Author

Kuaishou Tech

Official Kuaishou tech account, providing real-time updates on the latest Kuaishou technology practices.

229

Articles

Likes

678

Views

Comments

Latest from Kuaishou Tech

100 recent articles max

Kuaishou Tech

May 18, 2026 · Artificial Intelligence

How ALM‑MTA Improves Multi‑Touch Attribution with Front‑Door Identification and Adversarial Modeling

The ALM‑MTA method combines front‑door causal adjustment with an adversarial proxy for the unobserved mediator, eliminating hidden confounding in multi‑touch attribution and delivering more reliable uplift estimates that boosted Kuaishou's DAU by 0.6% and AUC by 11% over SOTA baselines, as reported in an ICLR 2026 paper.

AI researchadversarial learningcausal attribution

0 likes · 13 min read

How ALM‑MTA Improves Multi‑Touch Attribution with Front‑Door Identification and Adversarial Modeling

Kuaishou Tech

May 14, 2026 · Artificial Intelligence

Open‑Source Kwai Summary Attention (KSA): A Sequence‑Compression Mechanism for Long‑Context Inference

KSA inserts learnable summary tokens to compress KV cache by a factor of eight, enabling accurate long‑context retrieval with far lower memory and compute costs, and it consistently outperforms full‑attention and other hybrid methods on large‑scale benchmarks.

Efficient InferenceKSAKV cache reduction

0 likes · 13 min read

Open‑Source Kwai Summary Attention (KSA): A Sequence‑Compression Mechanism for Long‑Context Inference

Kuaishou Tech

May 13, 2026 · Artificial Intelligence

OneSearch‑V2 Launches: Self‑Distilled Generative Search That Truly Understands Users

OneSearch‑V2 introduces a latent‑reasoning enhanced self‑distillation framework that augments query understanding with thought‑augmented CoT, aligns preferences via direct user behavior feedback, and achieves up to 4 % CTR lift and significant order growth without adding inference cost or latency.

LLMbehavioral feedbacke-commerce

0 likes · 26 min read

OneSearch‑V2 Launches: Self‑Distilled Generative Search That Truly Understands Users

Kuaishou Tech

Apr 29, 2026 · Operations

Boosting Oncall Interception from 15% to 55%: KOncall’s AI‑Driven Evolution at Kuaishou

Kuaishou’s R&D efficiency team built the KOncall intelligent on‑call platform, integrating LLM‑based retrieval‑augmented generation, Redis Pub/Sub streaming, OCR multimodal parsing, FAQ knowledge ops, and custom reranking, which raised automated query interception from 15% to 55% and processed over 116 000 requests, turning on‑call from a bottleneck into a capability starter.

AI OperationsIncident ManagementLLM

0 likes · 26 min read

Boosting Oncall Interception from 15% to 55%: KOncall’s AI‑Driven Evolution at Kuaishou

Kuaishou Tech

Apr 24, 2026 · Artificial Intelligence

ICLR 2026: Kuaishou Tech Team’s Cutting‑Edge AI Research Highlights

This article reviews eight Kuaishou‑authored papers accepted at ICLR 2026, summarizing their problem statements, novel methods such as front‑door causal attribution, visual table retrieval, denoising rerankers, difficulty‑adaptive reasoning, diffusion code infilling, generative ordinal regression, multimodal video retrieval, e‑commerce dialogue benchmarks, and a new LLM creativity evaluator, together with reported experimental gains.

Artificial IntelligenceICLR 2026Kuaishou

0 likes · 19 min read

Kuaishou Tech

Apr 16, 2026 · Artificial Intelligence

Hierarchical Semantic RL Tackles Dynamic Action Spaces in Recommendations

Researchers from Kuaishou, Fudan and Tianjin University introduce the Hierarchical Semantic Reinforcement Learning (HSRL) framework, which maps high‑dimensional, dynamic item spaces into a fixed‑size semantic action space via semantic IDs, employs a hierarchical policy network and multi‑level critics, and demonstrates 13‑18% gains on public datasets and an 18.4% ad spend lift in billion‑scale online tests.

Large‑Scale Deploymenthierarchical policyindustrial experiments

0 likes · 11 min read

Hierarchical Semantic RL Tackles Dynamic Action Spaces in Recommendations

Kuaishou Tech

Mar 19, 2026 · Backend Development

How Kuaishou Boosted Build Performance with AutoFDO, ThinLTO, BOLT, and Propeller

This article details Kuaishou's systematic compiler and build‑system optimizations—including AutoFDO, ThinLTO, BOLT, and a newly improved Propeller—showing how they reduced compilation time from hours to seconds, cut CPU usage by 10%, and achieved up to 15% performance gains while solving profile‑staleness and integration challenges.

AutoFDOBoltBuild System

0 likes · 25 min read

How Kuaishou Boosted Build Performance with AutoFDO, ThinLTO, BOLT, and Propeller

Kuaishou Tech

Mar 4, 2026 · Artificial Intelligence

How LLMs Are Revolutionizing Reinforcement Learning for Recommendation Systems

This survey examines the emerging LLM‑RL collaborative recommendation paradigm, outlining its research background, five main collaboration patterns, standardized evaluation protocols, and the key challenges and future directions for building smarter, more robust recommender systems.

Artificial IntelligenceLLMRecommendation Systems

0 likes · 14 min read

How LLMs Are Revolutionizing Reinforcement Learning for Recommendation Systems

Kuaishou Tech

Jan 28, 2026 · Artificial Intelligence

BLM‑Guard: Explainable Multimodal Ad Moderation Using Chain‑of‑Thought and Policy‑Aligned RL

The paper introduces BLM‑Guard, an explainable multimodal ad‑moderation framework that combines interleaved‑modal chain‑of‑thought reasoning with a policy‑aligned reinforcement‑learning reward to detect hidden cross‑modal violations in short‑video ads, and presents a new benchmark that demonstrates state‑of‑the‑art performance across multiple risk scenarios.

ad risk detectionbenchmarkchain-of-thought

0 likes · 12 min read

BLM‑Guard: Explainable Multimodal Ad Moderation Using Chain‑of‑Thought and Policy‑Aligned RL

Kuaishou Tech

Jan 19, 2026 · Artificial Intelligence

How OneSug Revolutionizes E‑commerce Query Suggestion with End‑to‑End Generative Modeling

OneSug introduces an end‑to‑end generative framework that unifies recall, coarse‑ranking, and fine‑ranking for e‑commerce query suggestion, addressing the limitations of traditional multi‑stage cascades and dramatically improving relevance, efficiency, and business metrics in real‑world deployments.

Generative ModelsMachine LearningRecommendation Systems

0 likes · 10 min read

How OneSug Revolutionizes E‑commerce Query Suggestion with End‑to‑End Generative Modeling