BestHub
Sign in
Xiaohongshu Tech REDtech
Author

Xiaohongshu Tech REDtech

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

119
Articles
0
Likes
410
Views
0
Comments
Recent Articles

Latest from Xiaohongshu Tech REDtech

100 recent articles max
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Dec 11, 2025 · Artificial Intelligence

Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput

The article introduces a fine‑grained activation offloading technique implemented in Megatron‑Core that offloads module‑level activations to CPU, overlaps transfer with computation, and remains compatible with pipeline and virtual pipeline parallelism, dramatically reducing peak GPU memory for large language models while incurring minimal throughput loss.

LLMMegatronMemory Optimization
0 likes · 18 min read
Fine‑Grained Activation Offloading: Cutting Memory Use While Preserving LLM Throughput
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Dec 4, 2025 · Artificial Intelligence

CrossVid: A New Benchmark Reveals the Limits of Multimodal LLMs in Cross‑Video Reasoning

CrossVid is an open‑source benchmark that evaluates multimodal large language models on cross‑video reasoning tasks, providing 5,331 videos, 9,015 QA pairs, four high‑level dimensions and ten specific tasks, and exposing significant performance gaps between current models and humans.

AI evaluationcross-video reasoningmultimodal LLM
0 likes · 9 min read
CrossVid: A New Benchmark Reveals the Limits of Multimodal LLMs in Cross‑Video Reasoning
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Nov 20, 2025 · Artificial Intelligence

How DeepAgent Achieves End‑to‑End Reasoning with 16,000+ Scalable Tools

DeepAgent is a new end‑to‑end reasoning agent that unifies autonomous thinking, dynamic tool search, and execution, handling over 16,000 real APIs, supporting embodied environments and research assistance, and achieving state‑of‑the‑art results across multiple benchmarks through its unified reasoning core, memory‑folding mechanisms, structured memory, and the ToolPO training framework.

AI agentsGeneral AITool Integration
0 likes · 14 min read
How DeepAgent Achieves End‑to‑End Reasoning with 16,000+ Scalable Tools
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Nov 10, 2025 · R&D Management

How AI Is Redefining Engineering Teams: From Code Monkeys to Value Creators

In the AI‑native era, engineers spend most of their time on meetings and coordination rather than coding, prompting a shift toward networked, task‑oriented teams where AI acts as a collaborative agent, enabling smaller, high‑output groups that focus on value creation instead of mere implementation.

AITeam Collaborationengineering management
0 likes · 9 min read
How AI Is Redefining Engineering Teams: From Code Monkeys to Value Creators
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Nov 4, 2025 · Artificial Intelligence

Unveiling the Law of Capacity Gap: Boosting Language Model Distillation Efficiency

At ACL 2025, a collaborative paper introduced the Law of Capacity Gap, revealing a linear 2.5× optimal teacher‑student size relationship in language model distillation, dramatically cutting compute costs and achieving Pareto‑optimal efficiency, with the MiniMA model as a successful demonstration.

Language ModelsMiniMAartificial-intelligence
0 likes · 7 min read
Unveiling the Law of Capacity Gap: Boosting Language Model Distillation Efficiency
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Sep 22, 2025 · Big Data

How Dataverse’s Notebook Supercharges Data+AI Development at Xiaohongshu

The article details Xiaohongshu’s Dataverse platform evolution into a Data+AI system, highlighting inefficiencies in algorithm and data‑science workflows, the introduction of an interactive notebook, comprehensive data lineage, AI‑coding assistance, and future DataAgent plans to automate data engineering tasks.

AI codingData LineageData Platform
0 likes · 21 min read
How Dataverse’s Notebook Supercharges Data+AI Development at Xiaohongshu
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Sep 19, 2025 · Artificial Intelligence

FireRedTTS-2: How the New Open-Source Model Achieves Human‑Like Multi‑Speaker Dialogue Synthesis

FireRedTTS-2, the latest open‑source dialogue TTS model from Xiaohongshu’s audio team, upgrades its speech tokenizer and text‑to‑speech architecture to enable low‑latency, per‑sentence generation, robust multi‑speaker switching, and natural prosody across multiple languages, outperforming rivals in both objective and subjective tests.

AI audiodialogue synthesismultilingual
0 likes · 10 min read
FireRedTTS-2: How the New Open-Source Model Achieves Human‑Like Multi‑Speaker Dialogue Synthesis
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Aug 27, 2025 · Databases

How RedHub Revolutionizes Database Access for Billion‑User Scale

RedHub is a next‑generation database proxy built by Xiaohongshu that unifies fragmented access methods, leverages PolarDB‑X for distributed SQL execution, and delivers high‑performance, highly available, and easily observable database connectivity, enabling seamless migration and advanced features for massive‑scale workloads.

Database ProxyDistributed SQLObservability
0 likes · 15 min read
How RedHub Revolutionizes Database Access for Billion‑User Scale
Xiaohongshu Tech REDtech
Xiaohongshu Tech REDtech
Aug 19, 2025 · Artificial Intelligence

How Single Trajectory Distillation Boosts Diffusion Model Speed and Style Quality

The paper introduces Single Trajectory Distillation (STD), a novel training framework that aligns full PF‑ODE trajectories from a fixed noisy state, uses a Trajectory Bank to cut training cost, and adds an Asymmetric Adversarial Loss to markedly improve style consistency and aesthetic quality while accelerating image and video style‑transfer diffusion models.

AI accelerationStyle Transferconsistency models
0 likes · 14 min read
How Single Trajectory Distillation Boosts Diffusion Model Speed and Style Quality