>&#039;&#039;&#039;VLA 모델(Vision-Language-Action Model)&#039;&#039;&#039;은 텍스트, 비디오, 시연(Demonstration)등의 인풋을 받아 액션을 생성하는 로봇 파운데이션 모델들을 일컫는다. 즉, 인공지능 로봇에 들어가는 일종의 생성형 인공지능이다. (출처: https://namu.wiki/w/VLA)</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"></ins></div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">VLA는 [[VLM]] 을 통해 통합된 정보를 기반으로 로봇이 구체적인 행동을 계획하고 실행하도록 한다. (출처: 이코노미스트) </ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[분류:2026]]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[분류:2026]]</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[분류:AI용어]]</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[[분류:AI용어]]</div></td></tr> </table>

Ryanyang https://w.ryanyang.kr/index.php?title=VLA&diff=3940&oldid=prev 2026-02-15T11:53:41Z

<p>새 문서: Vision Language Action Model. In robot learning, a &#039;&#039;&#039;vision-language-action model (VLA)&#039;&#039;&#039; is a class of multimodal foundation models that integrates vision, language and actions. Given an input image (or video) of the robot&#039;s surroundings and a text instruction, a VLA directly outputs low-level robot actions that can be executed to accomplish the requested task. (Source: https://en.wikipedia.org/wiki/Vision-language-action_model) 파일:General architecture of a vision-lang...</p> <p><b>새 문서</b></p><div>Vision Language Action Model. In robot learning, a &#039;&#039;&#039;vision-language-action model (VLA)&#039;&#039;&#039; is a class of multimodal foundation models that integrates vision, language and actions. Given an input image (or video) of the robot&#039;s surroundings and a text instruction, a VLA directly outputs low-level robot actions that can be executed to accomplish the requested task. (Source: https://en.wikipedia.org/wiki/Vision-language-action_model)<br /> <br /> [[파일:General architecture of a vision-language-action model.png|대체글=It&#039;s a general architecture of a vision-language-action model.|가운데|프레임없음|800x800픽셀|It&#039;s a general architecture of a vision-language-action model.]]<br /> <br /> <br /> &#039;&#039;&#039;VLA 모델(Vision-Language-Action Model)&#039;&#039;&#039;은 텍스트, 비디오, 시연(Demonstration)등의 인풋을 받아 액션을 생성하는 로봇 파운데이션 모델들을 일컫는다. 즉, 인공지능 로봇에 들어가는 일종의 생성형 인공지능이다. (출처: https://namu.wiki/w/VLA)<br /> [[분류:2026]]<br /> [[분류:AI용어]]<br /> [[분류:인공지능]]<br /> [[분류:VLA]]<br /> [[분류:AI]]</div>

Ryanyang