Author name cluster

Caihua Chen

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.

4 papers

1 author row

AAAI Conference 2026 Conference Paper

Conditional Diffusion Model for Multi-Agent Dynamic Task Decomposition

Yanda Zhu
Yuanyang Zhu
Daoyi Dong
Caihua Chen
Chunlin Chen

Task decomposition has shown promise in complex cooperative multi-agent reinforcement learning (MARL) tasks, which enables efficient hierarchical learning for long-horizon tasks in dynamic and uncertain environments. However, learning dynamic task decomposition from scratch generally requires a large number of training samples, especially exploring the large joint action space under partial observability. In this paper, we present the Conditional Diffusion Model for Dynamic Task Decomposition (CD3T), a novel two-level hierarchical MARL framework designed to automatically infer subtask and coordination patterns. The high-level policy learns subtask representation to generate a subtask selection strategy based on subtask effects. To capture the effects of subtasks on the environment, CD3T predicts the next observation and reward using a conditional diffusion model. At the low level, agents collaboratively learn and share specialized skills within their assigned subtasks. Moreover, the learned subtask representation is also used as additional semantic information in a multi-head attention mixing network to enhance value decomposition and provide an efficient reasoning bridge between individual and joint value functions. Experimental results on various benchmarks demonstrate that CD3T achieves better performance than existing baselines.

PDF Details DOI

EAAI Journal 2026 Journal Article

Distribution adversarial gating enhanced prediction model for carbon emission with multi-agent automated modeling framework

Qingyang Wang
Piaoyang Zhao
Chengxi She
Yang Chen
Xiangyu Kong
Xuedong Wang
Caihua Chen

To address these limitations of tough prediction of data under different distributions and high cost of modeling and coding complex customized prediction model, this paper proposes a unified approach integrating four crucial components: customized feature processor, multi-stage carbon measurement model, distribution adversarial gating (DAG) enhanced prediction model, and multi-agent automated modeling framework. Firstly, we construct a comprehensive knowledge base containing various carbon emission factors and standards together with external carbon-related data portals for retrieval. Secondly, we propose a multi-stage carbon measurement model based on knowledge base constructed to generate accurate carbon emission labels for prediction model training. Thirdly, we propose DAG enhanced Long Short-Term Memory Neural Network (DAG-LSTM), which ensures favorable prediction of pre-trained models on different test data under different distributions. Lastly, we design a multi-agent framework leveraging Large Language Models (LLMs) for automated modeling and coding, which significantly reduces the technical barriers to application. We evaluate our approach using real-world power grid datasets from 2021–2024. The results demonstrate that our automated modeling framework achieves implementing carbon emission prediction with only a few simple instructions and DAG-LSTM reduces prediction errors with different data distribution by at least 69. 3% and at most 92. 6%. Our work provides both a novel prediction architecture and an intelligent modeling paradigm, contributing to scalable, accurate, and accessible carbon emission prediction in diverse industrial scenarios.

Details DOI

NeurIPS Conference 2025 Conference Paper

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang
Siyuan Liang
Yaning Tan
Zhaowei Chen
Linze Li
Ge Wu
Yuhao Chen
Shuheng Li

Diffusion transformers (DiTs) struggle to generate images at resolutions higher than their training resolutions. The primary obstacle is that the explicit positional encodings (PE), such as RoPE, need extrapolating to unseen positions which degrades performance when the inference resolution differs from training. In this paper, We propose a Length-Extrapolatable Diffusion Transformer (LEDiT) to overcome this limitation. LEDiT needs no explicit PEs, thereby avoiding PE extrapolation. The key innovation of LEDiT lies in the use of causal attention. We demonstrate that causal attention can implicitly encode global positional information and show that such information facilitates extrapolation. We further introduce a locality enhancement module, which captures fine-grained local information to complement the global coarse-grained position information encoded by causal attention. Experimental results on both conditional and text-to-image generation tasks demonstrate that LEDiT supports up to 4× resolution scaling (e. g. , from 256$\times$256 to 512$\times$512), achieving better image quality compared to the state-of-the-art length extrapolation methods. We believe that LEDiT marks a departure from the standard RoPE-based methods and offers a promising insight into length extrapolation. Project page: https: //shenzhang2145. github. io/ledit/

PDF Details

NeurIPS Conference 2020 Conference Paper

Fast Epigraphical Projection-based Incremental Algorithms for Wasserstein Distributionally Robust Support Vector Machine

Jiajin Li
Caihua Chen
Anthony Man-Cho So

Wasserstein \textbf{D}istributionally \textbf{R}obust \textbf{O}ptimization (DRO) is concerned with finding decisions that perform well on data that are drawn from the worst probability distribution within a Wasserstein ball centered at a certain nominal distribution. In recent years, it has been shown that various DRO formulations of learning models admit tractable convex reformulations. However, most existing works propose to solve these convex reformulations by general-purpose solvers, which are not well-suited for tackling large-scale problems. In this paper, we focus on a family of Wasserstein distributionally robust support vector machine (DRSVM) problems and propose two novel epigraphical projection-based incremental algorithms to solve them. The updates in each iteration of these algorithms can be computed in a highly efficient manner. Moreover, we show that the DRSVM problems considered in this paper satisfy a Hölderian growth condition with explicitly determined growth exponents. Consequently, we are able to establish the convergence rates of the proposed incremental algorithms. Our numerical results indicate that the proposed methods are orders of magnitude faster than the state-of-the-art, and the performance gap grows considerably as the problem size increases.

PDF Details