Publications (41)
Statistical Guarantees for Lifelong Reinforcement Learning using PAC-Bayes Theory
Zhi Zhang, Chris Chow, Yasi Zhang +7
Lifelong reinforcement learning (RL) has been developed as a paradigm for extending single-task RL to more realistic, dynamic settings. In lifelong RL, the "life" of an RL agent is…
Regret-Optimal Q-Learning with Low Cost for Single-Agent and Federated Reinforcement Learning
Haochen Zhang, Zhong Zheng, Lingzhou Xue
Motivated by real-world settings where data collection and policy deployment -- whether for a single agent or across multiple agents -- are costly, we study the problem of on-polic…
Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight Framework
Masafumi Enomoto, Ryoma Obara, Haochen Zhang +1
HTML observations in LLM-based web agents are extremely long, and while many reduction methods have been proposed, it remains unclear which methods reduce overall agent latency whi…
Gap-Dependent Bounds for Q-Learning using Reference-Advantage Decomposition
Zhong Zheng, Haochen Zhang, Lingzhou Xue
We study the gap-dependent bounds of two important algorithms for on-policy Q-learning for finite-horizon episodic tabular Markov Decision Processes (MDPs): UCB-Advantage (Zhang et…
VLA-3D: A Dataset for 3D Semantic Scene Understanding and Navigation
Haochen Zhang, Nader Zantout, Pujith Kachana +3
With the recent rise of Large Language Models (LLMs), Vision-Language Models (VLMs), and other general foundation models, there is growing potential for multimodal, multi-task embo…
Computational Pathology: A Survey Review and The Way Forward
Mahdi S. Hosseini, Babak Ehteshami Bejnordi, Vincent Quoc-Huy Trinh +18
Computational Pathology CPath is an interdisciplinary science that augments developments of computational approaches to analyze and model medical histopathology images. The main ob…
CoVE: Compressed Vocabulary Expansion Makes Better LLM-based Recommender Systems
Haochen Zhang, Tianyi Zhang, Junze Yin +3
Recommender systems play a pivotal role in providing relevant content to users. With the rapid development of large language models (LLMs), researchers have begun utilizing LLMs to…
On The Classification-Distortion-Perception Tradeoff
Dong Liu, Haochen Zhang, Zhiwei Xiong
Signal degradation is ubiquitous and computational restoration of degraded signal has been investigated for many years. Recently, it is reported that the capability of signal resto…
Jellyfish: A Large Language Model for Data Preprocessing
Haochen Zhang, Yuyang Dong, Chuan Xiao +1
This paper explores the utilization of LLMs for data preprocessing (DP), a crucial step in the data mining pipeline that transforms raw data into a clean format conducive to easy p…
SQL-RewriteBench: A Correctness-Gated, Full-Denominator Benchmark for Statement-Level SQL Rewriting [Experiment,Analysis & Benchmark]
Jiang Long, Tianci Gao, Shiyuan Hao +3
Statement-level SQL rewriting can improve query performance and maintainability without changing the DBMS kernel, but existing benchmarks do not evaluate rewrite methods as deploya…
FAST-EQA: Efficient Embodied Question Answering with Global and Local Region Relevancy
Haochen Zhang, Nirav Savaliya, Faizan Siddiqui +1
Embodied Question Answering (EQA) combines visual scene understanding, goal-directed exploration, spatial and temporal reasoning under partial observability. A central challenge is…
Gap-Dependent Bounds for Federated -learning
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We present the first gap-dependent analysis of regret and communication cost for on-policy federated -Learning in tabular episodic finite-horizon Markov decision processes (MDPs…
cotomi Act: Learning to Automate Work by Watching You
Masafumi Oyamada, Kunihiro Takeoka, Kosuke Akimoto +5
What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines reliable multi-step task execu…
Gap-Dependent Bounds for Nearly Minimax Optimal Reinforcement Learning with Linear Function Approximation
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We study gap-dependent performance guarantees for nearly minimax-optimal algorithms in reinforcement learning with linear function approximation. While prior works have established…
Ultrafast spin dynamics in the proximate quantum spin liquid α-RuCl3
Haochen Zhang, Subin Kim, Young-June Kim +2
α-RuCl3 is a Kitaev material suggested to be a proximate quantum spin liquid in a certain temperature and magnetic field range. Nonequilibrium measurements of transient dynamics h…
CFT from TQFT via Holographic Tensor Network, and Precision Discretisation of CFT
Lin Chen, Haochen Zhang, Kaixin Ji +4
We show that the path-integral of conformal field theories in dimensions (CFT) can be constructed by solving for eigenstates of an RG operator following from the Turaev-Vir…
Is There Tradeoff between Spatial and Temporal in Video Super-Resolution?
Haochen Zhang, Dong Liu, Zhiwei Xiong
Recent advances of deep learning lead to great success of image and video super-resolution (SR) methods that are based on convolutional neural networks (CNN). For video SR, advance…
Support Basis: Fast Attention Beyond Bounded Entries
Maryam Aliakbarpour, Vladimir Braverman, Junze Yin +1
Large language models (LLMs) have demonstrated remarkable performance across a wide range of tasks. However, the quadratic complexity of softmax attention remains a central bottlen…
Revealing unusual bandgap shifts with temperature and bandgap renormalization effect in phase-stabilized metal halide perovskite thin films
Haochen Zhang, Zhixuan Bi, Zehua Zhai +11
Hybrid organic-inorganic metal halide perovskites are emerging materials in photovoltaics, whose bandgap is one of the most crucial parameters governing their light harvesting perf…
Breaking the Frozen Subspace: Importance Sampling for Low-Rank Optimization in LLM Pretraining
Haochen Zhang, Junze Yin, Guanchu Wang +5
Low-rank optimization has emerged as a promising approach to enabling memory-efficient training of large language models (LLMs). Existing low-rank optimization methods typically pr…
Resilient Distribution System Restoration with Communication Recovery by Drone Small Cells
Haochen Zhang, Chen Chen, Shunbo Lei +1
Distribution system (DS) restoration after natural disasters often faces the challenge of communication failures to feeder automation (FA) facilities, resulting in prolonged load p…
High-Precision Temperature Estimation Based on Magnetic Nanoparticles Dominated by Brownian Relaxation under Combined AC and DC Magnetic Fields
Zhongzhou Du, Wenze Zhang, Yi Sun +10
Brownian relaxation is one of the primary mechanisms that allows magnetic nanoparticles (MNPs) to convert magnetic energy into thermal energy under an excitation magnetic field. Ac…
Large Language Models as Data Preprocessors
Haochen Zhang, Yuyang Dong, Chuan Xiao +1
Large Language Models (LLMs), typified by OpenAI's GPT, have marked a significant advancement in artificial intelligence. Trained on vast amounts of text data, LLMs are capable of…
Q-Learning with Fine-Grained Gap-Dependent Regret
Haochen Zhang, Zhong Zheng, Lingzhou Xue
We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in episodic tabular Markov Decision Processes. Existing model-free algorithms achieve minima…
Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost
Zhong Zheng, Haochen Zhang, Lingzhou Xue
In this paper, we consider model-free federated reinforcement learning for tabular episodic Markov decision processes. Under the coordination of a central server, multiple agents c…
Topology-Preserving Image Segmentation with Spatial-Aware Persistent Feature Matching
Bo Wen, Haochen Zhang, Dirk-Uwe G. Bartsch +3
Topological correctness is critical for segmentation of tubular structures, which pervade in biomedical images. Existing topological segmentation loss functions are primarily based…
Legendre Memory Unit with A Multi-Slice Compensation Model for Short-Term Wind Speed Forecasting Based on Wind Farm Cluster Data
Mumin Zhang, Haochen Zhang, Xin Zhi Khoo +4
With more wind farms clustered for integration, the short-term wind speed prediction of such wind farm clusters is critical for normal operation of power systems. This paper focuse…
Intrinsic exciton transport and recombination in single-crystal lead bromide perovskite
Zhixuan Bi, Yunfei Bai, Ying Shi +13
Photogenerated carrier transport and recombination in metal halide perovskites are critical to device performance. Despite considerable efforts, sample quality issues and measureme…
Adaptive Liquidity Provision in Uniswap V3 with Deep Reinforcement Learning
Haochen Zhang, Xi Chen, Lin F. Yang
Decentralized exchanges (DEXs) are a cornerstone of decentralized finance (DeFi), allowing users to trade cryptocurrencies without the need for third-party authorization. Investors…
Zero-Shot Transfer Capabilities of the Sundial Foundation Model for Leaf Area Index Forecasting
Peining Zhang, Hongchen Qin, Haochen Zhang +3
This work investigates the zero-shot forecasting capability of time series foundation models for Leaf Area Index (LAI) forecasting in agricultural monitoring. Using the HiQ dataset…
SORT3D: Spatial Object-centric Reasoning Toolbox for Zero-Shot 3D Grounding Using Large Language Models
Nader Zantout, Haochen Zhang, Pujith Kachana +4
Interpreting object-referential language and grounding objects in 3D with spatial relations and attributes is essential for robots operating alongside humans. However, this task is…
Learning by Passing Tests, with Application to Neural Architecture Search
Xuefeng Du, Haochen Zhang, Pengtao Xie
Learning through tests is a broadly used methodology in human learning and shows great effectiveness in improving learning outcome: a sequence of tests are made with increasing lev…
Flatness Preserves Instruction Following in Vision-Language-Action Models
Haochen Zhang, Yonatan Bisk
Vision-language-action (VLA) models have the potential for open-world generalization by leveraging pretrained vision-language representations, yet downstream finetuning on limited…
IRef-VLA: A Benchmark for Interactive Referential Grounding with Imperfect Language in 3D Scenes
Haochen Zhang, Nader Zantout, Pujith Kachana +2
With the recent rise of large language models, vision-language models, and other general foundation models, there is growing potential for multimodal, multi-task robotics that can…
Two-Stream Action Recognition-Oriented Video Super-Resolution
Haochen Zhang, Dong Liu, Zhiwei Xiong
We study the video super-resolution (SR) problem for facilitating video analytics tasks, e.g. action recognition, instead of for visual quality. The popular action recognition meth…
Non-Markov Multi-Round Conversational Image Generation with History-Conditioned MLLMs
Haochen Zhang, Animesh Sinha, Felix Juefei-Xu +8
Conversational image generation requires a model to follow user instructions across multiple rounds of interaction, grounded in interleaved text and images that accumulate as chat…
Spin Coherence and Spin Relaxation in Hybrid Organic-Inorganic Lead and Mixed Lead-Tin Perovskites
Haochen Zhang, Zehua Zhai, Zhixuan Bi +5
Metal halide perovskites make up a promising class of materials for semiconductor spintronics. Here we report a systematic investigation of coherent spin precession, spin dephasing…
A Novel Estimation Method for Temperature of Magnetic Nanoparticles Dominated by Brownian Relaxation Based on Magnetic Particle Spectroscopy
Zhongzhou Du, Gaoli Zhao, Zhanpeng Hua +9
This paper presents a novel method for estimating the temperature of magnetic nanoparticles (MNPs) based on AC magnetization harmonics of MNPs dominated by Brownian relaxation. The…
Characterization of GaN-based HEMTs Down to 4.2 K for Cryogenic Applications
Bolun Zeng, Haochen Zhang, Zikun Xiang +9
The cryogenic performance of GaN-based HEMTs (high-electron-mobility transistors) is systematically investigated by the direct current (DC) and low-frequency noise (LFN) characteri…
Read More, Think More: Revisiting Observation Reduction for Web Agents
Masafumi Enomoto, Ryoma Obara, Haochen Zhang +1
Web agents based on large language models (LLMs) rely on observations of web pages -- commonly represented as HTML -- as the basis for identifying available actions and planning su…
Inductive Generalization for Robotic Manipulation
Annabella Macaluso, Haochen Zhang, Ishaan Masilamony +2
Understanding the generalization capabilities of visuomotor policies is essential in the development of capable robotic agents. Generalizable models learn structures that transfer…