He Sun

TMLR Journal 2026 Journal Article

A Survey on Federated Fine-Tuning of Large Language Models

• Yebo Wu
• Chunlin Tian
• Jingguang Li
• He Sun
• KaHou Tam
• Zhanting Zhou
• Haicheng Liao
• Jing Xiong

Large Language Models (LLMs) have demonstrated impressive success across various tasks. Integrating LLMs with Federated Learning (FL), a paradigm known as FedLLM, offers a promising avenue for collaborative model adaptation while preserving data privacy. This survey provides a systematic and comprehensive review of FedLLM. We begin by tracing the historical development of both LLMs and FL, summarizing relevant prior research to set the context. Subsequently, we delve into an in-depth analysis of the fundamental challenges inherent in deploying FedLLM. Addressing these challenges often requires efficient adaptation strategies; therefore, we conduct an extensive examination of existing Parameter-Efficient Fine-tuning (PEFT) methods and explore their applicability within the FL framework. To rigorously evaluate the performance of FedLLM, we undertake a thorough review of existing fine-tuning datasets and evaluation benchmarks. Furthermore, we discuss FedLLM's diverse real-world applications across multiple domains. Finally, we identify critical open challenges and outline promising research directions to foster future advancements in FedLLM. This survey aims to serve as a foundational resource for researchers and practitioners, offering valuable insights into the rapidly evolving landscape of federated fine-tuning for LLMs. It also establishes a roadmap for future innovations in privacy-preserving AI. We actively maintain a GitHub repo to track cutting-edge advancements in this field.

TMLR Journal 2025 Journal Article

Dive3D: Diverse Distillation-based Text-to-3D Generation via Score Implicit Matching

• Weimin Bai
• Yubo Li
• Wenzheng Chen
• Weijian Luo
• He Sun

Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence—a formulation that inherently favors mode-seeking behavior and limits generation diversity. In this paper, we introduce Dive3D, a novel text-to-3D generation framework that replaces KL-based objectives with Score Implicit Matching (SIM) loss, a score-based objective that effectively mitigates mode collapse. Furthermore, Dive3D integrates both diffusion distillation and reward-guided optimization under a unified divergence perspective. Such reformulation, together with SIM loss, yields significantly more diverse 3D outputs while improving text alignment, human preference, and overall visual fidelity. We validate Dive3D across various 2D-to-3D prompts and find that it consistently outperforms prior methods in qualitative assessments, including diversity, photorealism, and aesthetic appeal. We further evaluate its performance on the GPTEval3D benchmark, comparing against nine state-of-the-art baselines. Dive3D also achieves strong results on quantitative metrics, including text–asset alignment, 3D plausibility, text–geometry consistency, texture quality, and geometric detail.

NeurIPS Conference 2025 Conference Paper

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

• Siyi Chen
• Yixuan Jia
• Qing Qu
• He Sun
• Jeffrey Fessler

Data assimilation (DA) integrates observations with a dynamical model to estimate states of PDE-governed systems. Model-driven methods (e. g. , Kalman Filter, Particle Filter) presuppose full knowledge of the true dynamics, which is not always satisfied in practice, while purely data-driven solvers learn a deterministic mapping between observations and states and therefore miss the intrinsic stochasticity of real processes. Recently, score-based diffusion models have shown promise for DA by learning a global diffusion prior to represent stochastic dynamics. However, their one-shot generation lacks stepwise physical consistency and struggles with complex stochastic processes. To address these issues, we propose FlowDAS, a generative DA framework that employs stochastic interpolants to learn state transition dynamics through step-by-step stochastic updates. By incorporating observations into each transition, FlowDAS can produce stable, measurement-consistent forecasts. Experiments on Lorenz-63, Navier–Stokes super-resolution/sparse-observation scenarios, and large-scale weather forecasting—where dynamics are partly or wholly unknown—show that FlowDAS surpasses model-driven methods, neural operators, and score-based baselines in accuracy and physical plausibility. Our implementation is available at https: //github. com/umjiayx/FlowDAS.

ICML Conference 2025 Conference Paper

Online Sparsification of Bipartite-Like Clusters in Graphs

• Joyentanuj Das
• Suranjan De
• He Sun

Graph clustering is an important algorithmic technique for analysing massive graphs, and has been widely applied in many research fields of data science. While the objective of most graph clustering algorithms is to find a vertex set of low conductance, there has been a sequence of recent studies that highlight the importance of the inter-connection between clusters when analysing real-world datasets. Following this line of research, in this work we study bipartite-like clusters and present efficient and online algorithms that find such clusters in both undirected graphs and directed ones. We conduct experimental studies on both synthetic and real-world datasets, and show that our algorithms significantly speedup the running time of existing clustering algorithms while preserving their effectiveness.

NeurIPS Conference 2025 Conference Paper

Uni-Instruct: One-step Diffusion Model through Unified Diffusion Divergence Instruction

• Yifei Wang
• Weimin Bai
• colin zhang
• Debing Zhang
• Weijian Luo
• He Sun

In this paper, we unify more than 10 existing one-step diffusion distillation approaches, such as Diff-Instruct, DMD, SIM, SiD, $f$-distill, etc, inside a theory-driven framework which we name the \textbf{\emph{Uni-Instruct}}. Uni-Instruct is motivated by our proposed diffusion expansion theory of the $f$-divergence family. Then we introduce key theories that overcome the intractability issue of the original expanded $f$-divergence, resulting in an equivalent yet tractable loss that effectively trains one-step diffusion models by minimizing the expanded $f$-divergence family. The novel unification introduced by Uni-Instruct not only offers new theoretical contributions that help understand existing approaches from a high-level perspective but also leads to state-of-the-art one-step diffusion generation performances. On the CIFAR10 generation benchmark, Uni-Instruct achieves record-breaking Frechet Inception Distance (FID) values of \textbf{\emph{1. 46}} for unconditional generation and \textbf{\emph{1. 38}} for conditional generation. On the ImageNet-$64\times 64$ generation benchmark, Uni-Instruct achieves a new SoTA one-step diffusion FID value of \textbf{\emph{1. 06}}, which outperforms its 79-step teacher diffusion with a significant improvement margin of 1. 29 (1. 06 vs 2. 35). We also apply Uni-Instruct on broader tasks like text-to-3D generation. For text-to-3D generation, Uni-Instruct gives decent results, which slightly outperforms previous methods, such as SDS and VSD, in terms of both generation quality and diversity. Both the solid theoretical and empirical contributions of Uni-Instruct will potentially help future studies on one-step diffusion distillation and knowledge transferring of diffusion models.

NeurIPS Conference 2024 Conference Paper

An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations

• Weimin Bai
• Yifei Wang
• Wenzheng Chen
• He Sun

Diffusion models excel in solving imaging inverse problems due to their ability to model complex image priors. However, their reliance on large, clean datasets for training limits their practical use where clean data is scarce. In this paper, we propose EMDiffusion, an expectation-maximization (EM) approach to train diffusion models from corrupted observations. Our method alternates between reconstructing clean images from corrupted data using a known diffusion model (E-step) and refining diffusion model weights based on these reconstructions (M-step). This iterative process leads the learned diffusion model to gradually converge to a local optimum, that is, to approximate the true clean data distribution. We validate our method through extensive experiments on diverse computational imaging tasks, including random inpainting, denoising, and deblurring, achieving new state-of-the-art performance.

NeurIPS Conference 2023 Conference Paper

Fast Approximation of Similarity Graphs with Kernel Density Estimation

• Peter Macgregor
• He Sun

Constructing a similarity graph from a set $X$ of data points in $ \mathbb{R}^d$ is the first step of many modern clustering algorithms. However, typical constructions of a similarity graph have high time complexity, and a quadratic space dependency with respect to $|X|$. We address this limitation and present a new algorithmic framework that constructs a sparse approximation of the fully connected similarity graph while preserving its cluster structure. Our presented algorithm is based on the kernel density estimation problem, and is applicable for arbitrary kernel functions. We compare our designed algorithm with the well-known implementations from the scikit-learn library and the FAISS library, and find that our method significantly outperforms the implementation from both libraries on a variety of datasets.

AAAI Conference 2021 Conference Paper

Deep Probabilistic Imaging: Uncertainty Quantification and Multi-modal Solution Characterization for Computational Imaging

• He Sun
• Katherine L. Bouman

Computational image reconstruction algorithms generally produce a single image without any measure of uncertainty or confidence. Regularized Maximum Likelihood (RML) and feed-forward deep learning approaches for inverse problems typically focus on recovering a point estimate. This is a serious limitation when working with underdetermined imaging systems, where it is conceivable that multiple image modes would be consistent with the measured data. Characterizing the space of probable images that explain the observational data is therefore crucial. In this paper, we propose a variational deep probabilistic imaging approach to quantify reconstruction uncertainty. Deep Probabilistic Imaging (DPI) employs an untrained deep generative model to estimate a posterior distribution of an unobserved image. This approach does not require any training data; instead, it optimizes the weights of a neural network to generate image samples that fit a particular measurement dataset. Once the network weights have been learned, the posterior distribution can be efficiently sampled. We demonstrate this approach in the context of interferometric radio imaging, which is used for black hole imaging with the Event Horizon Telescope, and compressed sensing Magnetic Resonance Imaging (MRI).

NeurIPS Conference 2021 Conference Paper

Finding Bipartite Components in Hypergraphs

• Peter Macgregor
• He Sun

Hypergraphs are important objects to model ternary or higher-order relations of objects, and have a number of applications in analysing many complex datasets occurring in practice. In this work we study a new heat diffusion process in hypergraphs, and employ this process to design a polynomial-time algorithm that approximately finds bipartite components in a hypergraph. We theoretically prove the performance of our proposed algorithm, and compare it against the previous state-of-the-art through extensive experimental analysis on both synthetic and real-world datasets. We find that our new algorithm consistently and significantly outperforms the previous state-of-the-art across a wide range of hypergraphs.

NeurIPS Conference 2021 Conference Paper

Hierarchical Clustering: $O(1)$-Approximation for Well-Clustered Graphs

• Bogdan-Adrian Manghiuc
• He Sun

Hierarchical clustering studies a recursive partition of a data set into clusters of successively smaller size, and is a fundamental problem in data analysis. In this work we study the cost function for hierarchical clustering introduced by Dasgupta, and present two polynomial-time approximation algorithms: Our first result is an $O(1)$-approximation algorithm for graphs of high conductance. Our simple construction bypasses complicated recursive routines of finding sparse cuts known in the literature. Our second and main result is an $O(1)$-approximation algorithm for a wide family of graphs that exhibit a well-defined structure of clusters. This result generalises the previous state-of-the-art, which holds only for graphs generated from stochastic models. The significance of our work is demonstrated by the empirical analysis on both synthetic and real-world data sets, on which our presented algorithm outperforms the previously proposed algorithm for graphs with a well-defined cluster structure.

NeurIPS Conference 2020 Conference Paper

Higher-Order Spectral Clustering of Directed Graphs

• Steinar Laenen
• He Sun

Clustering is an important topic in algorithms, and has a number of applications in machine learning, computer vision, statistics, and several other research disciplines. Traditional objectives of graph clustering are to find clusters with low conductance. Not only are these objectives just applicable for undirected graphs, they are also incapable to take the relationships between clusters into account, which could be crucial for many applications. To overcome these downsides, we study directed graphs (digraphs) whose clusters exhibit further “structural” information amongst each other. Based on the Hermitian matrix representation of digraphs, we present a nearly-linear time algorithm for digraph clustering, and further show that our proposed algorithm can be implemented in sublinear time under reasonable assumptions. The significance of our theoretical work is demonstrated by extensive experimental results on the UN Comtrade Dataset: the output clustering of our algorithm exhibits not only how the clusters (sets of countries) relate to each other with respect to their import and export records, but also how these clusters evolve over time, in accordance with known facts in international trade.

NeurIPS Conference 2016 Conference Paper

Communication-Optimal Distributed Clustering

• Jiecao Chen
• He Sun
• David Woodruff
• Qin Zhang

Clustering large datasets is a fundamental problem with a number of applications in machine learning. Data is often collected on different sites and clustering needs to be performed in a distributed manner with low communication. We would like the quality of the clustering in the distributed setting to match that in the centralized setting for which all the data resides on a single site. In this work, we study both graph and geometric clustering problems in two distributed models: (1) a point-to-point model, and (2) a model with a broadcast channel. We give protocols in both models which we show are nearly optimal by proving almost matching communication lower bounds. Our work highlights the surprising power of a broadcast channel for clustering problems; roughly speaking, to cluster n points or n vertices in a graph distributed across s servers, for a worst-case partitioning the communication complexity in a point-to-point model is n*s, while in the broadcast model it is n + s. We implement our algorithms and demonstrate this phenomenon on real life datasets, showing that our algorithms are also very efficient in practice.

TCS Journal 2013 Journal Article

Deterministic polynomial-time algorithms for designing short DNA words

• Ming-Yang Kao
• Henry C.M. Leung
• He Sun
• Yong Zhang

TCS Journal 2009 Journal Article

Two improved range-efficient algorithms for F 0 estimation

• He Sun
• Chung Keung Poon