Publications (16)
lmgame-Bench: How Good are LLMs at Playing Games?
Lanxiang Hu, Mingjia Huo, Yuxuan Zhang +6
Playing video games requires perception, memory, and planning, exactly the faculties modern large language model (LLM) agents are expected to master. We study the major challenges…
Design-based theory for causal inference
Xin Lu, Wanjia Fu, Hongzi Li +4
Causal inference, as a major research area in statistics and data science, plays a central role across diverse fields such as medicine, economics, education, and the social science…
General Modular Harness for LLM Agents in Multi-Turn Gaming Environments
Yuxuan Zhang, Haoyang Yu, Lanxiang Hu +2
We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum…
Light-YOLOv8-Flame: A Lightweight High-Performance Flame Detection Algorithm
Jiawei Lan, Ye Tao, Zhibiao Wang +2
Fire detection algorithms, particularly those based on computer vision, encounter significant challenges such as high computational costs and delayed response times, which hinder t…
Multitask Learning for Citation Purpose Classification
Alex Oesterling, Angikar Ghosal, Haoyang Yu +4
We present our entry into the 2021 3C Shared Task Citation Context Classification based on Purpose competition. The goal of the competition is to classify a citation in a scientifi…
Nonlinear MPC for Quadrotors in Close-Proximity Flight with Neural Network Downwash Prediction
Jinjie Li, Liang Han, Haoyang Yu +3
Swarm aerial robots are required to maintain close proximity to successfully traverse narrow areas in cluttered environments. However, this movement is affected by the downwash eff…
Potato: A Data-Oriented Programming 3D Simulator for Large-Scale Heterogeneous Swarm Robotics
Jinjie Li, Liang Han, Haoyang Yu +4
Large-scale simulation with realistic nonlinear dynamic models is crucial for algorithms development for swarm robotics. However, existing platforms are mainly developed based on O…
Using Low-rank Representation of Abundance Maps and Nonnegative Tensor Factorization for Hyperspectral Nonlinear Unmixing
Lianru Gao, Zhicheng Wang, Lina Zhuang +3
Tensor-based methods have been widely studied to attack inverse problems in hyperspectral imaging since a hyperspectral image (HSI) cube can be naturally represented as a third-ord…
Design-based edge-level causal inference with machine learning assisted covariate adjustment
Haoyang Yu, Yilin Li, Lu Deng +3
We study design-based causal inference for edge-level outcomes in directed networks under dyadic interference. In this setting, outcomes are defined on directed edges and depend on…
Benchmarking Scientific Understanding and Reasoning for Video Generation using VideoScience-Bench
Lanxiang Hu, Abhilash Shankarampeta, Yixin Huang +7
The next frontier for video generation lies in developing models capable of zero-shot reasoning, where understanding real-world scientific laws is crucial for accurate physical out…
Combining Priors with Experience: Confidence Calibration Based on Binomial Process Modeling
Jinzong Dong, Zhaohui Jiang, Dong Pan +1
Confidence calibration of classification models is a technique to estimate the true posterior probability of the predicted class, which is critical for ensuring reliable decision-m…
Sharp variance estimator and causal bootstrap in stratified randomized experiments
Haoyang Yu, Ke Zhu, Hanzhong Liu
Randomized experiments are the gold standard for estimating treatment effects, and randomization serves as a reasoned basis for inference. In widely used stratified randomized expe…
Construction of Nahm data and BPS monopoles with continuous symmetries
Benoit Charbonneau, Anuk Dayaprema, C. J. Lang +2
We study solutions to Nahm's equations with continuous symmetries and, under certain (mild) hypotheses, we classify the corresponding Ansätze. Using our classification, we constru…
Bitcoin Gold, Litecoin Silver:An Introduction to Cryptocurrency's Valuation and Trading Strategy
Haoyang Yu, Yutong Sun, Yulin Liu +1
Historically, gold and silver have played distinct roles in traditional monetary systems. While gold has primarily been revered as a superior store of value, prompting individuals…
Minimax Optimal Design with Spillover and Carryover Effects
Haoyang Yu, Wei Ma, Hanzhong Liu
In various applications, the potential outcome of a unit may be influenced by the treatments received by other units, a phenomenon known as interference, as well as by prior treatm…
Confused Modulo Projection based Somewhat Homomorphic Encryption -- Cryptosystem, Library and Applications on Secure Smart Cities
Xin Jin, Hongyu Zhang, Xiaodong Li +5
With the development of cloud computing, the storage and processing of massive visual media data has gradually transferred to the cloud server. For example, if the intelligent vide…