Author

AntTech

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

710

Articles

Likes

2.3k

Views

Comments

Latest from AntTech

100 recent articles max

AntTech

Jul 9, 2025 · Artificial Intelligence

How KAG-Thinker Boosts Structured Reasoning in Large Language Models

The KAG-Thinker model, a collaborative effort by Ant Group, Zhejiang University, and Tongji University, introduces a hierarchical "breadth splitting + depth solving" framework that enhances logical stability, knowledge utilization, and retrieval robustness for complex multi‑hop reasoning tasks across general and specialized domains.

AIKAG-ThinkerKnowledge retrieval

0 likes · 10 min read

How KAG-Thinker Boosts Structured Reasoning in Large Language Models

AntTech

Jul 8, 2025 · Artificial Intelligence

Four AI Papers at ACL 2025: Graph QA, Unsupervised Tokenizer, LLM Offsite Tuning

At ACL 2025 in Vienna, a live paper showcase will dissect four cutting‑edge AI studies: the M3GQA benchmark for multi‑entity graph question answering, an unsupervised morphological tree tokenizer, the GradOT method for training‑free, gradient‑preserving offsite LLM tuning, and a large‑language‑model approach to historical analogy.

ACL 2025Graph QAHistorical analogy

0 likes · 8 min read

Four AI Papers at ACL 2025: Graph QA, Unsupervised Tokenizer, LLM Offsite Tuning

AntTech

Jul 3, 2025 · Artificial Intelligence

How Ant Group’s AI Multimodal Evaluation Transforms Image, Speech, and Video Quality Testing

In a QECon 2025 talk, Ant Group’s AI team detailed a comprehensive multimodal evaluation framework that leverages large‑model metrics, custom pipelines, and benchmark datasets to assess image generation, speech recognition, and video quality, while also contributing to industry standards and academic research.

AI evaluationLarge ModelsMultimodal

0 likes · 16 min read

How Ant Group’s AI Multimodal Evaluation Transforms Image, Speech, and Video Quality Testing

AntTech

Jul 2, 2025 · Artificial Intelligence

How Multimodal Large Models Revolutionize UI Automation Testing

This article details how Alibaba's Ant Group leverages multimodal large‑language models and multi‑agent architectures to create a low‑code, AI‑driven UI automation testing framework that improves test coverage, reduces manual effort, and scales across diverse mobile mini‑program scenarios.

AI testingSoftware qualityUI automation

0 likes · 9 min read

How Multimodal Large Models Revolutionize UI Automation Testing

AntTech

Jun 25, 2025 · Artificial Intelligence

CVPR 2025: Semi-Body Digital Humans, Video Upscaling, Mobile Super‑Res

In this CVPR 2025 showcase, Ant Group presents three cutting‑edge papers—EchoMimicV2 introducing an open‑source semi‑body digital human generation framework, RivuletMLP offering an efficient MLP‑based architecture for compressed video quality enhancement, and a quantized super‑resolution model that achieves real‑time 3× upscaling on mobile NPUs.

AICVPRcomputer vision

0 likes · 6 min read

CVPR 2025: Semi-Body Digital Humans, Video Upscaling, Mobile Super‑Res

AntTech

Jun 23, 2025 · Artificial Intelligence

Can AI Auditors Ensure Reliable Software? Highlights from EXPRESS 2025 at ISSTA

The EXPRESS 2025 workshop at ISSTA in Norway will showcase AI‑driven code auditing, present cutting‑edge research on trustworthy software systems, and invite researchers and practitioners to discuss transparency, reliability, and security challenges in modern software engineering.

AI auditingISSTA 2025LLM

0 likes · 5 min read

Can AI Auditors Ensure Reliable Software? Highlights from EXPRESS 2025 at ISSTA

AntTech

Jun 21, 2025 · Artificial Intelligence

Ring-lite: Open‑Source Lightweight MoE Model Sets SOTA on AIME and LiveCodeBench

Ring-lite, an open‑source lightweight Mixture‑of‑Experts inference model built on Ling‑lite‑1.5, introduces the C3PO reinforcement‑learning training method and achieves state‑of‑the‑art results on benchmarks such as AIME24/25, LiveCodeBench, CodeForce, and GPQA‑diamond, while offering full transparency of weights, code, and data.

AI inferenceC3PObenchmark

0 likes · 11 min read

Ring-lite: Open‑Source Lightweight MoE Model Sets SOTA on AIME and LiveCodeBench

AntTech

Jun 18, 2025 · Artificial Intelligence

How Ant Group’s Baoling Models Push Toward AGI with MoE and Multimodal Innovations

In a detailed AICon talk, Ant Group’s Baoling team leader Zhou Jun outlines their latest large‑model training techniques, MoE architecture optimizations, multimodal breakthroughs, open‑source releases, and the strategic roadmap needed to turn AI into a ubiquitous, “scan‑code‑level” everyday assistant.

AI infrastructureMixture of ExpertsOpen Source

0 likes · 25 min read

How Ant Group’s Baoling Models Push Toward AGI with MoE and Multimodal Innovations

AntTech

Jun 16, 2025 · Information Security

Uncovering New Attack Vectors in Model Context Protocols: Risks and Defenses

A comprehensive study reveals that Model Context Protocol (MCP) platforms lack strict vetting, users struggle to detect malicious servers, and current large language models cannot effectively resist MCP‑level injection attacks, highlighting critical security challenges and proposing mitigation strategies.

Information SecurityLLM SecurityMCP

0 likes · 11 min read

Uncovering New Attack Vectors in Model Context Protocols: Risks and Defenses

AntTech

Jun 15, 2025 · Artificial Intelligence

21 Ant Research Papers Shaping CVPR 2025: AI Image & Video Generation Breakthroughs

The Interactive Intelligence Lab of Ant Technology Research Institute presented 21 accepted CVPR 2025 papers covering visual generation, editing, 3D vision, digital humans and multimodal AI, highlighting tools such as MagicQuill, Lumos, Aurora, FLARE, LeviTor, MangaNinja, AniDoc, Mimir, AvatarArtist, DiffListener, MotionStone, TensorialGaussianAvatars, DualTalk, CompreCap and Uni-AD.

CVPR2025Video Generationcomputer vision

0 likes · 20 min read

21 Ant Research Papers Shaping CVPR 2025: AI Image & Video Generation Breakthroughs