Author

Data Party THU

Official platform of Tsinghua Big Data Research Center, sharing the team's latest research, teaching updates, and big data news.

368

Articles

Likes

242

Views

Comments

Latest from Data Party THU

100 recent articles max

Data Party THU

Apr 4, 2026 · Artificial Intelligence

Can a Tiny AI‑Enabled Ring Decode Your Metabolic Odor in Real Time?

A Hong Kong University of Science and Technology team has created a miniature AI‑powered wearable ring that uses a 0.0081 mm² olfactory sensor chip to non‑invasively capture skin‑emitted VOCs, identify diet and activity states, and even quantify alcohol intake, offering a new frontier for continuous health monitoring.

Artificial IntelligenceNature Communicationshealth monitoring

0 likes · 8 min read

Can a Tiny AI‑Enabled Ring Decode Your Metabolic Odor in Real Time?

Data Party THU

Apr 3, 2026 · Artificial Intelligence

Can Attention Replace Residuals? Inside the New Attention Residuals Breakthrough

The article reviews the Kimi team's Attention Residuals approach, which substitutes traditional ResNet additive shortcuts with learned attention‑based weighting, explains the theoretical motivation linking depth to time, details full‑attention and block‑wise implementations, presents experimental results showing up to 1.25× compute efficiency and improved performance on reasoning and knowledge tasks.

Residual NetworksTransformerattention mechanism

0 likes · 11 min read

Can Attention Replace Residuals? Inside the New Attention Residuals Breakthrough

Data Party THU

Apr 2, 2026 · Backend Development

9 Essential Python Libraries That Boost Production Code Efficiency

This article introduces nine practical Python libraries—glom, boltons, beartype, result, whenever, pyinstrument, dirty‑equals, stamina, and pyfunctional—that address common development pain points such as nested data handling, missing standard‑library features, runtime type safety, error handling, timezone bugs, performance profiling, robust testing, retry logic, and functional pipelines, providing production‑ready solutions with concise examples.

Code ExamplesPythonlibraries

0 likes · 16 min read

9 Essential Python Libraries That Boost Production Code Efficiency

Data Party THU

Apr 1, 2026 · Artificial Intelligence

How SwiftTailor Accelerates Realistic 3D Garment Generation

SwiftTailor introduces a two‑stage, geometry‑centric framework that unifies pattern inference and mesh synthesis, dramatically cutting inference time to seconds while achieving state‑of‑the‑art accuracy and visual realism on the Multimodal GarmentCodeData benchmark for digital fashion.

3D garment generationAISwiftTailor

0 likes · 4 min read

How SwiftTailor Accelerates Realistic 3D Garment Generation

Data Party THU

Mar 31, 2026 · Artificial Intelligence

Can Lookup-Based Memory Revolutionize Transformers? Inside the STEM Architecture

The STEM architecture replaces the Transformer feed‑forward network with a static token‑indexed embedding table, enabling lookup‑based memory that decouples capacity from compute, improves training stability, expands addressable memory, and delivers consistent performance gains on long‑context and knowledge‑intensive tasks.

Lookup MemorySTEM ArchitectureTransformer

0 likes · 8 min read

Can Lookup-Based Memory Revolutionize Transformers? Inside the STEM Architecture

Data Party THU

Mar 30, 2026 · Artificial Intelligence

Why AI Needs a ‘Harness’: Building Environments for Persistent Agents

The article analyzes the emerging concept of Harness Engineering—combining AI models with structured environments, standards, and feedback loops—to enable agents that can work continuously, illustrated by OpenAI and Anthropic case studies, practical design guidelines, and a three‑week adoption plan.

AI EngineeringAgent DesignHarness Engineering

0 likes · 10 min read

Why AI Needs a ‘Harness’: Building Environments for Persistent Agents

Data Party THU

Mar 29, 2026 · Artificial Intelligence

How LoGeR Enables Minute‑Long 3D Reconstruction with Hybrid Memory

The article presents LoGeR, a long‑context geometric reconstruction framework that combines test‑time‑training memory and sliding‑window attention to achieve minute‑scale, fully‑feedforward 3D reconstruction with superior accuracy on benchmarks such as KITTI and VBR.

3D ReconstructionHybrid MemoryLoGeR

0 likes · 11 min read

How LoGeR Enables Minute‑Long 3D Reconstruction with Hybrid Memory

Data Party THU

Mar 27, 2026 · Artificial Intelligence

When AI Steps Out of the Screen: How Looki’s Proactive Engine Turns Wearables into Real‑World Assistants

The article analyzes the limits of screen‑bound AI agents, explains how Looki’s Proactive Intelligence Engine extends OpenClaw’s capabilities into the physical world through context‑aware perception, dynamic decision‑making, and privacy‑preserving pipelines, and discusses the technical and practical challenges of building truly proactive AI.

AI Agent ArchitectureContextual IntelligenceLooki

0 likes · 11 min read

When AI Steps Out of the Screen: How Looki’s Proactive Engine Turns Wearables into Real‑World Assistants

Data Party THU

Mar 26, 2026 · Artificial Intelligence

How Mixture-of-Depths Attention Boosts Large Language Model Efficiency

This article examines the Mixture‑of‑Depths Attention (MoDA) mechanism, detailing its novel flash‑compatible KV layout, combined sequence‑depth attention, theoretical analysis, and extensive experiments that show significant reductions in validation loss and accuracy gains on downstream tasks compared to the OLMo2 baseline.

Deep KVFlashAttentionMixture-of-Depths Attention

0 likes · 9 min read

How Mixture-of-Depths Attention Boosts Large Language Model Efficiency

Data Party THU

Mar 25, 2026 · Artificial Intelligence

How Knowledge‑Guided Context Optimization Boosts Zero‑Shot Vision‑Language Models

The article analyzes the Base‑to‑New generalization problem of CLIP‑based visual‑language models, explains why standard prompt tuning (CoOp) forgets base knowledge, and presents the KgCoOp framework that adds a knowledge‑guided loss to keep learned prompts close to hand‑crafted ones, dramatically improving unseen‑class performance while preserving efficiency.

CLIPGeneralizationKnowledge-guided Optimization

0 likes · 12 min read

How Knowledge‑Guided Context Optimization Boosts Zero‑Shot Vision‑Language Models