Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
[Journal club] Scalable Diffusion Models with T...
Search
Semantic Machine Intelligence Lab., Keio Univ.
PRO
July 22, 2024
Technology
0
110
[Journal club] Scalable Diffusion Models with Transformers
Semantic Machine Intelligence Lab., Keio Univ.
PRO
July 22, 2024
Tweet
Share
More Decks by Semantic Machine Intelligence Lab., Keio Univ.
See All by Semantic Machine Intelligence Lab., Keio Univ.
Machine Intelligence for Vision, Language, and Actions
keio_smilab
PRO
0
620
[Journal club] V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
keio_smilab
PRO
0
140
[Journal club] Model Alignment as Prospect Theoretic Optimization
keio_smilab
PRO
0
160
[Journal club] DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
keio_smilab
PRO
0
84
[Journal club] LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
keio_smilab
PRO
2
110
Will multimodal language processing change the world?
keio_smilab
PRO
4
630
[Journal club] MOKA: Open-Vocabulary Robotic Manipulation through Mark-Based Visual Prompting
keio_smilab
PRO
0
210
[Journal club] Seeing the Unseen: Visual Common Sense for Semantic Placement
keio_smilab
PRO
0
190
[Journal club] Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot
keio_smilab
PRO
0
200
Other Decks in Technology
See All in Technology
CDK Toolkit Libraryにおけるテストの考え方
smt7174
1
360
[SRE NEXT] ARR150億円_エンジニア140名_27チーム_17プロダクトから始めるSLO.pdf
satos
3
1.7k
CDK Vibe Coding Fes
tomoki10
1
450
いつの間にか入れ替わってる!?新しいAWS Security Hubとは?
cmusudakeisuke
0
150
AWS CDK 開発を成功に導くトラブルシューティングガイド
wandora58
3
140
OpenTelemetryセマンティック規約の恩恵とMackerel APMにおける活用例 / SRE NEXT 2025
mackerelio
2
1.3k
cdk initで生成されるあのファイル達は何なのか/cdk-init-generated-files
tomoki10
1
430
インフラ寄りSREの生存戦略
sansantech
PRO
8
3.3k
AIエージェントが書くのなら直接CloudFormationを書かせればいいじゃないですか何故AWS CDKを使う必要があるのさ
watany
14
5.8k
助けて! XからWaylandに移行しないと新しいGNOMEが使えなくなっちゃう 2025-07-12
nobutomurata
2
130
Zero Data Loss Autonomous Recovery Service サービス概要
oracle4engineer
PRO
2
7.8k
スタートアップに選択肢を 〜生成AIを活用したセカンダリー事業への挑戦〜
nstock
0
270
Featured
See All Featured
CSS Pre-Processors: Stylus, Less & Sass
bermonpainter
357
30k
Let's Do A Bunch of Simple Stuff to Make Websites Faster
chriscoyier
507
140k
Statistics for Hackers
jakevdp
799
220k
The Web Performance Landscape in 2024 [PerfNow 2024]
tammyeverts
8
700
Fight the Zombie Pattern Library - RWD Summit 2016
marcelosomers
233
17k
Bootstrapping a Software Product
garrettdimon
PRO
307
110k
Writing Fast Ruby
sferik
628
62k
The Pragmatic Product Professional
lauravandoore
35
6.7k
Testing 201, or: Great Expectations
jmmastey
43
7.6k
Building an army of robots
kneath
306
45k
Being A Developer After 40
akosma
90
590k
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
irinanazarova
8
830
Transcript
4DBMBCMF%JGGVTJPO.PEFMTXJUI 5SBOTGPSNFST ܚጯٛक़େֶ ਿӜ໌ݚڀࣨ#ീౡେ 8JMMJBN1FFCMFT 4BJOJOH9JF 6$#FSLFMFZ /FX:PSL6OJWFSTJUZ *$$7 8JMMJBN1FFCMFT
4BJOJOH9JFl4DBMBCMF%JGGVTJPO.PEFMTXJUI5SBOTGPSNFSTzJO*$$7 QQ
എܠɿ֦ࢄϞσϧʹΑΔಈը૾ੜ FH 4PSB ͷൃల IUUQTXXXZPVUVCFDPNXBUDI W),Z%"1/@
ؔ࿈ݚڀɿ֦ࢄϞσϧͷόοΫϘʔϯͱͯ͠6/FU͕ଟ༻ • 6/FUͷ.VMUJTDBMFTLJQDPOOFDUJPOTˠ ෆཁͳܭࢉࢿݯͷ༻ 手法 概要 DALL-E 2 [Ramesh+,
22] CLIPを用いてテキストと画像のAlignmentを行う Stable Diffusion [Rombach+, CVPR22] 潜在拡散モデル 6/FU<3POOFCFSHFS .*$$"*> 4UBCMF%JGGVTJPO<3PNCBDI $713>
ఏҊख๏ɿ%JGGVTJPO5SBOTGPSNFS %J5 • જࡏ֦ࢄϞσϧ -%. <3PNCBDI $713>Λϕʔεʹߏங • 7JTJPO5SBOTGPSNFS 7J5
<%PTPWJUTLJZ *$-3>ػߏΛಋೖ • $POEJUJPOJOHʹΑΔ݅ใͷೖྗ
ఏҊख๏ ɿજࡏ֦ࢄϞσϧͱֶͯ͠शͤ͞Δ • ߴ࣍ݩͷըૉۭؒͰ֦ࢄϞσϧΛֶश ͤ͞Δ͜ͱܭࢉྔతʹࠔ • -%.ͱֶͯ͠शͤ͞Δ͜ͱͰ ܭࢉྔΛݮ
• ըૉۭؒͷ֦ࢄϞσϧͰ͋Δ "%.<%IBSJXBM /FVS*14> ͷͷͷ(GMPQTͰֶशՄೳ
ఏҊख๏ ɿೖྗϊΠζΛQBUDIʹղ • "VUPFODPEFS͔ΒಘΒΕͨ /PJTFE-BUFOU YY Λ 7J5ͱಉ༷ʹE࣍ݩͷτʔΫϯ5ʹม •
1BUDIαΠζQΛʹ͢Δͱ5ഒ ʹͳΓUSBOTGPSNFSͷ (GMPQTগͳ͘ͱഒҎ্
ఏҊख๏ ɿ͖݅ೖྗ $POEJUJPOJOH ͷॲཧ • ͖֦݅ࢄϞσϧͰϊΠζΛؚΉը૾ͱͱʹՃใ͕Ճ͑ΒΕΔ FH UJNFTUFQɼΫϥεϥϕϧɼࣗવݴޠ FUD
• ຊݚڀͰ͜ΕΒͷ͖݅ೖྗΛॲཧ͢ΔͨΊʹҎԼͷͭͷҟͳΔઃܭΛఏҊ • *ODPOUFYUDPOEJUJPOJOH • $SPTT"UUFOUJPOCMPDL • "EBQUJWFMBZFSOPSN BEB-/ CMPDL • BEB-/;FSPCMPDL
ఏҊख๏ ɿBEB-/;FSPCMPDL • 7J5ͷTFMGBUUFOUJPOCMPDLʹରͯ͠"EB-/ػߏΛಋೖ • "EB-/ͷεέʔϧ ͓Αͼ ࠩଓͷલͷεέʔϧ
Λύϥϝʔλͱͯ͠Ճ ˠ݅ใΛը૾ʹΑΓڧ͘ө • "EB-/;FSPCMPDLͰͦΕΒΛθϩʹॳظԽ ˠֶशͷॳظஈ֊߃ؔʹ͍ۙಇ͖ ˠ ֶशͷ҆ఆԽ
࣮ݧઃఆ • σʔληοτ • $MBTT$POEJUJPOBM*NBHF/FUY Y<%FOH $713> • ΞʔΩςΫνϟ
• 7J5ͱಉ༷ʹͭͷϞσϧͷେ͖͞ 4 # - 9- Λ༻ҙ • QBUDITJ[FQ • %%1.TBNQMJOHTUFQT • ධՁई • '*% T'*% *4 1SFDJTJPO 3FDBMM • (GMPQT • ֶश • 516WQPE #BUDITJ[F
ఆྔత݁Ռɿ6/FUϕʔεͷख๏Λ্ճͬͨ
ఆੑత݁Ռ • 1BUDITJ[FΛখ͘͞ɼϞσϧΛେ͖͘͢ΔͱΑΓࣗવͳը૾͕ग़ྗ͞ΕΔ ˠ%J5Ͱ(GMPQT͕େ͖͍΄Ͳग़ྗը૾ͷ্࣭͕͕Δ
ࢼ͓ΑͼΤϥʔੳ ఆੑత݁Ռ ɿࣦഊྫ • ಛఆͷMBCFMʹରͯ͠ෆࣗવͳը૾͕ੜ͞ΕΔ • ྫɿJOQVUMBCFM UPZQPPEMF %%1.TBNQMJOHTUFQ
• ϥϕϧʹΑͬͯTUFQͰੜը૾͕ෆ҆ఆˠ ਪ࣌ͷTUFQΛಈతʹมߋ
ॴײ • 4USFOHUI • ֦ࢄϞσϧʹUSBOTGPSNFSΛಋೖ • ܭࢉࢿݯͱग़ྗը૾ͷ࣭ʹ͍ͭͯͷߟ • 8FBLOFTT
• ͕ࣜগͳ͔ͬͨ • Τϥʔੳ͕ͳ͍
·ͱΊ • എܠ • ֦ࢄϞσϧʹΑΔಈը૾ੜ FH 4PSB ͷൃల • ֦ࢄϞσϧʹ͓͚ΔUSBOTGPSNFSͷར༻͕গͳ͍
• ఏҊख๏ • USBOTGPSNFSϕʔεͷ֦ࢄϞσϧͰ͋Δ%JGGVTJPO5SBOTGPSNFS %J5 ΛఏҊ • ݁Ռ • %J5εέʔϥϏϦςΟ͕ߴ͘ɼ(GMPQT͕େ͖͍΄Ͳ'*%͕Լ ˠ ܭࢉࢿݯͱग़ྗը૾ͷ࣭ʹڧ͍૬ؔؔ • %J59-Ϟσϧ͕ɼ$MBTT$POEJUJPOBM*NBHF/FUʹ͓͍ͯ ैདྷͷ6/FUϕʔεͷ֦ࢄϞσϧΛ্ճͬͨ
"QQFOEJYɿ%FOPJTJOH%JGGVTJPO1SPCBCJMJTUJD.PEFM %%1. ֶश
"QQFOEJYɿ$MBTTJGJFSGSFFHVJEBODF • ͖֦݅ࢄϞσϧͰΫϥεϥϕϧΛϥϯμϜʹυϩοϓ ˠ αϯϓϦϯάͷਫ਼Λ্ • #BZFTͷఆཧΑΓ • ֦ࢄϞσϧͷग़ྗΛείΞͱͯ͠ղऍ͢Δͱਪఆ͢ΔϊΠζҎԼͷΑ͏ʹͳΔ
TɿΨΠμϯεεέʔϧ
"QQFOEJYɿ*ODPOUFYUDPOEJUJPOJOH • $POEJUJPOJOHͰ݅ͱͯ͠ೖྗ͞ΕͨτʔΫϯΛ ը૾τʔΫϯͷઌ಄ʹՃ • ͜ΕΒͷτʔΫϯը૾τʔΫϯͱಉ༷ʹѻΘΕɺ 7J5ʣʹ͓͚ΔDMTτʔΫϯͱࣅׂͨΛ࣋ͭ
"QQFOEJYɿ$SPTT"UUFOUJPOCMPDL • 4FMG"UUFOUJPOϒϩοΫͷޙʹ$SPTT"UUFOUJPOΛ Ճͨ͠ઃܭ • <7BTXBOJ /*14>-%.ͱྨࣅͨ͠ΞʔΩςΫνϟ
"QQFOEJYɿ%J5CMPDLEFTJHO • %J59-Ϟσϧʹ͓͍ͯBEB-/;FSPΛ༻͍ͨ ߹͕࠷গͳ͍ܭࢉࢿݯͰ࠷ྑ͍ '*%,είΞΛୡ
"QQFOEJYɿ7JTJPO5SBOTGPSNFS <%PTPWJUTLJZ *$-3>
"QQFOEJYɿ*ODFQUJPO4DPSF *4 • *NBHF/FUͰࣄલֶशࡁΈͷ*ODFQUJPOOFUXPSLΛ༻͍ͨධՁࢦඪ • *ODFQUJPOOFUXPSL͕ࣝผ͘͢͠ɼࣝผ͞ΕΔϥϕϧͷଟ༷ੑ͕͋Δ΄Ͳ େ͖͘ͳΔࢦඪ <4[FHFEZ $713>
"QQFOEJYɿ'SFDIFU*ODFQUJPO%JTUBODF '*% • *NBHF/FUͰࣄલֶशࡁΈͷ*ODFQUJPOOFUXPSLΛ༻͍ͨධՁࢦඪ • ੜ͞Εͨը૾ͷಛ͕(5ը૾ͷಛͱͲͷఔ ࣅ͍ͯΔ͔ΛධՁ͢Δࢦඪ • '*%͕খ͍͞΄Ͳੜ͞Εͨը૾ͷ࣭͕(5ը૾ʹ͍ۙͱߟ͑ΒΕΔ
"QQFOEJYɿ1SFDJTJPO3FDBMM • *NBHF/FUͰࣄલֶशࡁΈͷ7((<4JNPOZBO *$-3>Λ༻͍ͯ ಛϕΫτϧू߹ΛಘΔ
"QQFOEJYɿ(GMPQT • 'MPQTɿුಈখԋࢉͷճ • (GMPQT 'MPQT • ը૾ੜλεΫͰΞʔΩςΫνϟͷෳࡶ͞ΛධՁ͢ΔࡍύϥϝʔλΛ༻͍Δͷ ͕Ұൠత
• ੑೳʹେ͖͘Өڹ͢Δը૾ղ૾ΛҰߟྀ͍ͯ͠ͳ͍ • Ϟσϧͷෳࡶ͞Λද͢ࢦඪͱͯ͠ෆेͳ߹͕͋Δ
"QQFOEJYɿఆྔత݁Ռ
"QQFOEJY(GMPQTͱ'*%ͷ૬ؔ • ΑΓଟ͘ͷ(GMPQTΛͭϞσϧ'*%͕͘ͳΔ
"QQFOEJYɿϞσϧαΠζͱύοναΠζͷݕ౼