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
US Stocks
Access real US stocks and ETFs
HK Stocks
Trade quality Hong Kong-listed stocks
Stock Futures
High leverage, 24/7 trading
Tokenized Stocks
Backed by real stock assets
IPO Access
Unlock full access to global stock IPOs
GUSD
Mint GUSD for Treasury RWA yields
Stocks Activities
Trade Popular Stocks and Unlock Generous Airdrops
Earn
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
IPO Access
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
2026 World Cup
Rewards

Tilde Research Discovers Muon Optimizer Kills 25% of Neurons; Aurora Alternative Achieves 100x Data Efficiency Gain

GateNews
AI Industry News
According to Tilde Research, the Muon optimizer adopted by leading AI models including DeepSeek V4 and Kimi K2.5 has a hidden flaw: it causes over 25% of MLP layer neurons to permanently die during early training. The team designed Aurora, an alternative optimizer, and open-sourced it. A 1.1B parameter model trained with only 100B tokens matched the performance of Qwen3-1.7B trained on 36T tokens across language understanding benchmarks like HellaSwag and Winogrande, demonstrating roughly 100x data efficiency improvement. Aurora adds 6% computational overhead compared to Muon and can serve as a direct replacement.
View Source
Disclaimer: The information on this page may come from third-party sources and is for reference only. It does not represent the views or opinions of Gate and does not constitute any financial, investment, or legal advice. Virtual asset trading involves high risk. Please do not rely solely on the information on this page when making decisions. For details, see the Disclaimer.

Related News

05-10 01:55
TeraWulf Posts $427M Q1 Loss as AI Computing Revenue Surges 117%, Overtakes Bitcoin Mining
05-09 11:17
Google DeepMind AI Co-Mathematician Hits 47.9% on FrontierMath Tier 4, Beats GPT-5.5 Pro, Solves 3 Previously Unsolvable Problems
05-09 09:54
OpenAI's Reward System Inadvertently Scores Thinking Chains on 6 Models Including GPT-5.4
05-09 07:41
MiniMax Scans 200K Tokens, Discovers 4.9% Degradation in M2 Series Models
05-09 05:52
Deepseek Plans V4 Model Update for June Release
In-Depth Analysis

Fed Survey Shows AI Concerns Rising Across Markets, Credit and Jobs

Coinpedia05-10 03:39

NVIDIA’s open AI long-term partner Deepinfra raises $107 million Series B funding to build a “token factory”

ChainNewsAbmedia05-10 00:04

OpenAI reveals unexpected impact of CoT scoring: preserving chain-of-thought monitoring is a key line of defense for AI agent alignment

ChainNewsAbmedia05-09 07:34
Comment
0/400
No comments