Feng Luo

EAAI Journal 2026 Journal Article

A novel framework for wave forecasting based on deep learning: A case study in the Gulf of Aden

• Feng Luo
• Yifan Qin
• Jian Shi
• Zhipeng Chen
• Yongzhi Wang
• Aifeng Tao
• Jinhai Zheng
• Lin Lv

Accurate forecasts of significant wave heights are essential for shipping and coastal engineering. This study introduces a novel convolutional neural network-long short-term memory-attention (CNN-LSTM-Attention) model for wave height prediction in the Gulf of Aden (GA). Experiments were conducted using data from the Jason3 satellite at five sea area intersections. The proposed model outperforms advanced deep learning architectures such as LSTM, CNN-LSTM, and LSTM-Attention, particularly in predicting wave height extremes. The average root mean square error (RMSE) value at points A1-A5 is 0. 061, leading to reductions of 48. 40 %, 32. 23 %, and 30. 39 % compared to LSTM, CNN-LSTM, and LSTM-Attention models, respectively. This CNN-LSTM-Attention model provides more precise wave height predictions and better identifies extreme points in short-term forecasts. It offers computational efficiency for real-time applications and long-term robustness, demonstrating its potential for coastal disaster prevention and mitigation. This study signifies a significant advancement in utilizing deep learning to improve wave height predictions.

NeurIPS Conference 2025 Conference Paper

Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry

• Chengyuan Deng
• Jie Gao
• Kevin Lu
• Feng Luo
• Cheng Xin

The Johnson-Lindenstrauss (JL) lemma is a cornerstone of dimensionality reduction in Euclidean space, but its applicability to non-Euclidean data has remained limited. This paper extends the JL lemma beyond Euclidean geometry to handle general dissimilarity matrices that are prevalent in real-world applications. We present two complementary approaches: First, we show how the JL transform can be applied to vectors in pseudo-Euclidean space with signature $(p, q)$, providing theoretical guarantees that depend on the ratio of the $(p, q)$ norm and Euclidean norm of two vectors, measuring the deviation from Euclidean geometry. Second, we prove that any symmetric hollow dissimilarity matrix can be represented as a matrix of generalized power distances, with an additional parameter representing the uncertainty level within the data. In this representation, applying the JL transform yields multiplicative approximation with a controlled additive error term proportional to the deviation from Euclidean geometry. Our theoretical results provide fine-grained performance analysis based on the degree to which the input data deviates from Euclidean geometry, making practical and meaningful reduction in dimensionality accessible to a wider class of data. We validate our approaches on both synthetic and real-world datasets, demonstrating the effectiveness of extending the JL lemma to non-Euclidean settings.

ICLR Conference 2025 Conference Paper

Latent Radiance Fields with 3D-aware 2D Representations

• Chaoyi Zhou
• Xi Liu
• Feng Luo
• Siyu Huang

Latent 3D reconstruction has shown great promise in empowering 3D semantic understanding and 3D generation by distilling 2D features into the 3D space. However, existing approaches struggle with the domain gap between 2D feature space and 3D representations, resulting in degraded rendering performance. To address this challenge, we propose a novel framework that integrates 3D awareness into the 2D latent space. The framework consists of three stages: (1) a correspondence-aware autoencoding method that enhances the 3D consistency of 2D latent representations, (2) a latent radiance field (LRF) that lifts these 3D-aware 2D representations into 3D space, and (3) a VAE-Radiance Field (VAE-RF) alignment strategy that improves image decoding from the rendered 2D representations. Extensive experiments demonstrate that our method outperforms the state-of-the-art latent 3D reconstruction approaches in terms of synthesis performance and cross-dataset generalizability across diverse indoor and outdoor scenes. To our knowledge, this is the first work showing the radiance field representations constructed from 2D latent representations can yield photorealistic 3D reconstruction performance.

ICLR Conference 2025 Conference Paper

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

• Jiawei Xu
• Rui Yang 0010
• Shuang Qiu
• Feng Luo
• Meng Fang
• Baoxiang Wang 0001
• Lei Han 0001

Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significant challenge for existing offline RL methods, particularly when the real-world data is limited. Our study reveals that prior research focusing on adapting predominant offline RL methods based on temporal difference learning still falls short under data corruption when the dataset is limited. In contrast, we discover that vanilla sequence modeling methods, such as Decision Transformer, exhibit robustness against data corruption, even without specialized modifications. To unlock the full potential of sequence modeling, we propose **R**obust **D**ecision **T**ransformer (**RDT**) by incorporating three simple yet effective robust techniques: embedding dropout to improve the model's robustness against erroneous inputs, Gaussian weighted learning to mitigate the effects of corrupted labels, and iterative data correction to eliminate corrupted data from the source. Extensive experiments on MuJoCo, Kitchen, and Adroit tasks demonstrate RDT's superior performance under various data corruption scenarios compared to prior methods. Furthermore, RDT exhibits remarkable robustness in a more challenging setting that combines training-time data corruption with test-time observation perturbations. These results highlight the potential of sequence modeling for learning from noisy or corrupted offline datasets, thereby promoting the reliable application of offline RL in real-world scenarios. Our code is available at https://github.com/jiawei415/RobustDecisionTransformer。

ICML Conference 2024 Conference Paper

Directly Denoising Diffusion Models

• Dan Zhang
• Jingjing Wang
• Feng Luo

In this paper, we present Directly Denoising Diffusion Models (DDDMs): a simple and generic approach for generating realistic images with few-step sampling, while multistep sampling is still preserved for better performance. DDDMs require no delicately designed samplers nor distillation on pre-trained distillation models. DDDMs train the diffusion model conditioned on an estimated target that was generated from previous training iterations of its own. To generate images, samples generated from previous timestep are also taken into consideration, guiding the generation process iteratively. We further propose Pseudo-LPIPS, a novel metric loss that is more robust to various values of hyperparameter. Despite its simplicity, the proposed approach can achieve strong performance in benchmark datasets. Our model achieves FID scores of 2. 57 and 2. 33 on CIFAR-10 in one-step and two-step sampling respectively, surpassing those obtained from GANs and distillation-based models. By extending the sampling to 1000 steps, we further reduce FID score to 1. 79, aligning with state-of-the-art methods in the literature. For ImageNet 64x64, our approach stands as a competitive contender against leading models.

NeurIPS Conference 2024 Conference Paper

Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms

• Chengyuan Deng
• Jie Gao
• Kevin Lu
• Feng Luo
• Hongbin Sun
• Cheng Xin

We introduce \textbf{N}on-\textbf{Euc}lidean-\textbf{MDS} (Neuc-MDS), which extends Multidimensional Scaling (MDS) to generate outputs that can be non-Euclidean and non-metric. The main idea is to generalize the inner product to other symmetric bilinear forms to utilize the negative eigenvalues of dissimiliarity Gram matrices. Neuc-MDS efficiently optimizes the choice of (both positive and negative) eigenvalues of the dissimilarity Gram matrix to reduce STRESS, the sum of squared pairwise error. We provide an in-depth error analysis and proofs of the optimality in minimizing lower bounds of STRESS. We demonstrate Neuc-MDS's ability to address limitations of classical MDS raised by prior research, and test it on various synthetic and real-world datasets in comparison with both linear and non-linear dimension reduction methods.

ICML Conference 2024 Conference Paper

Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

• Rui Yang 0010
• Xiaoman Pan
• Feng Luo
• Shuang Qiu
• Han Zhong 0001
• Dong Yu 0001
• Jianshu Chen

We consider the problem of multi-objective alignment of foundation models with human preferences, which is a critical step towards helpful and harmless AI systems. However, it is generally costly and unstable to fine-tune large foundation models using reinforcement learning (RL), and the multi-dimensionality, heterogeneity, and conflicting nature of human preferences further complicate the alignment process. In this paper, we introduce Rewards-in-Context (RiC), which conditions the response of a foundation model on multiple rewards in its prompt context and applies supervised fine-tuning for alignment. The salient features of RiC are simplicity and adaptivity, as it only requires supervised fine-tuning of a single foundation model and supports dynamic adjustment for user preferences during inference time. Inspired by the analytical solution of an abstracted convex optimization problem, our dynamic inference-time adjustment method approaches the Pareto-optimal solution for multiple objectives. Empirical evidence demonstrates the efficacy of our method in aligning both Large Language Models (LLMs) and diffusion models to accommodate diverse rewards with only around 10% GPU hours compared with multi-objective RL baseline.

AAAI Conference 2022 Conference Paper

HoD-Net: High-Order Differentiable Deep Neural Networks and Applications

• Siyuan Shen
• Tianjia Shao
• Kun Zhou
• Chenfanfu Jiang
• Feng Luo
• Yin Yang

We introduce a deep architecture named HoD-Net to enable high-order differentiability for deep learning. HoD-Net is based on and generalizes the complex-step finite difference (CSFD) method. While similar to classic finite difference, CSFD approaches the derivative of a function from a higher-dimension complex domain, leading to highly accurate and robust differentiation computation without numerical stability issues. This method can be coupled with backpropagation and adjoint perturbation methods for an efficient calculation of high-order derivatives. We show how this numerical scheme can be leveraged in challenging deep learning problems, such as high-order network training, deep learningbased physics simulation, and neural differential equations.

YNIMG Journal 2004 Journal Article

Attenuation of brain response to heroin correlates with the reinstatement of heroin-seeking in rats by fMRI

• Feng Luo
• Zheng-Xiong Xi
• Gaohong Wu
• Chuang Liu
• Eliot L Gardner
• Shi-Jiang Li