arXiv subjects

Shengyu Feng

Publications and source records attributed to Shengyu Feng.

At least 19 recordsLinked to original sources

arXiv2026

Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching

Diffusion-based neural solvers have shown strong promise for combinatorial optimization (CO), but existing methods typically rely on supervised training with large collections of near-optimal solutions. In this work, we extend adjoint-based trajectory optimization methods to discrete combinatorial domains. We formulate diffusion-based CO as a stochastic control problem over Continuous-Time Markov Chains and introduce discrete adjoint dynamics for propagating optimization signals through discrete generative trajectories. Building on this formulation, we propose Combinatorial Adjoint Matching (CAM), an unsupervised training framework for discrete diffusion solvers with structured and low-variance trajectory-level optimization signals. Empirically, CAM consistently outperforms existing unsupervised diffusion baselines and achieves performance competitive with strong supervised diffusion solvers and even traditional solvers across diverse combinatorial optimization problems. Our code is available at https://github.com/Shengyu-Feng/CAM.

cs.LG↗

arXiv2025

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following

Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, and system-prompted instructions-remains a significant challenge. Rigorous evaluation and effective training for such capabilities are hindered by the lack of high-quality, human-annotated benchmarks and reliable, interpretable reward signals. In this work, we introduce AdvancedIF (we will release this benchmark soon), a comprehensive benchmark featuring over 1,600 prompts and expert-curated rubrics that assess LLMs ability to follow complex, multi-turn, and system-level instructions. We further propose RIFL (Rubric-based Instruction-Following Learning), a novel post-training pipeline that leverages rubric generation, a finetuned rubric verifier, and reward shaping to enable effective reinforcement learning for instruction following. Extensive experiments demonstrate that RIFL substantially improves the instruction-following abilities of LLMs, achieving a 6.7% absolute gain on AdvancedIF and strong results on public benchmarks. Our ablation studies confirm the effectiveness of each component in RIFL. This work establishes rubrics as a powerful tool for both training and evaluating advanced IF in LLMs, paving the way for more capable and reliable AI systems.

cs.CL↗

arXiv2025

Bradley-Terry Policy Optimization for Generative Preference Modeling

Reinforcement learning (RL) has recently proven effective at scaling chain-of-thought (CoT) reasoning in large language models for tasks with verifiable answers. However, extending RL-based thought training to more general non-verifiable tasks-where supervision is provided only through pairwise human preferences-remains challenging. Existing approaches typically apply RL objectives designed for verifiable rewards to preference-based settings in a heuristic manner. In this work, we show that introducing CoT reasoning into preference modeling fundamentally changes the structure of the Bradley-Terry (BT) likelihood, as the reasoning process must be treated as a latent variable. This results in a preference likelihood expressed as a ratio of expectations over stochastic generation trajectories, which cannot be optimized using Jensen-style bounds or standard RL objectives. To address this challenge, we derive a consistent Monte Carlo estimator for the gradient of the resulting likelihood, leading to Bradley-Terry Policy Optimization (BTPO). Empirically, BTPO enables stable and effective training of generative preference models with CoT reasoning, consistently outperforming prior heuristic approaches across multiple benchmarks and model scales.

cs.LG↗

arXiv2025

CGSim: A Simulation Framework for Large Scale Distributed Computing Environment

Large-scale distributed computing infrastructures such as the Worldwide LHC Computing Grid (WLCG) require comprehensive simulation tools for evaluating performance, testing new algorithms, and optimizing resource allocation strategies. However, existing simulators suffer from limited scalability, hardwired algorithms, lack of real-time monitoring, and inability to generate datasets suitable for modern machine learning approaches. We present CGSim, a simulation framework for large-scale distributed computing environments that addresses these limitations. Built upon the validated SimGrid simulation framework, CGSim provides high-level abstractions for modeling heterogeneous grid environments while maintaining accuracy and scalability. Key features include a modular plugin mechanism for testing custom workflow scheduling and data movement policies, interactive real-time visualization dashboards, and automatic generation of event-level datasets suitable for AI-assisted performance modeling. We demonstrate CGSim's capabilities through a comprehensive evaluation using production ATLAS PanDA workloads, showing significant calibration accuracy improvements across WLCG computing sites. Scalability experiments show near-linear scaling for multi-site simulations, with distributed workloads achieving 6x better performance compared to single-site execution. The framework enables researchers to simulate WLCG-scale infrastructures with hundreds of sites and thousands of concurrent jobs within practical time budget constraints on commodity hardware.

cs.DC↗

arXiv2025

Data Management System Analysis for Distributed Computing Workloads

Large-scale international collaborations such as ATLAS rely on globally distributed workflows and data management to process, move, and store vast volumes of data. ATLAS's Production and Distributed Analysis (PanDA) workflow system and the Rucio data management system are each highly optimized for their respective design goals. However, operating them together at global scale exposes systemic inefficiencies, including underutilized resources, redundant or unnecessary transfers, and altered error distributions. Moreover, PanDA and Rucio currently lack shared performance awareness and coordinated, adaptive strategies. This work charts a path toward co-optimizing the two systems by diagnosing data-management pitfalls and prioritizing end-to-end improvements. With the observation of spatially and temporally imbalanced transfer activities, we develop a metadata-matching algorithm that links PanDA jobs and Rucio datasets at the file level, yielding a complete, fine-grained view of data access and movement. Using this linkage, we identify anomalous transfer patterns that violate PanDA's data-centric job-allocation principle. We then outline mitigation strategies for these patterns and highlight opportunities for tighter PanDA-Rucio coordination to improve resource utilization, reduce unnecessary data movement, and enhance overall system resilience.

cs.DC↗

arXiv2025

Machine Learning-Driven Predictive Resource Management in Complex Science Workflows

The collaborative efforts of large communities in science experiments, often comprising thousands of global members, reflect a monumental commitment to exploration and discovery. Recently, advanced and complex data processing has gained increasing importance in science experiments. Data processing workflows typically consist of multiple intricate steps, and the precise specification of resource requirements is crucial for each step to allocate optimal resources for effective processing. Estimating resource requirements in advance is challenging due to a wide range of analysis scenarios, varying skill levels among community members, and the continuously increasing spectrum of computing options. One practical approach to mitigate these challenges involves initially processing a subset of each step to measure precise resource utilization from actual processing profiles before completing the entire step. While this two-staged approach enables processing on optimal resources for most of the workflow, it has drawbacks such as initial inaccuracies leading to potential failures and suboptimal resource usage, along with overhead from waiting for initial processing completion, which is critical for fast-turnaround analyses. In this context, our study introduces a novel pipeline of machine learning models within a comprehensive workflow management system, the Production and Distributed Analysis (PanDA) system. These models employ advanced machine learning techniques to predict key resource requirements, overcoming challenges posed by limited upfront knowledge of characteristics at each step. Accurate forecasts of resource requirements enable informed and proactive decision-making in workflow management, enhancing the efficiency of handling diverse, complex workflows across heterogeneous resources.

cs.DC↗

arXiv2025

SPL-LNS: Sampling-Enhanced Large Neighborhood Search for Solving Integer Linear Programs

Large Neighborhood Search (LNS) is a common heuristic in combinatorial optimization that iteratively searches over a large neighborhood of the current solution for a better one. Recently, neural network-based LNS solvers have achieved great success in solving Integer Linear Programs (ILPs) by learning to greedily predict the locally optimal solution for the next neighborhood proposal. However, this greedy approach raises two key concerns: (1) to what extent this greedy proposal suffers from local optima, and (2) how can we effectively improve its sample efficiency in the long run. To address these questions, this paper first formulates LNS as a stochastic process, and then introduces SPL-LNS, a sampling-enhanced neural LNS solver that leverages locally-informed proposals to escape local optima. We also develop a novel hindsight relabeling method to efficiently train SPL-LNS on self-generated data. Experimental results demonstrate that SPL-LNS substantially surpasses prior neural LNS solvers for various ILP problems of different sizes.

cs.LG↗

arXiv2025

Towards an Introspective Dynamic Model of Globally Distributed Computing Infrastructures

Large-scale scientific collaborations like ATLAS, Belle II, CMS, DUNE, and others involve hundreds of research institutes and thousands of researchers spread across the globe. These experiments generate petabytes of data, with volumes soon expected to reach exabytes. Consequently, there is a growing need for computation, including structured data processing from raw data to consumer-ready derived data, extensive Monte Carlo simulation campaigns, and a wide range of end-user analysis. To manage these computational and storage demands, centralized workflow and data management systems are implemented. However, decisions regarding data placement and payload allocation are often made disjointly and via heuristic means. A significant obstacle in adopting more effective heuristic or AI-driven solutions is the absence of a quick and reliable introspective dynamic model to evaluate and refine alternative approaches. In this study, we aim to develop such an interactive system using real-world data. By examining job execution records from the PanDA workflow management system, we have pinpointed key performance indicators such as queuing time, error rate, and the extent of remote data access. The dataset includes five months of activity. Additionally, we are creating a generative AI model to simulate time series of payloads, which incorporate visible features like category, event count, and submitting group, as well as hidden features like the total computational load-derived from existing PanDA records and computing site capabilities. These hidden features, which are not visible to job allocators, whether heuristic or AI-driven, influence factors such as queuing times and data movement.

cs.DC↗

arXiv2025

FrontierCO: Real-World and Large-Scale Evaluation of Machine Learning Solvers for Combinatorial Optimization

Machine learning (ML) has shown promise for tackling combinatorial optimization (CO), but much of the reported progress relies on small-scale, synthetic benchmarks that fail to capture real-world structure and scale. A core limitation is that ML methods are typically trained and evaluated on synthetic instance generators, leaving open how they perform on irregular, competition-grade, or industrial datasets. We present FrontierCO, a benchmark for evaluating ML-based CO solvers under real-world structure and extreme scale. FrontierCO spans eight CO problems, including routing, scheduling, facility location, and graph problems, with instances drawn from competitions and public repositories (e.g., DIMACS, TSPLib). Each task provides both easy sets (historically challenging but now solvable) and hard sets (open or computationally intensive), alongside standardized training/validation resources. Using FrontierCO, we evaluate 16 representative ML solvers--graph neural approaches, hybrid neural-symbolic methods, and LLM-based agents--against state-of-the-art classical solvers. We find a persistent performance gap that widens under structurally challenging and large instance sizes (e.g., TSP up to 10M nodes; MIS up to 8M), while also identifying cases where ML methods outperform classical solvers. By centering evaluation on real-world structure and orders-of-magnitude larger instances, FrontierCO provides a rigorous basis for advancing ML for CO. Our benchmark is available at https://huggingface.co/datasets/CO-Bench/FrontierCO.

cs.LG↗

arXiv2025

CO-Bench: Benchmarking Language Model Agents in Algorithm Search for Combinatorial Optimization

Although LLM-based agents have attracted significant attention in domains such as software engineering and machine learning research, their role in advancing combinatorial optimization (CO) remains relatively underexplored. This gap underscores the need for a deeper understanding of their potential in tackling structured, constraint-intensive problems -- a pursuit currently limited by the absence of comprehensive benchmarks for systematic investigation. To address this, we introduce CO-Bench, a benchmark suite featuring 36 real-world CO problems drawn from a broad range of domains and complexity levels. CO-Bench includes structured problem formulations and curated data to support rigorous investigation of LLM agents. We evaluate multiple agentic frameworks against established human-designed algorithms, revealing the strengths and limitations of existing LLM agents and identifying promising directions for future research. CO-Bench is publicly available at https://github.com/sunnweiwei/CO-Bench.

cs.CL↗

arXiv2025

Alternative Mixed Integer Linear Programming Optimization for Joint Job Scheduling and Data Allocation in Grid Computing

This paper presents a novel approach to the joint optimization of job scheduling and data allocation in grid computing environments. We formulate this joint optimization problem as a mixed integer quadratically constrained program. To tackle the nonlinearity in the constraint, we alternatively fix a subset of decision variables and optimize the remaining ones via Mixed Integer Linear Programming (MILP). We solve the MILP problem at each iteration via an off-the-shelf MILP solver. Our experimental results show that our method significantly outperforms existing heuristic methods, employing either independent optimization or joint optimization strategies. We have also verified the generalization ability of our method over grid environments with various sizes and its high robustness to the algorithm hyper-parameters.

cs.DC↗

arXiv2025

Regularized Langevin Dynamics for Combinatorial Optimization

This work proposes a simple yet effective sampling framework for combinatorial optimization (CO). Our method builds on discrete Langevin dynamics (LD), an efficient gradient-guided generative paradigm. However, we observe that directly applying LD often leads to limited exploration. To overcome this limitation, we propose the Regularized Langevin Dynamics (RLD), which enforces an expected distance between the sampled and current solutions, effectively avoiding local minima. We develop two CO solvers on top of RLD, one based on simulated annealing (SA), and the other one based on neural network (NN). Empirical results on three classic CO problems demonstrate that both of our methods can achieve comparable or better performance against the previous state-of-the-art (SOTA) SA- and NN-based solvers. In particular, our SA algorithm reduces the runtime of the previous SOTA SA method by up to 80\%, while achieving equal or superior performance. In summary, RLD offers a promising framework for enhancing both traditional heuristics and NN models to solve CO problems. Our code is available at https://github.com/Shengyu-Feng/RLD4CO.

cs.LG↗

arXiv2024

SORREL: Suboptimal-Demonstration-Guided Reinforcement Learning for Learning to Branch

Mixed Integer Linear Program (MILP) solvers are mostly built upon a Branch-and-Bound (B\&B) algorithm, where the efficiency of traditional solvers heavily depends on hand-crafted heuristics for branching. The past few years have witnessed the increasing popularity of data-driven approaches to automatically learn these heuristics. However, the success of these methods is highly dependent on the availability of high-quality demonstrations, which requires either the development of near-optimal heuristics or a time-consuming sampling process. This paper averts this challenge by proposing Suboptimal-Demonstration-Guided Reinforcement Learning (SORREL) for learning to branch. SORREL selectively learns from suboptimal demonstrations based on value estimation. It utilizes suboptimal demonstrations through both offline reinforcement learning on the demonstrations generated by suboptimal heuristics and self-imitation learning on past good experiences sampled by itself. Our experiments demonstrate its advanced performance in both branching quality and training efficiency over previous methods for various MILPs.

cs.LG↗

arXiv2024

AI Surrogate Model for Distributed Computing Workloads

Large-scale international scientific collaborations, such as ATLAS, Belle II, CMS, and DUNE, generate vast volumes of data. These experiments necessitate substantial computational power for varied tasks, including structured data processing, Monte Carlo simulations, and end-user analysis. Centralized workflow and data management systems are employed to handle these demands, but current decision-making processes for data placement and payload allocation are often heuristic and disjointed. This optimization challenge potentially could be addressed using contemporary machine learning methods, such as reinforcement learning, which, in turn, require access to extensive data and an interactive environment. Instead, we propose a generative surrogate modeling approach to address the lack of training data and concerns about privacy preservation. We have collected and processed real-world job submission records, totaling more than two million jobs through 150 days, and applied four generative models for tabular data -- TVAE, CTAGGAN+, SMOTE, and TabDDPM -- to these datasets, thoroughly evaluating their performance. Along with measuring the discrepancy among feature-wise distributions separately, we also evaluate pair-wise feature correlations, distance to closest record, and responses to pre-trained models. Our experiments indicate that SMOTE and TabDDPM can generate similar tabular data, almost indistinguishable from the ground truth. Yet, as a non-learning method, SMOTE ranks the lowest in privacy preservation. As a result, we conclude that the probabilistic-diffusion-model-based TabDDPM is the most suitable generative model for managing job record data.

cs.DC↗

arXiv2024

Step-by-Step Reasoning for Math Problems via Twisted Sequential Monte Carlo

Augmenting the multi-step reasoning abilities of Large Language Models (LLMs) has been a persistent challenge. Recently, verification has shown promise in improving solution consistency by evaluating generated outputs. However, current verification approaches suffer from sampling inefficiencies, requiring a large number of samples to achieve satisfactory performance. Additionally, training an effective verifier often depends on extensive process supervision, which is costly to acquire. In this paper, we address these limitations by introducing a novel verification method based on Twisted Sequential Monte Carlo (TSMC). TSMC sequentially refines its sampling effort to focus exploration on promising candidates, resulting in more efficient generation of high-quality solutions. We apply TSMC to LLMs by estimating the expected future rewards at partial solutions. This approach results in a more straightforward training target that eliminates the need for step-wise human annotations. We empirically demonstrate the advantages of our method across multiple math benchmarks, and also validate our theoretical analysis of both our approach and existing verification methods.

cs.LG↗

arXiv2023

Concept Discovery for Fast Adapatation

The advances in deep learning have enabled machine learning methods to outperform human beings in various areas, but it remains a great challenge for a well-trained model to quickly adapt to a new task. One promising solution to realize this goal is through meta-learning, also known as learning to learn, which has achieved promising results in few-shot learning. However, current approaches are still enormously different from human beings' learning process, especially in the ability to extract structural and transferable knowledge. This drawback makes current meta-learning frameworks non-interpretable and hard to extend to more complex tasks. We tackle this problem by introducing concept discovery to the few-shot learning problem, where we achieve more effective adaptation by meta-learning the structure among the data features, leading to a composite representation of the data. Our proposed method Concept-Based Model-Agnostic Meta-Learning (COMAML) has been shown to achieve consistent improvements in the structured data for both synthesized datasets and real-world datasets.

cs.LG↗

arXiv2022

Exploiting Long-Term Dependencies for Generating Dynamic Scene Graphs

Dynamic scene graph generation from a video is challenging due to the temporal dynamics of the scene and the inherent temporal fluctuations of predictions. We hypothesize that capturing long-term temporal dependencies is the key to effective generation of dynamic scene graphs. We propose to learn the long-term dependencies in a video by capturing the object-level consistency and inter-object relationship dynamics over object-level long-term tracklets using transformers. Experimental results demonstrate that our Dynamic Scene Graph Detection Transformer (DSG-DETR) outperforms state-of-the-art methods by a significant margin on the benchmark dataset Action Genome. Our ablation studies validate the effectiveness of each component of the proposed approach. The source code is available at https://github.com/Shengyu-Feng/DSG-DETR.

cs.CV↗

arXiv2022

X-GOAL: Multiplex Heterogeneous Graph Prototypical Contrastive Learning

Graphs are powerful representations for relations among objects, which have attracted plenty of attention. A fundamental challenge for graph learning is how to train an effective Graph Neural Network (GNN) encoder without labels, which are expensive and time consuming to obtain. Contrastive Learning (CL) is one of the most popular paradigms to address this challenge, which trains GNNs by discriminating positive and negative node pairs. Despite the success of recent CL methods, there are still two under-explored problems. First, how to reduce the semantic error introduced by random topology based data augmentations. Traditional CL defines positive and negative node pairs via the node-level topological proximity, which is solely based on the graph topology regardless of the semantic information of node attributes, and thus some semantically similar nodes could be wrongly treated as negative pairs. Second, how to effectively model the multiplexity of the real-world graphs, where nodes are connected by various relations and each relation could form a homogeneous graph layer. To solve these problems, we propose a novel multiplex heterogeneous graph prototypical contrastive leaning (X-GOAL) framework to extract node embeddings. X-GOAL is comprised of two components: the GOAL framework, which learns node embeddings for each homogeneous graph layer, and an alignment regularization, which jointly models different layers by aligning layer-specific node embeddings. Specifically, the GOAL framework captures the node-level information by a succinct graph transformation technique, and captures the cluster-level information by pulling nodes within the same semantic cluster closer in the embedding space. The alignment regularization aligns embeddings across layers at both node and cluster levels. We evaluate X-GOAL on various real-world datasets and downstream tasks to demonstrate its effectiveness.

cs.LG↗