Author

Xiaohongshu Tech REDtech

Official account of the Xiaohongshu tech team, sharing tech innovations and problem insights, advancing together.

115

Articles

Likes

324

Views

Comments

Latest from Xiaohongshu Tech REDtech

100 recent articles max

Xiaohongshu Tech REDtech

Feb 27, 2025 · Artificial Intelligence

SAFE: A Lightweight General AI Image Detection Method Achieving 96.7% Accuracy Across 33 Test Subsets

SAFE is a lightweight AI‑image detection framework using only 1.44 M parameters and 2.30 B FLOPs that preserves fine‑grained artifacts through crop‑based preprocessing, invariant augmentations, and high‑frequency wavelet features, achieving an average 96.7 % accuracy across 33 test subsets and strong generalization to unseen GAN and diffusion generators.

AI image detectionLightweight Modelcomputer vision

0 likes · 11 min read

SAFE: A Lightweight General AI Image Detection Method Achieving 96.7% Accuracy Across 33 Test Subsets

Xiaohongshu Tech REDtech

Feb 24, 2025 · Artificial Intelligence

AIDE: Hybrid Feature Detector for AI‑Generated Image Detection and the Chameleon Benchmark

The paper introduces AIDE, a hybrid AI‑generated image detector that fuses low‑level pixel statistics with high‑level semantic embeddings, and the manually curated Chameleon benchmark of ~26 000 diverse, high‑realism images, showing AIDE surpasses nine state‑of‑the‑art methods by up to 4.6 % while highlighting remaining challenges on this tougher dataset.

AI-generated image detectionbenchmark datasetcomputer vision

0 likes · 14 min read

AIDE: Hybrid Feature Detector for AI‑Generated Image Detection and the Chameleon Benchmark

Xiaohongshu Tech REDtech

Feb 20, 2025 · Big Data

How Xiaohongshu Accelerated Data Warehouse Queries with Logical Datasets & Materialized Views

Xiaohongshu tackled low reuse of APP tables, limited scalability of single-table BI datasets, and poor dashboard query performance by introducing logical datasets and materialized views, which enable query pruning, reduce data redundancy, and accelerate BI queries, achieving up to 80% latency reduction and higher hit rates.

BIData WarehouseQuery Optimization

0 likes · 25 min read

How Xiaohongshu Accelerated Data Warehouse Queries with Logical Datasets & Materialized Views

Xiaohongshu Tech REDtech

Feb 17, 2025 · Artificial Intelligence

WorldSense: A New Benchmark for Evaluating Multimodal Large Models in Real‑World Scenarios

WorldSense, a new benchmark of 1,662 real‑world video‑audio clips and 3,172 QA pairs across 26 cognitive tasks, reveals that current multimodal large models achieve only 25%–48% accuracy, highlighting the crucial role of combined visual‑audio input and the difficulty of audio‑ and emotion‑related reasoning.

benchmark datasetlarge modelsmodel analysis

0 likes · 12 min read

WorldSense: A New Benchmark for Evaluating Multimodal Large Models in Real‑World Scenarios

Xiaohongshu Tech REDtech

Jan 16, 2025 · Cloud Native

Xiaohongshu Large-Scale Cloud-Native Mixed Deployment and Elasticity Practices

Xiaohongshu’s cloud‑native team transformed its over‑90% containerized services by introducing resource‑pooled mixed deployment, fine‑grained unified scheduling, and an elastic container pool with global HPA and cluster autoscaling—driving 35% of resources to mixed use, tens of millions of daily core‑hours, and roughly 30% cost savings while preparing for hybrid‑cloud expansion and FinOps.

ContainerizationOperating systemcloud-native

0 likes · 7 min read

Xiaohongshu Large-Scale Cloud-Native Mixed Deployment and Elasticity Practices

Xiaohongshu Tech REDtech

Jan 16, 2025 · Artificial Intelligence

Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection

The authors present a semantic‑graph‑enhanced uncertainty modeling framework that captures token, sentence, and paragraph dependencies, propagates uncertainty through entity relations and contradiction probabilities, and achieves roughly a 20 % gain in paragraph‑level hallucination detection on WikiBio and NoteSum compared with existing uncertainty‑based baselines.

Hallucination DetectionSemantic GraphSentence-level Modeling

0 likes · 13 min read

Enhancing Uncertainty Modeling with Semantic Graph for Hallucination Detection

Xiaohongshu Tech REDtech

Jan 2, 2025 · Artificial Intelligence

Xiaohongshu's Self-developed RLHF System for Multimodal Large Language Models: Design, Optimization, and Performance

Xiaohongshu’s team unveiled a self‑developed RLHF system that trains multimodal large language models using heterogeneous and homogeneous network architectures, extensive PPO optimizations, and Medusa speculative sampling, achieving over 50% throughput gains, reduced hardware needs, and 5‑20% performance improvements on zero‑shot benchmarks.

Distributed TrainingPPOPRM

0 likes · 21 min read

Xiaohongshu's Self-developed RLHF System for Multimodal Large Language Models: Design, Optimization, and Performance

Xiaohongshu Tech REDtech

Dec 26, 2024 · Artificial Intelligence

Focused Large Language Models are Stable Many-Shot Learners

FocusICL mitigates the reverse‑scaling of in‑context learning by masking irrelevant tokens and applying hierarchical batch attention, cutting attention complexity, and delivering consistent query focus that yields average accuracy gains of about 5 % across multiple LLMs and benchmarks.

Attention MechanismsFew‑Shot LearningFocusICL

0 likes · 16 min read

Focused Large Language Models are Stable Many-Shot Learners

Xiaohongshu Tech REDtech

Dec 26, 2024 · Artificial Intelligence

Instruction Embedding: Latent Representations of Instructions for Task Identification

The paper introduces Instruction Embedding—a task‑focused text representation learned on the new Instruction Embedding Benchmark—and shows that Prompt‑based Instruction Embedding (PIE) outperforms standard embeddings in clustering, similarity, and downstream tasks such as data selection, in‑context example retrieval, test‑set compression, and task‑correlation analysis.

Fine-tuningcontrastive learninginstruction embedding

0 likes · 15 min read

Instruction Embedding: Latent Representations of Instructions for Task Identification

Xiaohongshu Tech REDtech

Dec 25, 2024 · Industry Insights

How Xiaohongshu’s Security Team Achieved Zero Defense Losses in Shanghai’s 2024 “Panshi Action”

In December 2024, Xiaohongshu’s information security team topped the Shanghai “Panshi Action” competition, earning top blue‑team honors and a zero‑loss defense record by leveraging real‑time traffic monitoring, big‑data analytics, rapid incident response, and successful attacker attribution.

CybersecurityInformation Securitybig data analysis

0 likes · 3 min read

How Xiaohongshu’s Security Team Achieved Zero Defense Losses in Shanghai’s 2024 “Panshi Action”