Author

Kuaishou Tech

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

229

Articles

Likes

680

Views

Comments

Latest from Kuaishou Tech

100 recent articles max

Kuaishou Tech

Jan 8, 2026 · Artificial Intelligence

Top 12 Kuaishou Papers Accepted at AAAI 2026: Breakthroughs in Recommendation, Video Generation, and LLM Research

Kuaishou secured 12 papers at AAAI 2026, covering advances in search and recommendation systems, multi‑camera video generation, multimodal understanding, generative model fundamentals, video large language models, experimental design, and LLM latent‑space reasoning, with three papers highlighted as oral presentations.

AILLMVideo Generation

0 likes · 22 min read

Top 12 Kuaishou Papers Accepted at AAAI 2026: Breakthroughs in Recommendation, Video Generation, and LLM Research

Kuaishou Tech

Dec 19, 2025 · Artificial Intelligence

Why Sampling Noise, Not Train‑Inference Gap, Drives RL Instability in MOE Models

The article reveals that sampling noise, rather than train‑inference inconsistency, is the primary cause of reward collapse during RL training of MOE models, and demonstrates that suppressing this noise stabilizes training and speeds convergence.

AI codingAgentic CodingMoE models

0 likes · 6 min read

Why Sampling Noise, Not Train‑Inference Gap, Drives RL Instability in MOE Models

Kuaishou Tech

Dec 18, 2025 · Artificial Intelligence

How SSR Turns Multimodal Recommendation into an Interpretable Frequency‑Domain Reasoning Problem

The paper introduces SSR, a novel multimodal recommendation framework that leverages graph Fourier transforms, energy‑balanced frequency bands, structured regularization, and low‑rank tensor decomposition to replace black‑box fusion with explainable, adaptive reasoning, achieving state‑of‑the‑art results on Amazon datasets and strong cold‑start performance.

cold startcontrastive learningfrequency domain

0 likes · 15 min read

How SSR Turns Multimodal Recommendation into an Interpretable Frequency‑Domain Reasoning Problem

Kuaishou Tech

Dec 16, 2025 · Mobile Development

How Leading Tech Giants Are Solving Cross‑Platform Challenges with KMP and AI

The "AI‑Led Cross‑Platform Technology New Paradigm" salon gathered experts from Kuaishou, Alipay, Tencent, and JetBrains to share deep technical insights on Kotlin Multiplatform, large‑scale multi‑device architecture, AI integration, and real‑world migration experiences across iOS, Android and HarmonyOS.

AI integrationKMPKotlin

0 likes · 8 min read

How Leading Tech Giants Are Solving Cross‑Platform Challenges with KMP and AI

Kuaishou Tech

Dec 4, 2025 · Artificial Intelligence

Can a Tree‑Reasoned Model Master Video Emotion Understanding?

The paper introduces VidEmo, a multimodal video foundation model that uses a two‑stage emotion‑clue‑guided reasoning framework and a large emotion‑centric dataset (Emo‑CFG) to achieve state‑of‑the‑art performance on facial attribute, expression, and fine‑grained emotion tasks, surpassing Gemini 2.0.

AIFoundation ModelMultimodal

0 likes · 15 min read

Can a Tree‑Reasoned Model Master Video Emotion Understanding?

Kuaishou Tech

Dec 3, 2025 · Artificial Intelligence

Can Diffusion Models Be Their Own Reward Model? Latent Reward Modeling & Step-Level Preference Optimization

This article presents a novel paradigm—Latent Reward Model (LRM) and Latent Preference Optimization (LPO)—that repurposes diffusion models as noise‑aware latent reward models for step‑level preference optimization, addressing the shortcomings of pixel‑level reward models, introducing multi‑preference consistent filtering, and demonstrating significant performance and efficiency gains on benchmarks such as PickScore and T2I‑CompBench++.

AI alignmentPreference Optimizationdiffusion models

0 likes · 9 min read

Can Diffusion Models Be Their Own Reward Model? Latent Reward Modeling & Step-Level Preference Optimization

Kuaishou Tech

Nov 28, 2025 · Artificial Intelligence

Keye-VL-671B-A37B Leads Vision, Video, and Math Benchmarks

Kwai has open‑sourced its new flagship multimodal model Keye‑VL‑671B‑A37B, which upgrades visual perception, cross‑modal alignment and complex reasoning, achieving top scores on image, video, and mathematical reasoning benchmarks while detailing its architecture, three‑stage pre‑training, post‑training strategies, and future multimodal agent plans.

Large Language ModelMultimodalOpen Source

0 likes · 10 min read

Keye-VL-671B-A37B Leads Vision, Video, and Math Benchmarks

Kuaishou Tech

Nov 25, 2025 · Artificial Intelligence

How Flow‑GRPO Boosts Image Generation Accuracy to 95% with Online Reinforcement Learning

Flow‑GRPO introduces online reinforcement learning into flow‑matching models by converting deterministic ODE sampling to stochastic SDE sampling and reducing denoising steps, raising SD‑3.5‑Medium's GenEval accuracy from 63% to 95%—surpassing GPT‑4o—and demonstrating strong gains in complex composition, text rendering, and human‑preference alignment across multiple generative tasks.

AI researchdeep learningflow matching

0 likes · 8 min read

How Flow‑GRPO Boosts Image Generation Accuracy to 95% with Online Reinforcement Learning

Kuaishou Tech

Nov 24, 2025 · Artificial Intelligence

How Human Feedback Supercharges Video Generation – The VideoAlign Pipeline Explained

This article details a new research pipeline that leverages large‑scale human preference data, a multi‑dimensional video reward model, and specialized alignment algorithms to dramatically improve video generation quality, motion fidelity, and text‑video consistency, with open‑source code and benchmarks for reproducibility.

AI alignmentHuman FeedbackRLHF

0 likes · 10 min read

How Human Feedback Supercharges Video Generation – The VideoAlign Pipeline Explained

Kuaishou Tech

Nov 20, 2025 · Artificial Intelligence

How UniDex and UniSearch Redefine Video Search with Semantic Indexing and Generative Models

This article explains how Kuaishou’s UniDex replaces traditional term‑based inverted indexes with model‑driven semantic posting lists and how the end‑to‑end UniSearch framework generates video IDs directly from queries, delivering higher relevance, lower latency, and significant online performance gains.

AIGenerative ModelsSearch

0 likes · 17 min read