arXiv subjects

Yize Chen

Publications and source records attributed to Yize Chen.

At least 37 records · Page 2Linked to original sources

arXiv2025

Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP

Existing neural methods for multi-task vehicle routing problems (VRPs) typically learn unified solvers to handle multiple constraints simultaneously. However, they often underutilize the compositional structure of VRP variants, each derivable from a common set of basis VRP variants. This critical oversight causes unified solvers to miss out the potential benefits of basis solvers, each specialized for a basis VRP variant. To overcome this limitation, we propose a framework that enables unified solvers to perceive the shared-component nature across VRP variants by proactively reusing basis solvers, while mitigating the exponential growth of trained neural solvers. Specifically, we introduce a State-Decomposable MDP (SDMDP) that reformulates VRPs by expressing the state space as the Cartesian product of basis state spaces associated with basis VRP variants. More crucially, this formulation inherently yields the optimal basis policy for each basis VRP variant. Furthermore, a Latent Space-based SDMDP extension is developed by incorporating both the optimal basis policies and a learnable mixture function to enable the policy reuse in the latent space. Under mild assumptions, this extension provably recovers the optimal unified policy of SDMDP through the mixture function that computes the state embedding as a mapping from the basis state embeddings generated by optimal basis policies. For practical implementation, we introduce the Mixture-of-Specialized-Experts Solver (MoSES), which realizes basis policies through specialized Low-Rank Adaptation (LoRA) experts, and implements the mixture function via an adaptive gating mechanism. Extensive experiments conducted across VRP variants showcase the superiority of MoSES over prior methods.

cs.AI↗

arXiv2025

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

With the rapid advancement of Artificial Intelligence Generated Content (AIGC) technologies, synthetic images have become increasingly prevalent in everyday life, posing new challenges for authenticity assessment and detection. Despite the effectiveness of existing methods in evaluating image authenticity and locating forgeries, these approaches often lack human interpretability and do not fully address the growing complexity of synthetic data. To tackle these challenges, we introduce FakeVLM, a specialized large multimodal model designed for both general synthetic image and DeepFake detection tasks. FakeVLM not only excels in distinguishing real from fake images but also provides clear, natural language explanations for image artifacts, enhancing interpretability. Additionally, we present FakeClue, a comprehensive dataset containing over 100,000 images across seven categories, annotated with fine-grained artifact clues in natural language. FakeVLM demonstrates performance comparable to expert models while eliminating the need for additional classifiers, making it a robust solution for synthetic data detection. Extensive evaluations across multiple datasets confirm the superiority of FakeVLM in both authenticity classification and artifact explanation tasks, setting a new benchmark for synthetic image detection. The code, model weights, and dataset can be found here: https://github.com/opendatalab/FakeVLM.

cs.CV↗

arXiv2025

From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes

Detecting deepfakes has been an increasingly important topic, especially given the rapid development of AI generation techniques. In this paper, we ask: How can we build a universal detection framework that is effective for most facial deepfakes? One significant challenge is the wide variety of deepfake generators available, resulting in varying forgery artifacts (e.g., lighting inconsistency, color mismatch, etc). But should we ``teach" the detector to learn all these artifacts separately? It is impossible and impractical to elaborate on them all. So the core idea is to pinpoint the more common and general artifacts across different deepfakes. Accordingly, we categorize deepfake artifacts into two distinct yet complementary types: Face Inconsistency Artifacts (FIA) and Up-Sampling Artifacts (USA). FIA arise from the challenge of generating all intricate details, inevitably causing inconsistencies between the complex facial features and relatively uniform surrounding areas. USA, on the other hand, are the inevitable traces left by the generator's decoder during the up-sampling process. This categorization stems from the observation that all existing deepfakes typically exhibit one or both of these artifacts. To achieve this, we propose a new data-level pseudo-fake creation framework that constructs fake samples with only the FIA and USA, without introducing extra less-general artifacts. Specifically, we employ a super-resolution to simulate the USA, while design a Blender module that uses image-level self-blending on diverse facial regions to create the FIA. We surprisingly found that, with this intuitive design, a standard image classifier trained only with our pseudo-fake data can non-trivially generalize well to unseen deepfakes.

cs.CV↗

arXiv2025

Carbon Emission Flow Tracing: Fast Algorithm and California Grid Study

Power systems decarbonization are at the focal point of the clean energy transition. While system operators and utility companies increasingly publicize system-level carbon emission information, it remains unclear how emissions from individual generators are transported through the grid and how they impact electricity users at specific locations. This paper presents a novel and computationally efficient approach for exact quantification of nodal average and marginal carbon emission rates, applicable to both AC and DC optimal power flow problems. The approach leverages graph-based topological sorting and directed cycle removal techniques, applied to directed graphs formed by generation dispatch and optimal power flow solutions. Our proposed algorithm efficiently identifies each generator's contribution to each node, capturing how emissions are spatially distributed under varying system conditions. To validate its effectiveness and reveal locational and temporal emission patterns in the real world, we simulate the 8,870-bus realistic California grid using actual CAISO data and the CATS model. Based on year long hourly data on nodal loads and renewable generation, obtained or estimated from CAISO public data, our method accurately estimates power flow conditions, generation mixes, and systemwide emissions, and delivers fine grained spatiotemporal emission analysis for every California county. Both our algorithm and the California study are open-sourced, providing a foundation for future research on grid emissions, planning, operations, and energy policy.

eess.SY↗

arXiv2025

BEAVER: Building Environments with Assessable Variation for Evaluating Multi-Objective Reinforcement Learning

Recent years have seen significant advancements in designing reinforcement learning (RL)-based agents for building energy management. While individual success is observed in simulated or controlled environments, the scalability of RL approaches in terms of efficiency and generalization across building dynamics and operational scenarios remains an open question. In this work, we formally characterize the generalization space for the cross-environment, multi-objective building energy management task, and formulate the multi-objective contextual RL problem. Such a formulation helps understand the challenges of transferring learned policies across varied operational contexts such as climate and heat convection dynamics under multiple control objectives such as comfort level and energy consumption. We provide a principled way to parameterize such contextual information in realistic building RL environments, and construct a novel benchmark to facilitate the evaluation of generalizable RL algorithms in practical building control tasks. Our results show that existing multi-objective RL methods are capable of achieving reasonable trade-offs between conflicting objectives. However, their performance degrades under certain environment variations, underscoring the importance of incorporating dynamics-dependent contextual information into the policy learning process.

cs.LG↗

arXiv2025

Fast Distribution Grid Topology Estimation via Subset Sum

Faced with increasing penetration of distributed energy resources and fast development of distribution grid energy management, topology identification of distribution grid becomes an important and fundamental task. As the underlying grid topology is usually unknown or incomplete to the utilities, it is becoming a fundamental task to efficiently identify the distribution grid network topology using limited measurements. A fast and accurate topology identification can help achieving the tasks of load monitoring, operation and control of power distribution system as well as outage detection. In this paper, we propose a novel and ultra-fast topology identification method. By adapting the subset sum method with a hierarchical structure, the overall grid topology can be inferred from fewer samples of smart meter power measurements. Such techniques can be applied in real time under the scenarios with fast topology change, and the proposed hierarchical algorithm is also robust against measurement noises.

eess.SY↗

arXiv2025

Vertex-Guided Redundant Constraints Identification for Unit Commitment

Power systems Unit Commitment (UC) problem determines the generator commitment schedule and dispatch decisions to realize the reliable and economic operation of power networks. The growing penetration of stochastic renewables and demand behaviors makes it necessary to solve the UC problem timely. It is possible to derive lightweight, faster-to-solve UC models via constraint screening to eliminate redundant constraints. However, the screening process remains computationally cumbersome due to the need of solving numerous linear programming (LP) problems. To reduce the number of LPs to solve, we introduce a novel perspective on such classic LP-based screening. Our key insights lie in the principle that redundant constraints will be satisfied by all vertices of the screened feasible region. Using the UC decision variables' bounds tightened by solving much fewer LPs, we build an outer approximation for the UC feasible region as the screened region. A matrix operation is then designed and applied to the outer approximation's vertices to identify all redundant constraints on-the-fly. Adjustments for the outer approximation are further explored to improve screening efficiency by considering the load operating range and cutting planes derived from UC cost and discrete unit status prediction. Extensive simulations are performed on a set of testbeds up to 2,383 buses to substantiate the effectiveness of the proposed schemes. Compared to classic LP-based screening, our schemes can achieve up to 8.8x acceleration while finding the same redundant constraints.

eess.SY↗

arXiv2025

Voltage Regulation in Distribution Systems with Data Center Loads

Recent boom in foundation models and AI computing have raised growing concerns on the power and energy trajectories of large-scale data centers. This paper focuses on the voltage issues caused by volatile and intensity of data center power demand, which also aligns with recent observations of more frequent voltage disturbances in power grids. To address these data center integration challenges, we propose a dynamic voltage control scheme by harnessing data center's load regulation capabilities. By taking local voltage measurements and adjusting power injections at each data center buses through the dynamic voltage and frequency scaling (DVFS) scheme, we are able to maintain safe voltage magnitude in a distributed fashion with higher data center computing load. Simulations using real large language model (LLM) inference load validate the effectiveness of our proposed mechanism. Both the LLM power data and proposed control scheme are open sourced.

eess.SY↗

arXiv2025

Exploring Compositional Generalization of Multimodal LLMs for Medical Imaging

Medical imaging provides essential visual insights for diagnosis, and multimodal large language models (MLLMs) are increasingly utilized for its analysis due to their strong generalization capabilities; however, the underlying factors driving this generalization remain unclear. Current research suggests that multi-task training outperforms single-task as different tasks can benefit each other, but they often overlook the internal relationships within these tasks. To analyze this phenomenon, we attempted to employ compositional generalization (CG), which refers to the models' ability to understand novel combinations by recombining learned elements, as a guiding framework. Since medical images can be precisely defined by Modality, Anatomical area, and Task, naturally providing an environment for exploring CG, we assembled 106 medical datasets to create Med-MAT for comprehensive experiments. The experiments confirmed that MLLMs can use CG to understand unseen medical images and identified CG as one of the main drivers of the generalization observed in multi-task training. Additionally, further studies demonstrated that CG effectively supports datasets with limited data and confirmed that MLLMs can achieve CG across classification and detection tasks, underscoring its broader generalization potential. Med-MAT is available at https://github.com/FreedomIntelligence/Med-MAT.

cs.CV↗

arXiv2025

X2-DFD: A framework for eXplainable and eXtendable Deepfake Detection

This paper proposes X2-DFD, an eXplainable and eXtendable framework based on multimodal large-language models (MLLMs) for deepfake detection, consisting of three key stages. The first stage, Model Feature Assessment, systematically evaluates the detectability of forgery-related features for the MLLM, generating a prioritized ranking of features based on their intrinsic importance to the model. The second stage, Explainable Dataset Construction, consists of two key modules: Strong Feature Strengthening, which is designed to enhance the model's existing detection and explanation capabilities by reinforcing its well-learned features, and Weak Feature Supplementing, which addresses gaps by integrating specific feature detectors (e.g., low-level artifact analyzers) to compensate for the MLLM's limitations. The third stage, Fine-tuning and Inference, involves fine-tuning the MLLM on the constructed dataset and deploying it for final detection and explanation. By integrating these three stages, our approach enhances the MLLM's strengths while supplementing its weaknesses, ultimately improving both the detectability and explainability. Extensive experiments and ablations, followed by a comprehensive human study, validate the improved performance of our approach compared to the original MLLMs. More encouragingly, our framework is designed to be plug-and-play, allowing it to seamlessly integrate with future more advanced MLLMs and specific feature detectors, leading to continual improvement and extension to face the challenges of rapidly evolving deepfakes.

cs.CV↗

arXiv2025

Long Term Memory: The Foundation of AI Self-Evolution

Large language models (LLMs) like GPTs, trained on vast datasets, have demonstrated impressive capabilities in language understanding, reasoning, and planning, achieving human-level performance in various tasks. Most studies focus on enhancing these models by training on ever-larger datasets to build more powerful foundation models. While training stronger models is important, enabling models to evolve during inference is equally crucial, a process we refer to as AI self-evolution. Unlike large-scale training, self-evolution may rely on limited data or interactions. Inspired by the columnar organization of the human cerebral cortex, we hypothesize that AI models could develop cognitive abilities and build internal representations through iterative interactions with their environment. To achieve this, models need long-term memory (LTM) to store and manage processed interaction data. LTM supports self-evolution by representing diverse experiences across environments and agents. In this report, we explore AI self-evolution and its potential to enhance models during inference. We examine LTM's role in lifelong learning, allowing models to evolve based on accumulated interactions. We outline the structure of LTM and the systems needed for effective data retention and representation. We also classify approaches for building personalized models with LTM data and show how these models achieve self-evolution through interaction. Using LTM, our multi-agent framework OMNE achieved first place on the GAIA benchmark, demonstrating LTM's potential for AI self-evolution. Finally, we present a roadmap for future research, emphasizing the importance of LTM for advancing AI technology and its practical applications.

cs.AI↗

arXiv2025

C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front

Multi-objective reinforcement learning (MORL) excels at handling rapidly changing preferences in tasks that involve multiple criteria, even for unseen preferences. However, previous dominating MORL methods typically generate a fixed policy set or preference-conditioned policy through multiple training iterations exclusively for sampled preference vectors, and cannot ensure the efficient discovery of the Pareto front. Furthermore, integrating preferences into the input of policy or value functions presents scalability challenges, in particular as the dimension of the state and preference space grow, which can complicate the learning process and hinder the algorithm's performance on more complex tasks. To address these issues, we propose a two-stage Pareto front discovery algorithm called Constrained MORL (C-MORL), which serves as a seamless bridge between constrained policy optimization and MORL. Concretely, a set of policies is trained in parallel in the initialization stage, with each optimized towards its individual preference over the multiple objectives. Then, to fill the remaining vacancies in the Pareto front, the constrained optimization steps are employed to maximize one objective while constraining the other objectives to exceed a predefined threshold. Empirically, compared to recent advancements in MORL methods, our algorithm achieves more consistent and superior performances in terms of hypervolume, expected utility, and sparsity on both discrete and continuous control tasks, especially with numerous objectives (up to nine objectives in our experiments).

cs.LG↗

arXiv2025

Open Datasets for Grid Modeling and Visualization: An Alberta Power Network Case

In the power and energy industry, multiple entities in grid operational logs are frequently recorded and updated. Thanks to recent advances in IT facilities and smart metering services, a variety of datasets such as system load, generation mix, and grid connection are often publicly available. While these resources are valuable in evaluating power grid's operational conditions and system resilience, the lack of fine-grained, accurate locational information constrain the usage of current data, which further hinders the development of smart grid and renewables integration. For instance, electricity end users are not aware of nodal generation mix or carbon emissions, while the general public have limited understanding about the effect of demand response or renewables integration if only the whole system's demands and generations are available. In this work, we focus on recovering power grid topology and line flow directions from open public dataset. Taking the Alberta grid as a working example, we start from mapping multi-modal power system datasets to the grid topology integrated with geographical information. By designing a novel optimization-based scheme to recover line flow directions, we are able to analyze and visualize the interactions between generations and demand vectors in an efficient manner. Proposed research is fully open-sourced and highly generalizable, which can help model and visualize grid information, create synthetic dataset, and facilitate analytics and decision-making framework for clean energy transition.

cs.HC↗

arXiv2025

Short-Term Load Forecasting for AI-Data Center

Recent research shows large-scale AI-centric data centers could experience rapid fluctuations in power demand due to varying computation loads, such as sudden spikes from inference or interruption of training large language models (LLMs). As a consequence, such huge and fluctuating power demand pose significant challenges to both data center and power utility operation. Accurate short-term power forecasting allows data centers and utilities to dynamically allocate resources and power large computing clusters as required. However, due to the complex data center power usage patterns and the black-box nature of the underlying AI algorithms running in data centers, explicit modeling of AI-data center is quite challenging. Alternatively, to deal with this emerging load forecasting problem, we propose a data-driven workflow to model and predict the short-term electricity load in an AI-data center, and such workflow is compatible with learning-based algorithms such as LSTM, GRU, 1D-CNN. We validate our framework, which achieves decent accuracy on data center GPU short-term power consumption. This provides opportunity for improved power management and sustainable data center operations.

eess.SP↗

arXiv2025

Hierarchical Learning-based Graph Partition for Large-scale Vehicle Routing Problems

Neural solvers based on the divide-and-conquer approach for Vehicle Routing Problems (VRPs) in general, and capacitated VRP (CVRP) in particular, integrates the global partition of an instance with local constructions for each subproblem to enhance generalization. However, during the global partition phase, misclusterings within subgraphs have a tendency to progressively compound throughout the multi-step decoding process of the learning-based partition policy. This suboptimal behavior in the global partition phase, in turn, may lead to a dramatic deterioration in the performance of the overall decomposition-based system, despite using optimal local constructions. To address these challenges, we propose a versatile Hierarchical Learning-based Graph Partition (HLGP) framework, which is tailored to benefit the partition of CVRP instances by synergistically integrating global and local partition policies. Specifically, the global partition policy is tasked with creating the coarse multi-way partition to generate the sequence of simpler two-way partition subtasks. These subtasks mark the initiation of the subsequent K local partition levels. At each local partition level, subtasks exclusive for this level are assigned to the local partition policy which benefits from the insensitive local topological features to incrementally alleviate the compounded errors. This framework is versatile in the sense that it optimizes the involved partition policies towards a unified objective harmoniously compatible with both reinforcement learning (RL) and supervised learning (SL). (*Due to the notification of arXiv "The Abstract field cannot be longer than 1,920 characters", the appeared Abstract is shortened. For the full Abstract, please download the Article.)

cs.LG↗

arXiv2024

Is Locational Marginal Price All You Need for Locational Marginal Emission?

Growing concerns over climate change call for improved techniques for estimating and quantifying the greenhouse gas emissions associated with electricity generation and transmission. Among the emission metrics designated for power grids, locational marginal emission (LME) can provide system operators and electricity market participants with valuable information on the emissions associated with electricity usage at various locations in the power network. In this paper, by investigating the operating patterns and physical interpretations of marginal emissions and costs in the security-constrained economic dispatch (SCED) problem, we identify and draw the exact connection between locational marginal price (LMP) and LME. Such interpretation helps instantly derive LME given nodal demand vectors or LMP, and also reveals the interplay between network congestion and nodal emission pattern. Our proposed approach helps reduce the computation time of LME by an order of magnitude compared to analytical approaches, while it can also serve as a plug-and-play module accompanied by an off-the-shelf market clearing and LMP calculation process.

eess.SY↗

arXiv2024

Implementing Deep Reinforcement Learning-Based Grid Voltage Control in Real-World Power Systems: Challenges and Insights

Deep reinforcement learning (DRL) holds significant promise for managing voltage control challenges in simulated power grid environments. However, its real-world application in power system operations remains underexplored. This study rigorously evaluates DRL's performance and limitations within actual operational contexts by utilizing detailed experiments across the IEEE 14-bus system, Illinois 200-bus system, and the ISO New England node-breaker model. Our analysis critically assesses DRL's effectiveness for grid control from a system operator's perspective, identifying specific performance bottlenecks. The findings provide actionable insights that highlight the necessity of advancing AI technologies to effectively address the growing complexities of modern power systems. This research underscores the vital role of DRL in enhancing grid management and reliability.

eess.SY↗

arXiv2024

Channel-aware Contrastive Conditional Diffusion for Multivariate Probabilistic Time Series Forecasting

Forecasting faithful trajectories of multivariate time series from practical scopes is essential for reasonable decision-making. Recent methods majorly tailor generative conditional diffusion models to estimate the target temporal predictive distribution. However, it remains an obstacle to enhance the exploitation efficiency of given implicit temporal predictive information to bolster conditional diffusion learning. To this end, we propose a generic channel-aware Contrastive Conditional Diffusion model entitled CCDM to achieve desirable Multivariate probabilistic forecasting, obviating the need for curated temporal conditioning inductive biases. In detail, we first design a channel-centric conditional denoising network to manage intra-variate variations and cross-variate correlations, which can lead to scalability on diverse prediction horizons and channel numbers. Then, we devise an ad-hoc denoising-based temporal contrastive learning to explicitly amplify the predictive mutual information between past observations and future forecasts. It can coherently complement naive step-wise denoising diffusion training and improve the forecasting accuracy and generality on unknown test time series. Besides, we offer theoretic insights on the benefits of such auxiliary contrastive training refinement from both neural mutual information and temporal distribution generalization aspects. The proposed CCDM can exhibit superior forecasting capability compared to current state-of-the-art diffusion forecasters over a comprehensive benchmark, with best MSE and CRPS outcomes on $66.67\%$ and $83.33\%$ cases. Our code is publicly available at https://github.com/LSY-Cython/CCDM.

cs.LG↗