Author name cluster

Jing Su

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.

7 papers

2 author rows

NeurIPS Conference 2025 Conference Paper

FAN: Fourier Analysis Networks

Yihong Dong
Ge Li
Yongding Tao
Xue Jiang
Kechi Zhang
Jia Li
Jinliang Deng
Jing Su

Despite the remarkable successes of general-purpose neural networks, such as MLPs and Transformers, we find that they exhibit notable shortcomings in modeling and reasoning about periodic phenomena, achieving only marginal performance within the training domain and failing to generalize effectively to out-of-domain (OOD) scenarios. Periodicity is ubiquitous throughout nature and science. Therefore, neural networks should be equipped with the essential ability to model and handle periodicity. In this work, we propose FAN, a novel neural network that effectively addresses periodicity modeling challenges while offering broad applicability similar to MLP with fewer parameters and FLOPs. Periodicity is naturally integrated into FAN's structure and computational processes by introducing the Fourier Principle. Unlike existing Fourier-based networks, which possess particular periodicity modeling abilities but face challenges in scaling to deeper networks and are typically designed for specific tasks, our approach overcomes this challenge to enable scaling to large-scale models and maintains the capability to be applied to more types of tasks. Through extensive experiments, we demonstrate the superiority of FAN in periodicity modeling tasks and the effectiveness and generalizability of FAN across a range of real-world tasks. Moreover, we reveal that compared to existing Fourier-based networks, FAN accommodates both periodicity modeling and general-purpose modeling well.

PDF Details

ICLR Conference 2025 Conference Paper

Merging LoRAs like Playing LEGO: Pushing the Modularity of LoRA to Extremes Through Rank-Wise Clustering

Ziyu Zhao 0001
Tao Shen 0002
Didi Zhu
Zexi Li 0001
Jing Su
Xuwu Wang
Fei Wu 0001

Low-Rank Adaptation (LoRA) has emerged as a popular technique for fine-tuning large language models (LLMs) to various domains due to its modular design and widespread availability on platforms like Huggingface. This modularity has sparked interest in combining multiple LoRAs to significantly enhance LLM capabilities. However, existing methods for LoRA composition primarily focus on task-specific adaptations that require additional training, and current model merging techniques often fail to fully leverage LoRA's modular nature, leading to parameter interference and performance degradation. In this paper, we explore the possibility of disassembling and reassembling multiple LoRAs at a finer granularity, much like assembling LEGO blocks. We introduce the concept of Minimal Semantic Units (MSUs), where the parameters corresponding to each rank in LoRA function as independent units. These MSUs exhibit properties such as permutation invariance and concatenation-summation equivalence, allowing for flexible combinations to form new LoRAs. Building on these insights, we propose the LoRA-LEGO framework. This framework conducts rank-wise parameter clustering by grouping MSUs from different LoRAs into $k$ clusters. The centroid of each cluster serves as a representative MSU, enabling the assembly of a merged LoRA with an adjusted rank of $k$. Additionally, we apply a dual reweighting strategy to optimize the scale of the merged LoRA. Experiments across various benchmarks demonstrate that our method outperforms existing approaches in LoRA merging.

Details

NeurIPS Conference 2025 Conference Paper

Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving

Daoguang Zan
Zhirong Huang
Wei Liu
Hanwu Chen
Shulin Xin
Linhao Zhang
Qi Liu
Li Aoyan

The task of issue resolving aims to modify a codebase to generate a patch that addresses a given issue. However, most existing benchmarks focus almost exclusively on Python, making them insufficient for evaluating Large Language Models (LLMs) across different programming languages. To bridge this gap, we introduce a multilingual issue-resolving benchmark, called Multi-SWE-bench, covering 8 languages of Python, Java, TypeScript, JavaScript, Go, Rust, C, and C++. In particular, this benchmark includes a total of 2, 132 high-quality instances, carefully curated by 68 expert annotators, ensuring a reliable and accurate evaluation of LLMs on the issue-resolving task. Based on human-annotated results, the issues are further classified into three difficulty levels. We evaluate a series of state-of-the-art models on Multi-SWE-bench, utilizing both procedural and agent-based frameworks for issue resolving. Our experiments reveal three key findings: (1) Limited generalization across languages: While existing LLMs perform well on Python issues, their ability to generalize across other languages remains limited; (2) Performance aligned with human-annotated difficulty: LLM-based agents' performance closely aligns with human-assigned difficulty, with resolution rates decreasing as issue complexity rises; and (3) Performance drop on cross-file issues: The performance of current methods significantly deteriorates when handling cross-file issues. These findings highlight the limitations of current LLMs and underscore the need for more robust models capable of handling a broader range of programming languages and complex issue scenarios.

PDF Details

ICLR Conference 2025 Conference Paper

The Rise and Down of Babel Tower: Investigating the Evolution Process of Multilingual Code Large Language Model

Jiawei Chen 0011
Wentao Chen
Jing Su
Jingjing Xu
Hongyu Lin
Mengjie Ren
Yaojie Lu 0001
Xianpei Han

Large language models (LLMs) have shown significant multilingual capabilities. However, the mechanisms underlying the development of these capabilities during pre-training are not well understood. In this paper, we use code LLMs as an experimental platform to explore the evolution of multilingual capabilities in LLMs during the pre-training process. Based on our observations, we propose the Babel Tower Hypothesis, which describes the entire process of LLMs acquiring new language capabilities. During the learning process, multiple languages initially share a single knowledge system dominated by the primary language and gradually develop language-specific knowledge systems. We then validate the above hypothesis by tracking the internal states of the LLM using specific methods. Experimental results show that the internal state changes of the LLM are consistent with our Babel Tower Hypothesis. Building on these insights, we propose a novel method to construct an optimized pre-training corpus for multilingual code LLMs, which significantly outperforms LLMs trained on the original corpus. The proposed Babel Tower Hypothesis provides new insights into designing pre-training data distributions to achieve optimal multilingual capabilities in LLMs.

Details

ICML Conference 2024 Conference Paper

InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks

Xueyu Hu
Ziyu Zhao 0001
Shuang Wei
Ziwei Chai
Qianli Ma
Guoyin Wang 0002
Xuwu Wang
Jing Su

In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks. Agents need to solve these tasks end-to-end by interacting with an execution environment. This benchmark contains DAEval, a dataset consisting of 603 data analysis questions derived from 124 CSV files, and an agent framework which incorporates LLMs to serve as data analysis agents for both serving and evaluating. Since data analysis questions are often open-ended and hard to evaluate without human supervision, we adopt a format-prompting technique to convert each question into a closed-form format so that they can be automatically evaluated. Our extensive benchmarking of 34 LLMs uncovers the current challenges encountered in data analysis tasks. In addition, building upon our agent framework, we develop a specialized agent, DAAgent, which surpasses GPT-3. 5 by 3. 9% on DABench. Evaluation datasets and toolkits for InfiAgent-DABench are released at https: //github. com/InfiAgent/InfiAgent.

Details

AAAI Conference 2023 Conference Paper

Accurate Fairness: Improving Individual Fairness without Trading Accuracy

Xuran Li
Peng Wu
Jing Su

Accuracy and individual fairness are both crucial for trustworthy machine learning, but these two aspects are often incompatible with each other so that enhancing one aspect may sacrifice the other inevitably with side effects of true bias or false fairness. We propose in this paper a new fairness criterion, accurate fairness, to align individual fairness with accuracy. Informally, it requires the treatments of an individual and the individual's similar counterparts to conform to a uniform target, i.e., the ground truth of the individual. We prove that accurate fairness also implies typical group fairness criteria over a union of similar sub-populations. We then present a Siamese fairness in-processing approach to minimize the accuracy and fairness losses of a machine learning model under the accurate fairness constraints. To the best of our knowledge, this is the first time that a Siamese approach is adapted for bias mitigation. We also propose fairness confusion matrix-based metrics, fair-precision, fair-recall, and fair-F1 score, to quantify a trade-off between accuracy and individual fairness. Comparative case studies with popular fairness datasets show that our Siamese fairness approach can achieve on average 1.02%-8.78% higher individual fairness (in terms of fairness through awareness) and 8.38%-13.69% higher accuracy, as well as 10.09%-20.57% higher true fair rate, and 5.43%-10.01% higher fair-F1 score, than the state-of-the-art bias mitigation techniques. This demonstrates that our Siamese fairness approach can indeed improve individual fairness without trading accuracy. Finally, the accurate fairness criterion and Siamese fairness approach are applied to mitigate the possible service discrimination with a real Ctrip dataset, by on average fairly serving 112.33% more customers (specifically, 81.29% more customers in an accurately fair way) than baseline models.

PDF Details DOI

JBHI Journal 2014 Journal Article

Modeling Cell–Cell Interactions in Regulating Multiple Myeloma Initiating Cell Fate

Tao Peng
Huiming Peng
Dong Soon Choi
Jing Su
Chung-Che Chang
Xiaobo Zhou

Cancer initiating cells have been documented in multiple myeloma and believed to be a key factor that initiates and drives tumor growth, differentiation, metastasis, and recurrence of the diseases. Although myeloma initiating cells (MICs) are likely to share many properties of normal stem cells, the underlying mechanisms regulating the fate of MICs are largely unknown. Studies designed to explore such communication are urgently needed to enhance our ability to predict the fate decisions of MICs (self-renewal, differentiation, and proliferation). In this study, we developed a novel system to understand the intercellular communication between MICs and their niche by seamlessly integrating experimental data and mathematical model. We first designed dynamic cell culture experiments and collected three types of cells (side population cells, progenitor cells, and mature myeloma cells) under various cultural conditions with flow cytometry. Then we developed a lineage model with ordinary differential equations by considering secreted factors, self-renewal, differentiation, and other biological functions of those cells, to model the cell–cell interactions among the three cell types. Particle swarm optimization was employed to estimate the model parameters by fitting the experimental data to the lineage model. The theoretical results show that the correlation coefficient analysis can reflect the feedback loops among the three cell types, the intercellular feedback signaling can regulate cell population dynamics, and the culture strategies can decide cell growth. This study provides a basic framework of studying cell–cell interactions in regulating MICs fate.

Details DOI