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
Stocks
CFD
U.S. stock CFD derivatives
Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
GUSD
Mint GUSD for Treasury RWA yields
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
IPO Access
tag
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
IPO
Rewards
Square
Latest
Hot
News
Profile

Tencent HunYuan releases UniRL: Unified Multimodal Reinforcement Learning Infrastructure

MeNews
robot
Abstract generation in progress
ME AI Message: Tencent Hunyuan has launched UniRL, a reinforcement learning infrastructure that supports unified multimodal models, and has released two new algorithms, DRPO and Flow-DPPO. UniRL covers diffusion/flow-matching models, LLM/VLM, and unified multimodal models (such as Hunyuan-Image 3 and Bagel) through a single post-training loop (generation → scoring → advantage → update → synchronization). Models and algorithms are independent axes, enabling coverage of any combination of model × algorithm. The framework supports pluggable rollout engines (training side/SGLang/vLLM-Omni), FSDP2 sharding, and three deployment modes. Flow-DPPO introduces trust-region policy optimization based on precise divergence for flow/diffusion models; DRPO provides a smooth, advantage-weighted quadratic regularization method for LLM RL. The code has been open-sourced. (Source: AiHot)
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
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments

  • Pinned

Sitemap