BestHub
Sign in
Data Party THU
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
0
Likes
242
Views
0
Comments
Recent Articles

Latest from Data Party THU

100 recent articles max
Data Party THU
Data Party THU
May 31, 2026 · Artificial Intelligence

Reinforcement Learning Launches a New Paradigm for Spatial Omics Experiment Design

A reinforcement‑learning framework called SOFisher, developed by teams from Fudan and Beijing Institute of Technology, enables intelligent, adaptive selection of field‑of‑view positions in costly spatial‑omics experiments, dramatically improving target detection efficiency and revealing disease‑relevant cellular niches with far fewer measurements.

AI-driven microscopyAlzheimer's diseaseSOFisher
0 likes · 7 min read
Reinforcement Learning Launches a New Paradigm for Spatial Omics Experiment Design
Data Party THU
Data Party THU
May 31, 2026 · Artificial Intelligence

Why AI Agents Get Dumber Over Time? ICML 2026 Theory of Agent Explains

The article introduces the ICML 2026 Theory of Agent (ToA), analyzes four common failure modes of modern agents, explains the internal‑vs‑external tool trade‑off through a knowledge‑boundary framework, and outlines how effort‑conservation and the β parameter guide self‑evolving agent design and future research.

AI agentsICML 2026Theory of Agent
0 likes · 24 min read
Why AI Agents Get Dumber Over Time? ICML 2026 Theory of Agent Explains
Data Party THU
Data Party THU
May 30, 2026 · Artificial Intelligence

How USTC’s Tiny LCPO Training Cuts Large Model Overthinking in Half

The paper introduces LCPO, a lightweight preference‑optimization technique that uses only 800 training examples and 50 steps to teach large language models to produce concise, accurate answers, halving inference length while often improving accuracy and reducing training cost by up to two orders of magnitude.

Efficient InferenceLCPOLow-Resource Training
0 likes · 8 min read
How USTC’s Tiny LCPO Training Cuts Large Model Overthinking in Half
Data Party THU
Data Party THU
May 30, 2026 · Artificial Intelligence

The Most Comprehensive Survey of Agent Harness Engineering Revealed

This article summarizes the extensive “Agent Harness Engineering: A Survey” paper, detailing how moving beyond prompt engineering to a seven‑layer harness framework (ETCLOVG) is crucial for reliable, production‑grade agents, and explains benchmark gains, evaluation shifts, and the evolving competition from framework to platform.

AI agentsAgent HarnessContext Engineering
0 likes · 13 min read
The Most Comprehensive Survey of Agent Harness Engineering Revealed
Data Party THU
Data Party THU
May 29, 2026 · Artificial Intelligence

Token Superposition Training: 2.5× Faster LLM Pre‑training Without Model Changes

The article presents Token Superposition Training (TST), which temporarily averages embeddings of non‑overlapping token bags and predicts groups of tokens in a first phase before reverting to standard token‑wise prediction, achieving up to 2.5× pre‑training speedup on 10B‑1B MoE models without altering model architecture or inference.

LLM pretrainingMCE lossMixture of Experts
0 likes · 9 min read
Token Superposition Training: 2.5× Faster LLM Pre‑training Without Model Changes
Data Party THU
Data Party THU
May 28, 2026 · Artificial Intelligence

Replacing Fragile Monoliths with Multi‑Agent Networks for Stable Productivity

The article explains why single‑agent LLM pipelines are brittle for complex tasks, how mature multi‑agent toolchains enable cooperative or competitive agent designs, and provides concrete communication protocols, task‑decomposition rules, framework comparisons, code samples, and scaling considerations for building robust production AI systems.

AI orchestrationMulti-Agent Systemsagent communication
0 likes · 29 min read
Replacing Fragile Monoliths with Multi‑Agent Networks for Stable Productivity
Data Party THU
Data Party THU
May 27, 2026 · Artificial Intelligence

AI Scientific Assistants Rise: Google’s Co‑Scientist and FutureHouse’s Robin

Two groundbreaking Nature papers introduce Google DeepMind’s multi‑agent Co‑Scientist and FutureHouse’s Robin, AI systems that combine literature search, hypothesis generation, experimental design and data analysis to accelerate drug repurposing for leukemia and age‑related macular degeneration, demonstrating how AI is evolving from a tool into a collaborative scientific partner.

AIDeepMindFutureHouse
0 likes · 8 min read
AI Scientific Assistants Rise: Google’s Co‑Scientist and FutureHouse’s Robin
Data Party THU
Data Party THU
May 27, 2026 · Artificial Intelligence

How Bengio’s TBA Decouples Sampling and Learning to Speed Up LLM RL by 50×

The article explains how large‑language‑model post‑training suffers from rollout bottlenecks, introduces the Trajectory Balance with Asynchrony (TBA) framework that separates a Searcher from a Trainer, reuses off‑policy trajectories via a Trajectory Balance objective, and demonstrates up to 50× speed‑ups while preserving or improving performance on math reasoning, preference fine‑tuning, and automated red‑team tasks.

Asynchronous TrainingLLMLarge Models
0 likes · 9 min read
How Bengio’s TBA Decouples Sampling and Learning to Speed Up LLM RL by 50×
Data Party THU
Data Party THU
May 26, 2026 · Artificial Intelligence

Time-Series Forecasting Augmentation: Frequency, Decomposition, and Patch Methods Compared

The article examines the challenges of augmenting time-series forecasting, reviews mainstream techniques—including frequency-domain, decomposition, and patch-based methods—and demonstrates through extensive experiments that Temporal Patch Shuffle (TPS) consistently achieves superior performance across long-term, short-term, and classification tasks.

Temporal Patch Shuffledata augmentationfrequency domain
0 likes · 20 min read
Time-Series Forecasting Augmentation: Frequency, Decomposition, and Patch Methods Compared