Author name cluster

Zihao Zhou

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

AAAI Conference 2026 Conference Paper

BIQ: Bisection Interval Quantization for Communication-efficient Federated Learning

Luyang Gai
Shusen Yang
Xuebin Ren
Zihao Zhou

Quantization is a pivotal technique for enhancing communication efficiency in Federated Learning (FL). Traditional quantization methods often set uniform intervals, may fail to adequately characterize non-uniform data distributions, thus leading to substantial estimation errors and degrated model performance. Non-uniform quantization can better solve the problem. However, when applied to FL, it would bring additional communication overheads for the alignment of parameter distributions among distributed models. To address this issue, we propose Bisection Interval Quantization (BIQ), a novel non-uniform quantization framework for FL with great communication efficiency. In particular, BIQ works by optimizing the interval selection through recursive bisection among distributed clients without extra parameter communication. For scenarios involving amounts of boundary inputs, we further design Weighted Bisection Interval Quantization (WBIQ), which incorporates maximum likelihood estimation to refine boundary value reconstruction to enhance the estimation quality of boundary inputs. Our theoretical analysis rigorously establishes, for the first time under biased quantization conditions, that both BIQ and WBIQ achieve tighter error bounds and enhanced stability. Extensive experiments validate that both BIQ and WBIQ significantly accelerate the convergence of FL model training when compared to the state-of-the-art quantizers under both convex and non-convex settings.

PDF Details DOI

YNIMG Journal 2026 Journal Article

Dual neural mechanisms of sustained response inhibition: Right-lateralized core control and left-lateralized adaptive support

Liyue Lin
Jiahe Sun
Wei Xiong
Jiayi Zhao
Yishu Chen
Min Li
Xi Li
Ruyan Jiao

Sustained inhibition is critical for adaptive behavioral control in complex environments, yet its neural underpinnings remain poorly understood. Using a sequence-selective stop-signal task, we hypothesized that increasing stop-signal delay (SSD) would elicit distinct behavioral dynamics and recruit dissociable neural systems supporting different stages of sustained inhibition. fMRI data from 26 participants across three SSD conditions (no-, short-, and long-delay), combined with an activation likelihood estimation (ALE) meta-analysis of 64 classical stop-signal studies, enabled us to contrast sustained and transient inhibition. Key behavioral results revealed a systematic decrease in response time (RT) with increasing SSD, while inhibition execution time (IT/ET) followed an inverted U-shaped pattern. Neuroimaging findings demonstrated that sustained inhibition engages a significantly broader bilateral network compared to transient inhibition, spanning prefrontal, parietal, and subcortical regions. Further analyses revealed a dual-mechanism inhibitory network in which early go-stop competition recruited bilateral inhibitory regions, with the left hemisphere providing complementary support, whereas late-stage emergency stopping relied primarily on a right-dominant prefrontal pathway. Together, these findings establish sustained inhibition as a distinct and dynamically organized control process, providing a novel framework for understanding how the brain flexibly regulates behavior under evolving temporal demands.

Details DOI

ICLR Conference 2025 Conference Paper

Can LLMs Understand Time Series Anomalies?

Zihao Zhou
Rose Yu

Large Language Models (LLMs) have gained popularity in time series forecasting, but their potential for anomaly detection remains largely unexplored. Our study investigates whether LLMs can understand and detect anomalies in time series data, focusing on zero-shot and few-shot scenarios. Inspired by conjectures about LLMs' behavior from time series forecasting research, we formulate key hypotheses about LLMs' capabilities in time series anomaly detection. We design and conduct principled experiments to test each of these hypotheses. Our investigation reveals several surprising findings about LLMs for time series: (1) LLMs understand time series better as *images* rather than as text, (2) LLMs do not demonstrate enhanced performance when prompted to engage in *explicit reasoning* about time series analysis. (3) Contrary to common beliefs, LLMs' understanding of time series *do not* stem from their repetition biases or arithmetic abilities. (4) LLMs' behaviors and performance in time series analysis *vary significantly* across different models. This study provides the first comprehensive analysis of contemporary LLM capabilities in time series anomaly detection. Our results suggest that while LLMs can understand trivial time series anomalies (we have no evidence that they can understand more subtle real-world anomalies), many common conjectures based on their reasoning capabilities do not hold. All synthetic dataset generators, final prompts, and evaluation scripts have been made available in https://github.com/rose-stl-lab/anomllm.

Details

NeurIPS Conference 2025 Conference Paper

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?

Yijie Hu
Zihao Zhou
Kaizhu Huang
Xiaowei Huang
Qiufeng Wang

Math reasoning has been one crucial ability of large language models (LLMs), where significant advancements have been achieved in recent years. However, most efforts focus on LLMs by curating high-quality annotation data and intricate training (or inference) paradigms, while the math reasoning performance of multi-modal LLMs (MLLMs) remains lagging behind. Since the MLLM typically consists of an LLM and vision block, we wonder: \textit{Can MLLMs directly absorb math reasoning abilities from off-the-shelf math LLMs without tuning? } Recent model-merging approaches may offer insights into this question. However, they overlook the alignment between the MLLM and LLM, where we find that there is a large gap between their parameter spaces, resulting in lower performance. Our empirical evidence reveals two key factors behind this issue: the identification of crucial reasoning-associated layers in the model and the mitigation of the gaps in parameter space. Based on the empirical insights, we propose \textbf{IP-Merging} that first \textbf{I}dentifies the reasoning-associated parameters in both MLLM and Math LLM, then \textbf{P}rojects them into the subspace of MLLM aiming to maintain the alignment, finally merges parameters in this subspace. IP-Merging is a tuning-free approach since parameters are directly adjusted. Extensive experiments demonstrate that our IP-Merging method can enhance the math reasoning ability of MLLMs directly from Math LLMs without compromising their other capabilities.

PDF Details

AAAI Conference 2025 Conference Paper

GNS: Solving Plane Geometry Problems by Neural-Symbolic Reasoning with Multi-Modal LLMs

Maizhen Ning
Zihao Zhou
Qiufeng Wang
Xiaowei Huang
Kaizhu Huang

With the outstanding capabilities of Large Language Models (LLMs), solving math word problems (MWP) has greatly progressed, achieving higher performance on several benchmark datasets. However, it is more challenging to solve plane geometry problems (PGPs) due to the necessity of understanding, reasoning and computation on two modality data including both geometry diagrams and textual questions, where Multi-Modal Large Language Models (MLLMs) have not been extensively explored. Previous works simply regarded a plane geometry problem as multi-modal QA task, which ignored the importance of explicit parsing geometric elements from problems. To tackle this limitation, we propose to solve plane Geometry problems by Neural-Symbolic reasoning with MLLMs (GNS). We first leverage an MLLM to understand PGPs through knowledge prediction and symbolic parsing, next perform mathematical reasoning to obtain solutions, last adopt a symbolic solver to compute answers. Correspondingly, we introduce the largest PGPs dataset GNS-260K with multiple annotations including symbolic parsing, understanding, reasoning and computation. In experiments, our Phi3-Vision-based MLLM wins the first place on the PGPs solving task of MathVista benchmark, outperforming GPT-4o, Gemini Ultra and other much larger MLLMs. While LLaVA-13B-based MLLM markedly exceeded other close-source and open-source MLLMs on the MathVerse benchmark and also achieved the new SOTA on GeoQA dataset.

PDF Details DOI

ICLR Conference 2025 Conference Paper

Is Your Model Really A Good Math Reasoner? Evaluating Mathematical Reasoning with Checklist

Zihao Zhou
Shudong Liu 0004
Maizhen Ning
Wei Liu 0131
Jindong Wang 0001
Derek F. Wong
Xiaowei Huang 0001
Qiufeng Wang 0001

Exceptional mathematical reasoning ability is one of the key features that demonstrate the power of large language models (LLMs). How to comprehensively define and evaluate the mathematical abilities of LLMs, and even reflect the user experience in real-world scenarios, has emerged as a critical issue. Current benchmarks predominantly concentrate on problem-solving capabilities, presenting a substantial risk of model overfitting and fails to accurately measure the genuine mathematical reasoning abilities. In this paper, we argue that if a model really understands a problem, it should be robustly and readily applied across a diverse array of tasks. To this end, we introduce MathCheck, a well-designed checklist for testing task generalization and reasoning robustness, as well as an automatic tool to generate checklists efficiently. MathCheck includes multiple mathematical reasoning tasks and robustness tests to facilitate a comprehensive evaluation of both mathematical reasoning ability and behavior testing. Utilizing MathCheck, we develop MathCheck-GSM and MathCheck-GEO to assess mathematical textual reasoning and multi-modal reasoning capabilities, respectively, serving as upgraded versions of benchmarks including GSM8k, GeoQA, UniGeo, and Geometry3K. We adopt MathCheck-GSM and MathCheck-GEO to evaluate over 26 LLMs and 17 multi-modal LLMs, assessing their comprehensive mathematical reasoning abilities. Our results demonstrate that while frontier LLMs like GPT-4o continue to excel in various abilities on the checklist, many other model families exhibit a significant decline. Further experiments indicate that, compared to traditional math benchmarks, MathCheck better reflects true mathematical abilities and represents mathematical intelligence more linearly, thereby supporting our design. Using MathCheck, we can also efficiently conduct informative behavior analysis to deeply investigate models. Finally, we show that our proposed checklist paradigm can easily extend to other reasoning tasks for their comprehensive evaluation.

Details

JBHI Journal 2025 Journal Article

Multi-Perturbation Consistency Learning for Semi-Supervised Medical Image Segmentation

Zhiyuan Zhang
Yu Zhang
Jing Chen
Wenlong Feng
Zihao Zhou
Jie Zou
Uzair Aslam Bhatti
Gang Wang

Existing semi-supervised learning (SSL) methods primarily rely on consistency learning to enhance model performance. However, most current approaches only validate the effectiveness of consistency learning under single perturbations, while introducing multiple perturbations may lead to the failure of consistency learning and degrade model performance. To address this issue and effectively leverage multiple perturbations for consistency learning, we propose a semi-supervised medical image segmentation method based on multi-perturbation consistency learning. Specifically, we design a cross-teaching framework integrating sparsely annotated 3D and 2D networks, introducing network perturbations through multidimensional architectures while combining strong and weak data augmentation techniques to achieve input perturbations. Furthermore, to address the instability issue in multi-perturbation consistency learning, we develop two complementary uncertainty-aware correction algorithm targeting labeled and unlabeled data. These designs effectively enhance the model's robustness to both labeled and unlabeled data, overcoming the instability problem in multi-perturbation consistency learning. To validate the proposed method, we conducted experiments on four datasets(ProstateX, HPH55, ACDC, and LA). Experimental results demonstrate that our algorithm outperforms existing methods across all validation datasets and exhibits strong generalization capabilities. This indicates that our approach can maintain excellent performance with limited annotated data while achieving efficient medical image segmentation. The project code will be made publicly available upon acceptance.

Details DOI

RLJ Journal 2024 Journal Article

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

Bin Hu
Chenyang Zhao
Pu Zhang
Zihao Zhou
Yuanhang Yang
Zenglin Xu
Bin Liu

Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. However, interactions with LLMs can be time-consuming. In many practical scenarios, it requires a significant amount of storage space that can only be deployed on remote cloud servers. Additionally, using commercial LLMs can be costly since they may charge based on usage frequency. In this paper, we explore how to enable intelligent cost-effective interactions between a down stream task oriented agent and an LLM. We find that this problem can be naturally formulated by a Markov decision process (MDP), and propose When2Ask, a reinforcement learning based approach that learns when it is necessary to query LLMs for high-level instructions to accomplish a target task. On one side, When2Ask discourages unnecessary redundant interactions, while on the other side, it enables the agent to identify and follow useful instructions from the LLM. This enables the agent to halt an ongoing plan and transition to a more suitable one based on new environmental observations. Experiments on MiniGrid and Habitat environments that entail planning sub-goals demonstrate that When2Ask learns to solve target tasks with only a few necessary interactions with the LLM, significantly reducing interaction costs in testing environments compared with baseline methods. Our code is available at: https://github.com/ZJLAB-AMMI/LLM4RL.

PDF Details

RLC Conference 2024 Conference Paper

Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach

Bin Hu
Chenyang Zhao
Pu Zhang
Zihao Zhou
Yuanhang Yang
Zenglin Xu
Bin Liu

PDF Details

IJCAI Conference 2024 Conference Paper

Large Language Model as a Policy Teacher for Training Reinforcement Learning Agents

Zihao Zhou
Bin Hu
Chenyang Zhao
Pu Zhang
Bin Liu

Recent studies have uncovered the potential of Large Language Models (LLMs) in addressing complex sequential decision-making tasks through the provision of high-level instructions. However, LLM-based agents lack specialization in tackling specific target problems, particularly in real-time dynamic environments. Additionally, deploying an LLM-based agent in practical scenarios can be both costly and time-consuming. On the other hand, reinforcement learning (RL) approaches train agents that specialize in the target task but often suffer from low sampling efficiency and high exploration costs. In this paper, we introduce a novel framework that addresses these challenges by training a smaller, specialized student RL agent using instructions from an LLM-based teacher agent. By incorporating the guidance from the teacher agent, the student agent can distill the prior knowledge of the LLM into its own model. Consequently, the student agent can be trained with significantly less data. Moreover, through further training with environment feedback, the student agent surpasses the capabilities of its teacher for completing the target task. We conducted experiments on challenging MiniGrid and Habitat environments, specifically designed for embodied AI research, to evaluate the effectiveness of our framework. The results clearly demonstrate that our approach achieves superior performance compared to strong baseline methods. Our code is available at https: //github. com/ZJLAB-AMMI/LLM4Teach.

PDF Details DOI

AAAI Conference 2024 Conference Paper

MathAttack: Attacking Large Language Models towards Math Solving Ability

Zihao Zhou
Qiufeng Wang
Mingyu Jin
Jie Yao
Jianan Ye
Wei Liu
Wei Wang
Xiaowei Huang

With the boom of Large Language Models (LLMs), the research of solving Math Word Problem (MWP) has recently made great progress. However, there are few studies to examine the robustness of LLMs in math solving ability. Instead of attacking prompts in the use of LLMs, we propose a MathAttack model to attack MWP samples which are closer to the essence of robustness in solving math problems. Compared to traditional text adversarial attack, it is essential to preserve the mathematical logic of original MWPs during the attacking. To this end, we propose logical entity recognition to identify logical entries which are then frozen. Subsequently, the remaining text are attacked by adopting a word-level attacker. Furthermore, we propose a new dataset RobustMath to evaluate the robustness of LLMs in math solving ability. Extensive experiments on our RobustMath and two another math benchmark datasets GSM8K and MultiAirth show that MathAttack could effectively attack the math solving ability of LLMs. In the experiments, we observe that (1) Our adversarial samples from higher-accuracy LLMs are also effective for attacking LLMs with lower accuracy (e.g., transfer from larger to smaller-size LLMs, or from few-shot to zero-shot prompts); (2) Complex MWPs (such as more solving steps, longer text, more numbers) are more vulnerable to attack; (3) We can improve the robustness of LLMs by using our adversarial samples in few-shot prompts. Finally, we hope our practice and observation can serve as an important attempt towards enhancing the robustness of LLMs in math solving ability. The code and dataset is available at: https://github.com/zhouzihao501/MathAttack.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Automatic Integration for Spatiotemporal Neural Point Processes

Zihao Zhou
Rose Yu

Learning continuous-time point processes is essential to many discrete event forecasting tasks. However, integration poses a major challenge, particularly for spatiotemporal point processes (STPPs), as it involves calculating the likelihood through triple integrals over space and time. Existing methods for integrating STPP either assume a parametric form of the intensity function, which lacks flexibility; or approximating the intensity with Monte Carlo sampling, which introduces numerical errors. Recent work by Omi et al. proposes a dual network approach for efficient integration of flexible intensity function. However, their method only focuses on the 1D temporal point process. In this paper, we introduce a novel paradigm: Auto-STPP (Automatic Integration for Spatiotemporal Neural Point Processes) that extends the dual network approach to 3D STPP. While previous work provides a foundation, its direct extension overly restricts the intensity function and leads to computational challenges. In response, we introduce a decomposable parametrization for the integral network using ProdNet. This approach, leveraging the product of simplified univariate graphs, effectively sidesteps the computational complexities inherent in multivariate computational graphs. We prove the consistency of Auto-STPP and validate it on synthetic data and benchmark real-world datasets. Auto-STPP shows a significant advantage in recovering complex intensity functions from irregular spatiotemporal events, particularly when the intensity is sharply localized. Our code is open-source at https: //github. com/Rose-STL-Lab/AutoSTPP.

PDF Details

NeurIPS Conference 2023 Conference Paper

WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding

Yanchao Tan
Zihao Zhou
Hang Lv
Weiming Liu
Carl Yang

Graphs are widely used to model interconnected entities and improve downstream predictions in various real-world applications. However, real-world graphs nowadays are often associated with complex attributes on multiple types of nodes and even links that are hard to model uniformly, while the widely used graph neural networks (GNNs) often require sufficient training toward specific downstream predictions to achieve strong performance. In this work, we take a fundamentally different approach than GNNs, to simultaneously achieve deep joint modeling of complex attributes and flexible structures of real-world graphs and obtain unsupervised generic graph representations that are not limited to specific downstream predictions. Our framework, built on a natural integration of language models (LMs) and random walks (RWs), is straightforward, powerful and data-efficient. Specifically, we first perform attributed RWs on the graph and design an automated program to compose roughly meaningful textual sequences directly from the attributed RWs; then we fine-tune an LM using the RW-based textual sequences and extract embedding vectors from the LM, which encapsulates both attribute semantics and graph structures. In our experiments, we evaluate the learned node embeddings towards different downstream prediction tasks on multiple real-world attributed graph datasets and observe significant improvements over a comprehensive set of state-of-the-art unsupervised node embedding methods. We believe this work opens a door for more sophisticated technical designs and empirical evaluations toward the leverage of LMs for the modeling of real-world graphs.

PDF Details