Buy Crypto
Pay with
USD
USD
Buy & Sell
Hot
Supports Visa, Mastercard, SEPA & more
P2P
0 Fees
Flexible trading, zero fees
Gate Card
Use your crypto for payments worldwide
Markets
Trade
Basic
Advanced
Futures
Futures
Access hundreds of perpetual contracts
CFD
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Earn
Launch
CandyDrop
tag
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Pre-IPOs
Unlock full access to global stock IPOs
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
Investment
Square
Square
Post, share, and explore crypto trends
Live
moments live
Live crypto market analysis
Chat
Chat with crypto traders
News
What is happening in crypto
flower_head
More
Promotions
AI
Others
TradFi
Gate Card
Rewards
Square
Latest
Hot
News
Profile

RAEv2 Open Source: Convergence Speed Increased by 10 Times, 80 Training Epochs Surpass the Previous 800 Epoch Record

CoinNetwork
robot
Abstract generation in progress
CryptoWorld News: The RAEv2 open-source project was jointly launched by institutions including Adobe Research, the Australian National University (ANU), and the Xie Saining team at New York University (NYU), among others. It improves convergence speed by 10 times, surpassing the previous record of 800 rounds with just 80 training rounds. As an image reconstruction scheme based on diffusion models to replace traditional variational autoencoders (VAE), the new version addresses pain points such as poor reconstruction quality in the first generation, an inability to use standard classifier-free guidance (CFG), and extremely slow convergence. On ImageNet, it achieves a global FID (GFID) score of 1.06 with only 80 training rounds. In its architectural design, the research team delivered three core optimizations: adopting a multi-layer representation scheme that directly sums the outputs of the last K layers of the encoder, preserving the structure of the underlying subspace. The new architecture also clarifies the complementary mechanism between the representation autoencoder and representation alignment (REPA), enabling stronger performance on generative tasks. Tests show that to reach a GFID below 2, the first-generation model requires 177 rounds, while the new architecture needs only 35 rounds.
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • 10
  • Repost
  • Share
Comment
Add a comment
Add a comment
PaperSculptureSquidward
· 5h ago
How do REPA and multi-layer representations work together? Wait for the paper to analyze in detail.
View OriginalReply0
GateUser-b6d80ba0
· 22h ago
Adding the last K layers of the encoder together has a bit of a ResNet skip connection feel, but applied in the latent space
View OriginalReply0
NeonVortexInTheSmog
· 22h ago
Diffusion reconstruction + CFG compatibility, clearing technical debt in one go
View OriginalReply0
CyberBridgeDeepPerspective
· 22h ago
Round 35 GFID<2, this efficiency makes the alchemist ecstatic
View OriginalReply0
RevokingPermissionsOnARainy
· 22h ago
Someone finally took the issue of VAE reconstruction blurriness seriously, tearing up.
View OriginalReply0
HoldingPositionsIsLikeTending
· 22h ago
Adobe + ANU + NYU three partners join forces, maximizing resources
View OriginalReply0
CandleAfterTheRain
· 22h ago
The multi-layer representation preserves the underlying structure; this design is very detailed and not just a simple stacking depth.
View OriginalReply0
BitByBitBenny
· 22h ago
GFID 1.06 only 80 rounds, the previous generation 177 rounds was cut off halfway, convergence speed skyrocketing
View OriginalReply0
GateUser-0f8d377b
· 22h ago
Xie Saining's team has connected reconstruction and generation this time; the REPA complementary mechanism has some substance.
View OriginalReply0
Salt-BakedSentimentChart
· 22h ago
Using diffusion models as VAE is indeed a wild idea.
View OriginalReply0
View More

  • Pinned

Sitemap