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

Apr 10, 2024 · Artificial Intelligence

Early‑Stopping Self‑Consistency (ESC): Reducing Sampling Cost for Large Language Model Reasoning

Early‑Stopping Self‑Consistency (ESC) dynamically halts sampling once a sliding‑window answer distribution reaches zero entropy, cutting the number of required LLM reasoning samples by 34‑84 % across arithmetic, commonsense, and symbolic benchmarks while preserving accuracy and offering a theoretically‑bounded, robust, budget‑adaptive alternative to traditional Self‑Consistency.

AIEarly StoppingInference

0 likes · 14 min read

Early‑Stopping Self‑Consistency (ESC): Reducing Sampling Cost for Large Language Model Reasoning

Xiaohongshu Tech REDtech

Mar 18, 2024 · Big Data

Optimizing Offline Data Warehouse with StarRocks: Replacing Spark for Faster, Cost‑Effective Data Processing

By replacing part of its Spark‑based offline pipeline with StarRocks, Xiaohongshu’s data‑warehouse team cut job execution from hours to minutes, reduced resource usage over 90 %, lowered back‑fill cost by 99 %, and accelerated daily data production by 1.5 hours.

Data WarehouseOLAPPerformance optimization

0 likes · 16 min read

Optimizing Offline Data Warehouse with StarRocks: Replacing Spark for Faster, Cost‑Effective Data Processing

Xiaohongshu Tech REDtech

Mar 4, 2024 · Big Data

Integrating Data Lake Technologies with Data Warehouse Architecture at Xiaohongshu: Practices and Performance Optimizations

Xiaohongshu’s data‑warehouse team integrated Apache Iceberg‑based data‑lake techniques into its existing warehouse, replacing the legacy Hive/Spark stack with global sorting, Z‑order, and upsert‑enabled tables, which cut query latency by up to 90 %, boosted data freshness by 50 %, slashed storage costs by 83 % and saved tens of thousands of GB‑hours of compute daily.

Apache IcebergData WarehouseFlink

0 likes · 19 min read

Integrating Data Lake Technologies with Data Warehouse Architecture at Xiaohongshu: Practices and Performance Optimizations

Xiaohongshu Tech REDtech

Feb 27, 2024 · Artificial Intelligence

InstantID: Zero-shot Identity-Preserving Generation in Seconds

InstantID, an open‑source tool released by Xiaohongshu in early 2024, generates multiple stylized portraits that preserve a person’s facial identity from a single reference photo in seconds, eliminating fine‑tuning, large storage needs, and multi‑image requirements while seamlessly working with popular diffusion models like Stable Diffusion 1.5 and SDXL.

AIImage GenerationInstantID

0 likes · 6 min read

InstantID: Zero-shot Identity-Preserving Generation in Seconds

Xiaohongshu Tech REDtech

Feb 9, 2024 · Artificial Intelligence

How InstantID Generates High‑Fidelity Holiday Portraits in 30 Seconds

InstantID is a plug‑in adapter that adds identity‑preserving capabilities to text‑to‑image diffusion models, allowing users to upload a single photo and, within 30 seconds, produce a Spring Festival‑styled portrait with accurate facial features, customizable prompts, and strong text control.

AI image generationDiffusion ModelsHugging Face

0 likes · 7 min read

How InstantID Generates High‑Fidelity Holiday Portraits in 30 Seconds

Xiaohongshu Tech REDtech

Jan 31, 2024 · Artificial Intelligence

Encoding‑Alignment‑Interaction (EAI) Framework for Full‑Body Human Motion Forecasting

The Encoding‑Alignment‑Interaction (EAI) framework predicts full‑body human motion—including detailed hand joints—by extracting spatio‑temporal features with DCT and GCNs, aligning heterogeneous body‑hand representations via Cross‑Context Alignment, and modeling semantic and physical interactions through Cross‑Context Interaction, achieving state‑of‑the‑art accuracy on the GRAB dataset.

EAI frameworkcomputer visioncross-context alignment

0 likes · 15 min read

Encoding‑Alignment‑Interaction (EAI) Framework for Full‑Body Human Motion Forecasting

Xiaohongshu Tech REDtech

Jan 23, 2024 · Artificial Intelligence

Controllable Mind Visual Diffusion Model (CMVDM) for Reconstructing Visual Stimuli from fMRI Signals

The Controllable Mind Visual Diffusion Model (CMVDM) decodes fMRI signals into semantic vectors and silhouette maps, feeds them into a latent diffusion framework with a ControlNet‑style encoder, and reconstructs high‑fidelity images that surpass existing baselines in both structural similarity and semantic accuracy across multiple brain‑imaging datasets.

AIbrain decodingdiffusion model

0 likes · 13 min read

Controllable Mind Visual Diffusion Model (CMVDM) for Reconstructing Visual Stimuli from fMRI Signals

Xiaohongshu Tech REDtech

Jan 20, 2024 · Artificial Intelligence

Decoding Xiaohongshu’s Recommendation System: How Ordinary Users Gain Visibility

Xiaohongshu’s recommendation system uses large‑scale multimodal embeddings, dual‑tower and graph models, and diversity techniques like DPP and SSD to quickly surface high‑quality user‑generated content, enabling ordinary users to gain visibility while balancing personalization, exploration, and efficient LLM‑augmented pipelines.

Xiaohongshucold startcontent diversity

0 likes · 15 min read

Decoding Xiaohongshu’s Recommendation System: How Ordinary Users Gain Visibility

Xiaohongshu Tech REDtech

Jan 18, 2024 · R&D Management

Beyond Coding: Engineer Self‑Iteration and Growing with the Organization

In a fast‑changing workplace, engineers must pursue self‑success, cooperation and empowerment by developing small and big T‑shaped skills, mastering clear goal‑setting, meeting structures, and the WWH perspective, while leveraging AIGC as a tool, to continuously iterate toward leadership and meaningful career growth.

Career DevelopmentEngineering ManagementT-shaped talent

0 likes · 14 min read

Beyond Coding: Engineer Self‑Iteration and Growing with the Organization

Xiaohongshu Tech REDtech

Jan 12, 2024 · Artificial Intelligence

Negative Sample Assisted Distillation for Large Language Models

The AAAI‑2024 paper introduces a Negative Sample Assisted Distillation framework—comprising Negative Assistance Training, Negative Calibration Enhancement, and Adaptive Self‑Consistency—that leverages both correct and incorrect reasoning examples to train a compact LLaMA‑7B student, achieving up to 75.75 % accuracy gains over fine‑tuning on MATH and improving out‑of‑domain benchmarks.

LLMchain-of-thoughtknowledge distillation

0 likes · 13 min read

Negative Sample Assisted Distillation for Large Language Models