Author

Kuaishou Tech

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

225

Articles

Likes

574

Views

Comments

Latest from Kuaishou Tech

100 recent articles max

Kuaishou Tech

Jun 5, 2025 · Artificial Intelligence

7 Kuaishou AI Papers Accepted at ACL 2025: Video Understanding & Safe LLM Decoding

Kuaishou’s foundational large-model team has secured seven papers at ACL 2025, spanning alignment bias in training, safety defenses during inference, decoding strategies, fine-grained video-temporal understanding, reward fairness in RLHF, multimodal captioning benchmarks, and methods to curb hallucinations in vision-language models.

ACLAI safetybenchmark

0 likes · 13 min read

7 Kuaishou AI Papers Accepted at ACL 2025: Video Understanding & Safe LLM Decoding

Kuaishou Tech

Jun 4, 2025 · Artificial Intelligence

KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning

The KwaiPilot team released the KwaiCoder‑AutoThink‑preview model, which introduces a novel automatic‑thinking training paradigm and a process‑supervised reinforcement‑learning method called Step‑SRPO, enabling the model to dynamically switch between thinking and non‑thinking modes, reduce inference cost, and achieve up to 20‑point gains on code and math benchmarks while handling large‑scale codebases.

AI researchModel OptimizationReinforcement learning

0 likes · 12 min read

KwaiCoder-AutoThink-preview: An Automatic‑Thinking Large Model Enhanced with Step‑SRPO Reinforcement Learning

Kuaishou Tech

May 28, 2025 · Databases

Optimizing Kuaishou's Photo Object Storage: Reducing Size and Boosting Cache Hit Rate

This article details how Kuaishou dramatically cut storage costs and improved cache efficiency for its core Photo data object by cleaning up redundant JSON fields, applying selective serialization, and performing large‑scale data cleaning, achieving a 25% size reduction, a 2% cache‑hit increase, and multi‑hundred‑TB savings.

Cache Hit RateKuaishouPhoto Object

0 likes · 20 min read

Optimizing Kuaishou's Photo Object Storage: Reducing Size and Boosting Cache Hit Rate

Kuaishou Tech

May 26, 2025 · Artificial Intelligence

CineMaster: A 3D‑Aware and Controllable Framework for Cinematic Text‑to‑Video Generation

Researchers introduce CineMaster, a SIGGRAPH‑2025 paper presenting a 3D‑aware, controllable text‑to‑video generation framework that lets users define target objects and camera motions via an interactive workflow, enabling cinematic video creation with high‑quality, user‑directed results.

3D-awareAI videoCineMaster

0 likes · 6 min read

CineMaster: A 3D‑Aware and Controllable Framework for Cinematic Text‑to‑Video Generation

Kuaishou Tech

May 14, 2025 · Artificial Intelligence

StableReinforce and R1-Reward: Enhancing Multimodal Reward Models with Reinforcement Learning

This article presents StableReinforce and the R1-Reward model, demonstrating how reinforcement learning techniques can stabilize training and significantly improve the performance of multimodal reward models for large language models across several benchmarks.

AILLMR1-Reward

0 likes · 15 min read

StableReinforce and R1-Reward: Enhancing Multimodal Reward Models with Reinforcement Learning

Kuaishou Tech

May 13, 2025 · Artificial Intelligence

How KuaiMod Uses Multimodal AI to Revolutionize Short‑Video Content Quality

This article analyzes KuaiMod, a multimodal large‑model solution developed by Kuaishou for short‑video content quality assessment, detailing its benchmark dataset, chain‑of‑thought data construction, offline SFT + DPO training, online reinforcement‑learning updates, evaluation results, and large‑scale deployment impact.

KuaiModReinforcement learningbenchmark

0 likes · 19 min read

How KuaiMod Uses Multimodal AI to Revolutionize Short‑Video Content Quality

Kuaishou Tech

Apr 24, 2025 · Artificial Intelligence

Two‑Stage History‑Resampling Policy Optimization (SRPO) for Large‑Scale LLM Reinforcement Learning

The article introduces SRPO, a two‑stage history‑resampling reinforcement‑learning framework that systematically tackles common GRPO training issues and achieves state‑of‑the‑art performance on both math and code benchmarks with far fewer training steps, while also revealing emergent self‑reflection behaviors in large language models.

LLM optimizationReinforcement learningSRPO

0 likes · 12 min read

Two‑Stage History‑Resampling Policy Optimization (SRPO) for Large‑Scale LLM Reinforcement Learning

Kuaishou Tech

Apr 23, 2025 · Artificial Intelligence

Kuaishou's Accepted Papers at ICLR 2025 and Their Summaries

The article highlights Kuashou's eleven high‑quality papers accepted at ICLR 2025, covering advances in streaming video understanding, 3D trajectory control, multimodal talking‑face animation, transformer indexing, efficient video generation, industrial recommendation datasets, token gradient conflict in MoE, stable segmentation, multi‑camera video synthesis, large‑scale multimodal instruction tuning, and hallucination detection in retrieval‑augmented generation.

AIResearchDeepLearningICLR2025

0 likes · 20 min read

Kuaishou's Accepted Papers at ICLR 2025 and Their Summaries

Kuaishou Tech

Apr 2, 2025 · Big Data

Apache Hudi Asia Summit Successfully Held

The first Apache Hudi Asia Summit in Beijing attracted over 230 attendees, featuring technical discussions on data lake optimization and case studies from companies like Fastly and Meituan.

Apache HudiTechnical Conferencebig data

0 likes · 12 min read

Apache Hudi Asia Summit Successfully Held

Kuaishou Tech

Feb 20, 2025 · Artificial Intelligence

Second Short-Form Video Quality Assessment and Enhancement Challenge (CVPR NTIRE 2025)

The second short-form video quality assessment and enhancement challenge, co‑organized by Kuaishou's audio‑video team and the Intelligent Media Computing Lab, invites global researchers to develop efficient quality assessment models and diffusion‑based super‑resolution methods using the new KwaiSR dataset, with prize money and potential CVPR workshop paper invitations.

AI competitionCVPR NTIREdataset

0 likes · 9 min read

Second Short-Form Video Quality Assessment and Enhancement Challenge (CVPR NTIRE 2025)