Author name cluster

Mo 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.

18 papers

2 author rows

AAAI Conference 2026 Conference Paper

DAWN: Distributed LLM Multi-Agent Workflow Synthesis

Guancheng Wan
Mo Zhou
Ziyi Wang
Xiaoran Shang
Eric Hanchen Jiang
Guibin Zhang
Jinhe Bi
Yunpu Ma

Large language models (LLMs) have recently empowered multi-agent systems (MAS) to achieve remarkable advances in collaborative reasoning and complex task automation. The effectiveness of these systems fundamentally depends on the design of adaptive communication graphs—the underlying workflows that coordinate agent interactions. However, in real-world scenarios, strict privacy constraints often silo data across organizations, and client distributions are highly non-IID, posing major challenges for synthesizing such workflows. In this work, we are the first to systematically study distributed multi-agent workflow synthesis under these privacy and heterogeneity constraints, and we introduce the Difficulty-Based Skew (DBS) benchmark to emulate such challenging environments. Drawing inspiration from federated graph learning (FGL)—which has primarily focused on classification over static graphs—we identify a critical gap: existing FGL methods do not address the generative design of communication topologies. We reveal two fundamental obstacles to generative workflow synthesis in this setting: (i) workflow specialization conflict, where agents optimized for different task distributions generate incompatible communication patterns that resist meaningful aggregation, and (ii) structural communication shift, where locally optimal agent interaction graphs fail to compose into globally coherent multi-agent workflows. To address these challenges, we propose DAWN, a federated framework that integrates two key innovations: Parametric Resonance, which robustly aggregates heterogeneous local updates via layer-wise SVD-based denoising and alignment, and Structural Gravity, which regularizes local workflow generation by penalizing the Fusion Gromov-Wasserstein distance to a set of prototype communication graphs, ensuring global structural coherence without stifling local adaptation. Experiments on the DBS benchmark show that DAWN surpasses baselines in global task success and reduces inter-client graph divergence, laying a solid foundation for privacy-preserving, adaptive MAS workflow design in heterogeneous settings.

PDF Details DOI

EAAI Journal 2026 Journal Article

Global relationship awareness 3-dimensional object detection using 4-dimensional radar

Pianzhang Duan
Li Wang
Cheng Fang
Ziying Song
Ming Gao
Mo Zhou
Ying Li
Yibo Zhang

4D (4-dimensional) radar sensing technology is essential for high-precision autonomous driving perception systems, as its superior detection capabilities at increased distances, compared to traditional LiDAR (Light Detection and Ranging). However, due to the sparsity of point clouds and the low resolution of millimeter-wave radar, voxel-based methods may fail to detect distant or closely adjacent objects, leading to inadequate detection accuracy. To mitigate the accuracy issues arising from the sparse nature of point clouds in such scenarios, we propose a novel object detection network: GRA-Net (Global Relation-Aware object detection Network). By leveraging a self-attention mechanism, GRA-Net effectively learns critical features from each radar pillar, enhancing the network’s capacity to capture relevant information about nearby objects. Furthermore, we introduce a global perception module that integrates key features within the pillars and global features, mitigating the impact of point cloud sparsity, particularly in distant regions. We conducted a series of experiments to evaluate the performance of GRA-Net. On the Astyx HiRes 2019 dataset, our method achieved 33. 63 mAP (mean Average Precision) and 43. 93 mAP at the moderate level; On the View-of-Delft dataset, our method achieved 47. 74 mAP in the entire annotated area and 69. 25 mAP in the driving corridor area.

Details DOI

NeurIPS Conference 2025 Conference Paper

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

Mucong Ding
Bang An
Tahseen Rabbani
Chenghao Deng
Anirudh Satheesh
Souradip Chakraborty
Mehrdad Saberi
Yuxin Wen

AI-generated images have become pervasive, raising critical concerns around content authenticity, intellectual property, and the spread of misinformation. Invisible watermarks offer a promising solution for identifying AI-generated images, preserving content provenance without degrading visual quality. However, their real-world robustness remains uncertain due to the lack of standardized evaluation protocols and large-scale stress testing. To bridge this gap, we organized “Erasing the Invisible, ” a NeurIPS 2024 competition and newly established benchmark designed to systematically stress testing the resilience of watermarking techniques. The competition introduced two attack tracks—Black-box and Beige-box—that simulate practical scenarios with varying levels of attacker knowledge on watermarks, providing a comprehensive assessment of watermark robustness. The competition attracted significant global participation, with 2, 722 submissions from 298 teams. Through a rigorous evaluation pipeline featuring real-time feedback and human-verified final rankings, participants developed and demonstrated new attack strategies that revealed critical vulnerabilities in state-of-the-art watermarking methods. On average, the top-5 teams in both tracks could remove watermarks from $\geq$ 89% of the images while preserving high visual quality, setting strong baselines for future research on watermark attacks and defenses. To support continued progress in this field, we summarize the insights and lessons learned from this competition in this paper, and release the benchmark dataset, evaluation toolkit, and competition results. “Erasing the Invisible” establishes a valuable open resource for advancing more robust watermarking techniques and strengthening content provenance in the era of generative AI.

PDF Details

ICLR Conference 2025 Conference Paper

Field-DiT: Diffusion Transformer on Unified Video, 3D, and Game Field Generation

Kangfu Mei
Mo Zhou
Vishal M. Patel

The probabilistic field models the distribution of continuous functions defined over metric spaces. While these models hold great potential for unifying data generation across various modalities, including images, videos, and 3D geometry, they still struggle with long-context generation beyond simple examples. This limitation can be attributed to their MLP architecture, which lacks sufficient inductive bias to capture global structures through uniform sampling. To address this, we propose a new and simple model that incorporates a view-wise sampling algorithm to focus on local structure learning, along with autoregressive generation to preserve global geometry. It adapts cross-modality conditions, such as text prompts for text-to-video generation, camera poses for 3D view generation, and control actions for game generation. Experimental results across various modalities demonstrate the effectiveness of our model, with its 675M parameter size, and highlight its potential as a foundational framework for scalable, architecture-unified visual content generation for different modalities with different weights. Our project page can be found at https://kfmei.com/Field-DiT/.

Details

NeurIPS Conference 2025 Conference Paper

V2X-Radar: A Multi-modal Dataset with 4D Radar for Cooperative Perception

Lei Yang
Xinyu Zhang
Jun Li
Chen Wang
Jiaqi Ma
Zhiying Song
Tong Zhao
Ziying Song

Modern autonomous vehicle perception systems often struggle with occlusions and limited perception range. Previous studies have demonstrated the effectiveness of cooperative perception in extending the perception range and overcoming occlusions, thereby enhancing the safety of autonomous driving. In recent years, a series of cooperative perception datasets have emerged; however, these datasets primarily focus on cameras and LiDAR, neglecting 4D Radar—a sensor used in single-vehicle autonomous driving to provide robust perception in adverse weather conditions. In this paper, to bridge the gap created by the absence of 4D Radar datasets in cooperative perception, we present V2X-Radar, the first large-scale, real-world multi-modal dataset featuring 4D Radar. V2X-Radar dataset is collected using a connected vehicle platform and an intelligent roadside unit equipped with 4D Radar, LiDAR, and multi-view cameras. The collected data encompasses sunny and rainy weather conditions, spanning daytime, dusk, and nighttime, as well as various typical challenging scenarios. The dataset consists of 20K LiDAR frames, 40K camera images, and 20K 4D Radar data, including 350K annotated boxes across five categories. To support various research domains, we have established V2X-Radar-C for cooperative perception, V2X-Radar-I for roadside perception, and V2X-Radar-V for single-vehicle perception. Furthermore, we provide comprehensive benchmarks across these three sub-datasets.

PDF Details

NeurIPS Conference 2024 Conference Paper

How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks

Mo Zhou
Rong Ge

The ability of learning useful features is one of the major advantages of neural networks. Although recent works show that neural network can operate in a neural tangent kernel (NTK) regime that does not allow feature learning, many works also demonstrate the potential for neural networks to go beyond NTK regime and perform feature learning. Recently, a line of work highlighted the feature learning capabilities of the early stages of gradient-based training. In this paper we consider another mechanism for feature learning via gradient descent through a local convergence analysis. We show that once the loss is below a certain threshold, gradient descent with a carefully regularized objective will capture ground-truth directions. We further strengthen this local convergence analysis by incorporating early-stage feature learning analysis. Our results demonstrate that feature learning not only happens at the initial gradient steps, but can also occur towards the end of training.

PDF Details DOI

TMLR Journal 2024 Journal Article

MixedNUTS: Training-Free Accuracy-Robustness Balance via Nonlinearly Mixed Classifiers

Yatong Bai
Mo Zhou
Vishal M. Patel
Somayeh Sojoudi

Adversarial robustness often comes at the cost of degraded accuracy, impeding real-life applications of robust classification models. Training-based solutions for better trade-offs are limited by incompatibilities with already-trained high-performance large models, necessitating the exploration of training-free ensemble approaches. Observing that robust models are more confident in correct predictions than in incorrect ones on clean and adversarial data alike, we speculate amplifying this "benign confidence property" can reconcile accuracy and robustness in an ensemble setting. To achieve so, we propose "MixedNUTS", a *training-free* method where the output logits of a robust classifier and a standard non-robust classifier are processed by nonlinear transformations with only three parameters, which are optimized through an efficient algorithm. MixedNUTS then converts the transformed logits into probabilities and mixes them as the overall output. On CIFAR-10, CIFAR-100, and ImageNet datasets, experimental results with custom strong adaptive attacks demonstrate MixedNUTS's vastly improved accuracy and near-SOTA robustness -- it boosts CIFAR-100 clean accuracy by $7.86$ points, sacrificing merely $0.87$ points in robust accuracy.

PDF Details

ICLR Conference 2023 Conference Paper

Depth Separation with Multilayer Mean-Field Networks

Yunwei Ren
Mo Zhou
Rong Ge 0001

Depth separation—why a deeper network is more powerful than a shallow one—has been a major problem in deep learning theory. Previous results often focus on representation power, for example, Safran et al. (2019) constructed a function that is easy to approximate using a 3-layer network but not approximable by any 2-layer network. In this paper, we show that this separation is in fact algorithmic: one can learn the function constructed by Safran et al. (2019) using an overparametrized network with polynomially many neurons efﬁciently. Our result relies on a new way of extending the mean-ﬁeld limit to multilayer networks, and a decomposition of loss that factors out the error introduced by the discretization of inﬁnite-width mean-ﬁeld networks.

Details

ICML Conference 2023 Conference Paper

Implicit Regularization Leads to Benign Overfitting for Sparse Linear Regression

Mo Zhou
Rong Ge 0001

In deep learning, often the training process finds an interpolator (a solution with 0 training loss), but the test loss is still low. This phenomenon, known as benign overfitting, is a major mystery that received a lot of recent attention. One common mechanism for benign overfitting is implicit regularization, where the training process leads to additional properties for the interpolator, often characterized by minimizing certain norms. However, even for a simple sparse linear regression problem $y = \beta^{\ast\top} x +\xi$ with sparse $\beta^{\ast}$, neither minimum $\ell_1$ or $\ell_2$ norm interpolator gives the optimal test loss. In this work, we give a different parametrization of the model which leads to a new implicit regularization effect that combines the benefit of $\ell_1$ and $\ell_2$ interpolators. We show that training our new model via gradient descent leads to an interpolator with near-optimal test loss. Our result is based on careful analysis of the training dynamics and provides another example of implicit regularization effect that goes beyond norm minimization.

Details

ICLR Conference 2023 Conference Paper

Plateau in Monotonic Linear Interpolation - A "Biased" View of Loss Landscape for Deep Networks

Xiang Wang 0011
Annie N. Wang
Mo Zhou
Rong Ge 0001

Monotonic linear interpolation (MLI) --- on the line connecting a random initialization with the minimizer it converges to, the loss and accuracy are monotonic --- is a phenomenon that is commonly observed in the training of neural networks. Such a phenomenon may seem to suggest that optimization of neural networks is easy. In this paper, we show that the MLI property is not necessarily related to the hardness of optimization problems, and empirical observations on MLI for deep neural networks depend heavily on the biases. In particular, we show that interpolating both weights and biases linearly leads to very different influences on the final output, and when different classes have different last-layer biases on a deep network, there will be a long plateau in both the loss and accuracy interpolation (which existing theory of MLI cannot explain). We also show how the last-layer biases for different classes can be different even on a perfectly balanced dataset using a simple model. Empirically we demonstrate that similar intuitions hold on practical networks and realistic datasets.

Details

JMLR Journal 2023 Journal Article

Single Timescale Actor-Critic Method to Solve the Linear Quadratic Regulator with Convergence Guarantees

Mo Zhou
Jianfeng Lu

We propose a single timescale actor-critic algorithm to solve the linear quadratic regulator (LQR) problem. A least squares temporal difference (LSTD) method is applied to the critic and a natural policy gradient method is used for the actor. We give a proof of convergence with sample complexity $\mathcal{O}(\varepsilon^{-1} \log(\varepsilon^{-1})^2)$. The method in the proof is applicable to general single timescale bilevel optimization problems. We also numerically validate our theoretical results on the convergence. [abs] [ pdf ][ bib ] [ code ] &copy JMLR 2023. ( edit, beta )

PDF Details

ICLR Conference 2023 Conference Paper

Understanding Edge-of-Stability Training Dynamics with a Minimalist Example

Xingyu Zhu 0003
Zixuan Wang
Xiang Wang 0011
Mo Zhou
Rong Ge 0001

Recently, researchers observed that gradient descent for deep neural networks operates in an ``edge-of-stability'' (EoS) regime: the sharpness (maximum eigenvalue of the Hessian) is often larger than stability threshold $2/\eta$ (where $\eta$ is the step size). Despite this, the loss oscillates and converges in the long run, and the sharpness at the end is just slightly below $2/\eta$. While many other well-understood nonconvex objectives such as matrix factorization or two-layer networks can also converge despite large sharpness, there is often a larger gap between sharpness of the endpoint and $2/\eta$. In this paper, we study EoS phenomenon by constructing a simple function that has the same behavior. We give rigorous analysis for its training dynamics in a large local region and explain why the final converging point has sharpness close to $2/\eta$. Globally we observe that the training dynamics for our example has an interesting bifurcating behavior, which was also observed in the training of neural nets.

Details

ICLR Conference 2023 Conference Paper

Understanding The Robustness of Self-supervised Learning Through Topic Modeling

Zeping Luo
Shiyou Wu
Cindy Weng
Mo Zhou
Rong Ge 0001

Self-supervised learning has significantly improved the performance of many NLP tasks. However, how can self-supervised learning discover useful features, and why is it better than traditional approaches such as probabilistic models are still largely unknown. In this paper, we focus on the context of topic modeling and highlight a key advantage of self-supervised learning - when applied to data generated by topic models, self-supervised learning can be oblivious to the specific model, and hence is less susceptible to model misspecification. In particular, we prove that commonly used self-supervised objectives based on reconstruction or contrastive samples can both recover useful posterior information for general topic models. Empirically, we show that the same objectives can perform on par with posterior inference using the correct model, while outperforming posterior inference using misspecified models.

Details

NeurIPS Conference 2022 Conference Paper

Resource-Adaptive Federated Learning with All-In-One Neural Composition

Yiqun Mei
Pengfei Guo
Mo Zhou
Vishal Patel

Conventional Federated Learning (FL) systems inherently assume a uniform processing capacity among clients for deployed models. However, diverse client hardware often leads to varying computation resources in practice. Such system heterogeneity results in an inevitable trade-off between model complexity and data accessibility as a bottleneck. To avoid such a dilemma and achieve resource-adaptive federated learning, we introduce a simple yet effective mechanism, termed All-In-One Neural Composition, to systematically support training complexity-adjustable models with flexible resource adaption. It is able to efficiently construct models at various complexities using one unified neural basis shared among clients, instead of pruning the global model into local ones. The proposed mechanism endows the system with unhindered access to the full range of knowledge scattered across clients and generalizes existing pruning-based solutions by allowing soft and learnable extraction of low footprint models. Extensive experiment results on popular FL benchmarks demonstrate the effectiveness of our approach. The resulting FL system empowered by our All-In-One Neural Composition, called FLANC, manifests consistent performance gains across diverse system/data heterogeneous setups while keeping high efficiency in computation and communication.

PDF Details

NeurIPS Conference 2021 Conference Paper

Understanding Deflation Process in Over-parametrized Tensor Decomposition

Rong Ge
Yunwei Ren
Xiang Wang
Mo Zhou

In this paper we study the training dynamics for gradient flow on over-parametrized tensor decomposition problems. Empirically, such training process often first fits larger components and then discovers smaller components, which is similar to a tensor deflation process that is commonly used in tensor decomposition algorithms. We prove that for orthogonally decomposable tensor, a slightly modified version of gradient flow would follow a tensor deflation process and recover all the tensor components. Our proof suggests that for orthogonal tensors, gradient flow dynamics works similarly as greedy low-rank learning in the matrix setting, which is a first step towards understanding the implicit regularization effect of over-parametrized models for low-rank tensors.

PDF Details

AAAI Conference 2020 Conference Paper

Ladder Loss for Coherent Visual-Semantic Embedding

Mo Zhou
Zhenxing Niu
Le Wang
Zhanning Gao
Qilin Zhang
Gang Hua

For visual-semantic embedding, the existing methods normally treat the relevance between queries and candidates in a bipolar way – relevant or irrelevant, and all “irrelevant” candidates are uniformly pushed away from the query by an equal margin in the embedding space, regardless of their various proximity to the query. This practice disregards relatively discriminative information and could lead to suboptimal ranking in the retrieval results and poorer user experience, especially in the long-tail query scenario where a matching candidate may not necessarily exist. In this paper, we introduce a continuous variable to model the relevance degree between queries and multiple candidates, and propose to learn a coherent embedding space, where candidates with higher relevance degrees are mapped closer to the query than those with lower relevance degrees. In particular, the new ladder loss is proposed by extending the triplet loss inequality to a more general inequality chain, which implements variable push-away margins according to respective relevance degrees. In addition, a proper Coherent Score metric is proposed to better measure the ranking results including those “irrelevant” candidates. Extensive experiments on multiple datasets validate the efﬁcacy of our proposed method, which achieves signiﬁcant improvement over existing state-of-the-art methods.

PDF Details

ICML Conference 2019 Conference Paper

Toward Understanding the Importance of Noise in Training Neural Networks

Mo Zhou
Tianyi Liu
Yan Li 0074
Dachao Lin
Enlu Zhou
Tuo Zhao

Numerous empirical evidence has corroborated that the noise plays a crucial rule in effective and efficient training of deep neural networks. The theory behind, however, is still largely unknown. This paper studies this fundamental problem through training a simple two-layer convolutional neural network model. Although training such a network requires to solve a non-convex optimization problem with a spurious local optimum and a global optimum, we prove that a perturbed gradient descent algorithm in conjunction with noise annealing is guaranteed to converge to a global optimum in polynomial time with arbitrary initialization. This implies that the noise enables the algorithm to efficiently escape from the spurious local optimum. Numerical experiments are provided to support our theory.

Details

NeurIPS Conference 2019 Conference Paper

Towards Understanding the Importance of Shortcut Connections in Residual Networks

Tianyi Liu
Minshuo Chen
Mo Zhou
Simon Du
Enlu Zhou
Tuo Zhao

Residual Network (ResNet) is undoubtedly a milestone in deep learning. ResNet is equipped with shortcut connections between layers, and exhibits efficient training using simple first order algorithms. Despite of the great empirical success, the reason behind is far from being well understood. In this paper, we study a two-layer non-overlapping convolutional ResNet. Training such a network requires solving a non-convex optimization problem with a spurious local optimum. We show, however, that gradient descent combined with proper normalization, avoids being trapped by the spurious local optimum, and converges to a global optimum in polynomial time, when the weight of the first layer is initialized at 0, and that of the second layer is initialized arbitrarily in a ball. Numerical experiments are provided to support our theory.

PDF Details