Xiu Li

A Parallel GPU-Based Approach to Clustering Very Fast Data Streams

2015

Clustering data streams has become a hot topic in the era of big data. Driven by the ever increasing volume, velocity and variety of data, more efficient algorithms for clustering large-scale complex data streams are …

Bibliometric Analysis on the Resource Rooms for Learning in Regular Class in Our Country in the Recent Twenty Years

2017

Bibliometric analysis is applied to review the research results of resource room for learning in regular class of our country from 1999 to 2016. The results reveal: although the amount of research literature on resource …

MHER: Model-based Hindsight Experience Replay

2021 · arXiv (Cornell University)

Solving multi-goal reinforcement learning (RL) problems with sparse rewards is generally challenging. Existing approaches have utilized goal relabeling on collected experiences to alleviate issues raised from sparse rewards. However, these methods are still limited in …

Double Check Your State Before Trusting It: Confidence-Aware Bidirectional Offline Model-Based Imagination

2022 · arXiv (Cornell University)

The learned policy of model-free offline reinforcement learning (RL) methods is often constrained to stay within the support of datasets to avoid possible dangerous out-of-distribution actions or states, making it challenging to handle out-of-support region. …

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

2023 · arXiv (Cornell University)

This paper aims to efficiently enable Large Language Models (LLMs) to use multimodal tools. Advanced proprietary LLMs, such as ChatGPT and GPT-4, have shown great potential for tool usage through sophisticated prompt engineering. Nevertheless, these …

Evaluating Embeddings from Pre-Trained Language Models and Knowledge Graphs for Educational Content Recommendation

2023 · Future Internet

Educational content recommendation is a cornerstone of AI-enhanced learning. In particular, to facilitate navigating the diverse learning resources available on learning platforms, methods are needed for automatically linking learning materials, e.g., in order to recommend …

Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective

2025

World models have recently attracted growing interest in Multi-Agent Reinforcement Learning (MARL) due to their ability to improve sample efficiency for policy learning. However, accurately modeling environments in MARL is challenging due to the exponentially …

Ultra-efficient physical field computing by complex-valued network quantization

2026 · Nature Communications

Neural network quantization is an established technique for compressing real-valued models, but its application to complex-valued networks-essential in electromagnetics, acoustics, and quantum physics-remains underdeveloped. Conventional quantization methods treat real and imaginary components as independent channels, …