BestHub
Sign in
AntTech
Author

AntTech

Technology is the core driver of Ant's future creation.

726
Articles
0
Likes
4.2k
Views
0
Comments
Recent Articles

Latest from AntTech

100 recent articles max
AntTech
AntTech
Sep 4, 2026 · Databases

OmniTable: One Logical Table Manages 305B Records Across 35PB for LLM Training

Ant Group's OmniTable system, awarded VLDB 2026 Best Industrial Paper, uses a unified logical wide table to manage 35PB and 305B records for LLM training, reducing end-to-end data preparation from 14 days to 2.5 days via logical-physical separation, feature dependency DAGs, record-level fault tolerance, and operator fusion.

Fault ToleranceLLM data curationOmniTable
0 likes · 18 min read
OmniTable: One Logical Table Manages 305B Records Across 35PB for LLM Training
AntTech
AntTech
Sep 2, 2026 · Artificial Intelligence

ECCV 2026 Paper Showcase: Breaking Vision Perception & Prediction Boundaries

This article summarizes four ECCV 2026 papers: a dynamic cross-layer injection framework for deep vision-language fusion, an event-augmented VLA model enabling robot operation in extreme darkness and blur, a predictive differentiable rendering method using 2D Gaussians for high-fidelity video prediction, and a data-scaling approach for high-resolution weather forecasting that demonstrates clear scaling laws.

Data ScalingECCV 2026Event Cameras
0 likes · 10 min read
ECCV 2026 Paper Showcase: Breaking Vision Perception & Prediction Boundaries
AntTech
AntTech
Aug 20, 2026 · Artificial Intelligence

Ling-3.0-flash: Open-Source LLM Designed for Real-World Deployment

Ling-3.0-flash is a newly open‑sourced 124B‑parameter MoE model that offers multiple quantized versions, API, single‑machine private deployment, and high‑performance GPU inference exceeding 1100 tokens/s, with detailed benchmarks, optimization techniques, and real‑world use‑case analyses for agents, coding, and sensitive data processing.

LLMLing-3.0-flashMoE
0 likes · 15 min read
Ling-3.0-flash: Open-Source LLM Designed for Real-World Deployment
AntTech
AntTech
Aug 12, 2026 · Artificial Intelligence

Live #44: Multi‑Agent Automation of Rust Code Verification & 30× Storage Reduction for User Representations

This live session reviews four KDD 2026 papers that introduce a multi‑agent framework for industrial Rust code verification, a unified quantized tokenizer that cuts user representation storage by 30×, a query‑anchored LLM approach for scenario‑adaptive user modeling, and the HIVE ensemble method for efficient out‑of‑distribution generalization, each validated with extensive experiments and real‑world deployments.

Large Language ModelMulti-Agent SystemsOut-of-Distribution
0 likes · 9 min read
Live #44: Multi‑Agent Automation of Rust Code Verification & 30× Storage Reduction for User Representations
AntTech
AntTech
Jul 28, 2026 · Artificial Intelligence

Introducing PIBench: A Payment‑Scenario Benchmark for AI Coding Agents

PIBench, an open‑source benchmark from Alipay’s AI payment team, defines 459 rubric items across 9 payment products and 9 real‑world projects to evaluate AI coding agents’ ability to integrate secure payment flows, covering basic functionality and advanced risk‑handling, with detailed experimental results showing significant model gaps and the impact of structured skill guidance.

AI coding agentsAlipayLLM evaluation
0 likes · 14 min read
Introducing PIBench: A Payment‑Scenario Benchmark for AI Coding Agents
AntTech
AntTech
Jul 27, 2026 · Artificial Intelligence

LLaDA2.2 Released: Levenshtein Editing Enables Diffusion Language Models to Correct On-the-Fly

LLaDA2.2 introduces a Levenshtein‑based edit mechanism and the L‑EBPO reinforcement framework, allowing diffusion language models to delete and insert tokens during agent interactions, achieving near‑autoregressive accuracy (53.83 vs 55.74) and 1.64× higher BF16 throughput, plus an 8.6 % gain on SWE‑bench.

LLaDA2.2Levenshtein editingMoE
0 likes · 11 min read
LLaDA2.2 Released: Levenshtein Editing Enables Diffusion Language Models to Correct On-the-Fly
AntTech
AntTech
Jul 18, 2026 · Artificial Intelligence

How HOP 3.0 Gives Intelligent Agents a Native Language for Trustworthy Enterprise AI

The article analyzes the lack of a native language for autonomous agents, outlines three generations of task‑language designs and three associated risks, and explains how Ant Financial’s HOP 3.0 fuses explicit structured logic with large‑model reasoning to improve reliability, reduce token usage and fault rates, and embed security rules directly into the agent’s execution language.

AI TrustworthinessHOP 3.0Intelligent Agents
0 likes · 9 min read
How HOP 3.0 Gives Intelligent Agents a Native Language for Trustworthy Enterprise AI
AntTech
AntTech
Jul 18, 2026 · Artificial Intelligence

How Ant Group and 20+ Partners Are Building a Trustworthy Agent Ecosystem with ASL

Ant Group outlines the security challenges of scaling AI agents and describes its native‑security AgentOS platform, the ASL trust protocol, and the Avernet collaboration infrastructure, developed together with more than twenty industry partners to enable trustworthy multi‑agent interactions.

AI AgentsASL protocolAgentOS
0 likes · 8 min read
How Ant Group and 20+ Partners Are Building a Trustworthy Agent Ecosystem with ASL