Author name cluster

Xiangyu 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.

17 papers

2 author rows

EAAI Journal 2026 Journal Article

An improved retrieval-augmented long-term grouting power prediction method: Rejecting low-similarity retrievals

Baoxi Liu
Liangsi Xu
Bingyu Ren
Chengyu Yu
Hongling Yu
Xiangyu Chen
Xinyu Liu

Grouting power long-term prediction is beneficial to regulating power output. Traditional long-term prediction methods require iterative updates with newly accumulated data during construction, which is time-consuming. Retrieval-augmented methods not only achieve higher prediction accuracy but also enable more efficient performance upgrades through database updates, avoiding the need to retrain models. However, conventional retrieval augmented frameworks unconditionally incorporate retrieved sequences into the prediction process, even when their similarity to the query is low. This design choice can introduce noisy or irrelevant historical patterns, misleading the fusion mechanism and degrading overall performance. To address this issue, this study proposes a retrieval-augmented method for long-term grouting power prediction with a rejection-substitution mechanism. Compared with the naive retrieval augmented prediction method, this mechanism enables selective fusion of retrievals by evaluating the similarity of each retrieved sequence before integration. If the similarity falls below a predefined threshold, the corresponding result is substituted with a prediction from the TimeXer model. Otherwise, the retrieved result is retained. The processed results are then fused by a Gate Recurrent Unit network to generate the final prediction. To validate the effectiveness of the proposed method, experiments were conducted on both a grouting power dataset and a publicly accessible dataset. The results indicate that incorporating a rejection-substitution mechanism enhances the prediction accuracy compared to the traditional retrieval-augmented prediction approach.

Details DOI

AAAI Conference 2026 Conference Paper

LatentLLM: Activation-Aware Transform to Multi-Head Latent Attention

Toshiaki Koike-Akino
Xiangyu Chen
Jing Liu
Ye Wang
Pu (Perry) Wang
Matthew Brand

Modern foundation models such as large language models (LLMs) require a massive amount of computational and memory resources. We propose a new framework to convert such LLMs into a reduced-dimension latent structure. Our method extends a local activation-aware tensor decomposition to a global attention-aware joint tensor decomposition. Our framework can significantly improve the model accuracy over the existing model compression methods when reducing the latent dimension to realize computationally/memory-efficient LLMs. We show the benefit on several benchmark including multi-modal reasoning tasks.

PDF Details DOI

AAAI Conference 2025 Conference Paper

Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression

Chuqin Zhou
Guo Lu
Jiangchuan Li
Xiangyu Chen
Zhengxue Cheng
Li Song
Wenjun Zhang

Neural image compression often faces a challenging trade-off among rate, distortion and perception. While most existing methods typically focus on either achieving high pixel-level fidelity or optimizing for perceptual metrics, we propose a novel approach that simultaneously addresses both aspects for a fixed neural image codec. Specifically, we introduce a plug-and-play module at the decoder side that leverages a latent diffusion process to transform the decoded features, enhancing either low distortion or high perceptual quality without altering the original image compression codec. Our approach facilitates fusion of original and transformed features without additional training, enabling users to flexibly adjust the balance between distortion and perception during inference. Extensive experimental results demonstrate that our method significantly enhances the pretrained codecs with a wide, adjustable distortion-perception range while maintaining their original compression capabilities. For instance, we can achieve more than 150% improvement in LPIPS-BDRate without sacrificing more than 1 dB in PSNR.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings

Yanru Wu
Jianning Wang
Xiangyu Chen
Yang Tan
Hanbing Liu
Yang Li

Continual learning (CL) has been a critical topic in contemporary deep neural network applications, where higher levels of both forward and backward transfer are desirable for an effective CL performance. Existing CL strategies primarily focus on task models — either by regularizing model updates or by separating task-specific and shared components — while often overlooking the potential of leveraging inter-task relationships to enhance transfer. To address this gap, we propose a transferability-aware task embedding, termed H-embedding, and construct a hypernet framework under its guidance to learn task-conditioned model weights for CL tasks. Specifically, H-embedding is derived from an information theoretic measure of transferability and is designed to be online and easy to compute. Our method is also characterized by notable practicality, requiring only the storage of a low-dimensional task embedding per task and supporting efficient end-to-end training. Extensive evaluations on benchmarks including CIFAR-100, ImageNet-R, and DomainNet show that our framework performs prominently compared to various baseline and SOTA approaches, demonstrating strong potential in capturing and utilizing intrinsic task relationships. Our code is publicly available at \url{https: //github. com/viki760/Hembedding Guided Hypernet}.

PDF Details

ICLR Conference 2025 Conference Paper

WeatherGFM: Learning a Weather Generalist Foundation Model via In-context Learning

Xiangyu Zhao
Zhiwang Zhou
Wenlong Zhang
Yihao Liu
Xiangyu Chen
Junchao Gong
Hao Chen 0045
Ben Fei

The Earth's weather system involves intricate weather data modalities and diverse weather understanding tasks, which hold significant value to human life. Existing data-driven models focus on single weather understanding tasks (e.g., weather forecasting). While these models have achieved promising results, they fail to tackle various complex tasks within a single and unified model. Moreover, the paradigm that relies on limited real observations for a single scenario hinders the model's performance upper bound. Inspired by the in-context learning paradigm from visual foundation models and large language models, in this paper, we introduce the first generalist weather generalist foundation model (WeatherGFM) to address weather understanding tasks in a unified manner. Specifically, we first unify the representation and definition for diverse weather understanding tasks. Subsequently, we design weather prompt formats to handle different weather data modalities, including single, multiple, and temporal modalities. Finally, we adopt a visual prompting question-answering paradigm for the training of unified weather understanding tasks. Extensive experiments indicate that our WeatherGFM can effectively handle up to 12 weather understanding tasks, including weather forecasting, super-resolution, weather image translation, and post-processing. Our method also showcases generalization ability on unseen tasks. The source code is available at https://github.com/xiangyu-mm/WeatherGFM.

Details

ICRA Conference 2024 Conference Paper

Block-Map-Based Localization in Large-Scale Environment

Yixiao Feng
Zhou Jiang
Yongliang Shi
Yunlong Feng
Xiangyu Chen
Hao Zhao 0002
Guyue Zhou

Accurate localization is an essential technology for the flexible navigation of robots in large-scale environments. Both SLAM-based and map-based localization will increase the computing load due to the increase in map size, which will affect downstream tasks such as robot navigation and services. To this end, we propose a localization system based on Block Maps (BMs) to reduce the computational load caused by maintaining large-scale maps. Firstly, we introduce a method for generating block maps and the corresponding switching strategies, ensuring that the robot can estimate the state in large-scale environments by loading local map information. Secondly, global localization according to Branch-and-Bound Search (BBS) in the 3D map is introduced to provide the initial pose. Finally, a graph-based optimization method is adopted with a dynamic sliding window that determines what factors are being marginalized whether a robot is exposed to a BM or switching to another one, which maintains the accuracy and efficiency of pose tracking. Comparison experiments are performed on publicly available large-scale datasets. Results show that the proposed method can track the robot pose even though the map scale reaches more than 6 kilometers, while efficient and accurate localization is still guaranteed on NCLT [6] and M2DGR [35]. Codes and data will be publicly available on https://github.com/YixFeng/blocklocalization.

Details

NeurIPS Conference 2024 Conference Paper

DiffuBox: Refining 3D Object Detection with Point Diffusion

Xiangyu Chen
Zhenzhen Liu
Katie Z. Luo
Siddhartha Datta
Adhitya Polavaram
Yan Wang
Yurong You
Boyi Li

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing sensor setups or geographic locations, often resulting in poor localization accuracy due to domain shift. To overcome this challenge, we introduce a novel diffusion-based box refinement approach. This method employs a domain-agnostic diffusion model, conditioned on the LiDAR points surrounding a coarse bounding box, to simultaneously refine the box's location, size, and orientation. We evaluate this approach under various domain adaptation settings, and our results reveal significant improvements across different datasets, object classes and detectors. Our PyTorch implementation is available at https: //github. com/cxy1997/DiffuBox.

PDF Details DOI

AAAI Conference 2024 Conference Paper

Direction-Aware Video Demoiréing with Temporal-Guided Bilateral Learning

Shuning Xu
Binbin Song
Xiangyu Chen
Jiantao Zhou

Moiré patterns occur when capturing images or videos on screens, severely degrading the quality of the captured images or videos. Despite the recent progresses, existing video demoiréing methods neglect the physical characteristics and formation process of moiré patterns, significantly limiting the effectiveness of video recovery. This paper presents a unified framework, DTNet, a direction-aware and temporal-guided bilateral learning network for video demoiréing. DTNet effectively incorporates the process of moiré pattern removal, alignment, color correction, and detail refinement. Our proposed DTNet comprises two primary stages: Frame-level Direction-aware Demoiréing and Alignment (FDDA) and Tone and Detail Refinement (TDR). In FDDA, we employ multiple directional DCT modes to perform the moiré pattern removal process in the frequency domain, effectively detecting the prominent moiré edges. Then, the coarse and fine-grained alignment is applied on the demoiréd features for facilitating the utilization of neighboring information. In TDR, we propose a temporal-guided bilateral learning pipeline to mitigate the degradation of color and details caused by the moiré patterns while preserving the restored frequency information in FDDA. Guided by the aligned temporal features from FDDA, the affine transformations for the recovery of the ultimate clean frames are learned in TDR. Extensive experiments demonstrate that our video demoiréing method outperforms state-of-the-art approaches by 2.3 dB in PSNR, and also delivers a superior visual experience.

PDF Details DOI

AAAI Conference 2023 Conference Paper

Low-Light Video Enhancement with Synthetic Event Guidance

Lin Liu
Junfeng An
Jianzhuang Liu
Shanxin Yuan
Xiangyu Chen
Wengang Zhou
Houqiang Li
Yan Feng Wang

Low-light video enhancement (LLVE) is an important yet challenging task with many applications such as photographing and autonomous driving. Unlike single image low-light enhancement, most LLVE methods utilize temporal information from adjacent frames to restore the color and remove the noise of the target frame. However, these algorithms, based on the framework of multi-frame alignment and enhancement, may produce multi-frame fusion artifacts when encountering extreme low light or fast motion. In this paper, inspired by the low latency and high dynamic range of events, we use synthetic events from multiple frames to guide the enhancement and restoration of low-light videos. Our method contains three stages: 1) event synthesis and enhancement, 2) event and image fusion, and 3) low-light enhancement. In this framework, we design two novel modules (event-image fusion transform and event-guided dual branch) for the second and third stages, respectively. Extensive experiments show that our method outperforms existing low-light video or single image enhancement approaches on both synthetic and real LLVE datasets. Our code will be available at https://gitee.com/mindspore/models/tree/master/research/cv/LLVE-SEG.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Real-World Image Super-Resolution as Multi-Task Learning

Wenlong Zhang
Xiaohui Li
Guangyuan SHI
Xiangyu Chen
Yu Qiao
Xiaoyun Zhang
Xiao-ming Wu
Chao Dong

In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-task learning perspective. We demonstrate that the conventional formulation of real-SR can be viewed as solving multiple distinct degradation tasks using a single shared model. This poses a challenge known as task competition or task conflict in multi-task learning, where certain tasks dominate the learning process, resulting in poor performance on other tasks. This problem is exacerbated in the case of real-SR, due to the involvement of numerous degradation tasks. To address the issue of task competition in real-SR, we propose a task grouping approach. Our approach efficiently identifies the degradation tasks where a real-SR model falls short and groups these unsatisfactory tasks into multiple task groups. We then utilize the task groups to fine-tune the real-SR model in a simple way, which effectively mitigates task competition and facilitates knowledge transfer. Extensive experiments demonstrate our method achieves significantly enhanced performance across a wide range of degradation scenarios.

PDF Details

NeurIPS Conference 2023 Conference Paper

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

Katie Luo
Zhenzhen Liu
Xiangyu Chen
Yurong You
Sagie Benaim
Cheng Perng Phoo
Mark Campbell
Wen Sun

Recent advances in machine learning have shown that Reinforcement Learning from Human Feedback (RLHF) can improve machine learning models and align them with human preferences. Although very successful for Large Language Models (LLMs), these advancements have not had a comparable impact in research for autonomous vehicles—where alignment with human expectations can be imperative. In this paper, we propose to adapt similar RL-based methods to unsupervised object discovery, i. e. learning to detect objects from LiDAR points without any training labels. Instead of labels, we use simple heuristics to mimic human feedback. More explicitly, we combine multiple heuristics into a simple reward function that positively correlates its score with bounding box accuracy, i. e. , boxes containing objects are scored higher than those without. We start from the detector’s own predictions to explore the space and reinforce boxes with high rewards through gradient updates. Empirically, we demonstrate that our approach is not only more accurate, but also orders of magnitudes faster to train compared to prior works on object discovery. Code is available at https: //github. com/katieluo88/DRIFT.

PDF Details

NeurIPS Conference 2023 Conference Paper

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

Cole Gulino
Justin Fu
Wenjie Luo
George Tucker
Eli Bronstein
Yiren Lu
Jean Harb
Xinlei Pan

Simulation is an essential tool to develop and benchmark autonomous vehicle planning software in a safe and cost-effective manner. However, realistic simulation requires accurate modeling of multi-agent interactive behaviors to be trustworthy, behaviors which can be highly nuanced and complex. To address these challenges, we introduce Waymax, a new data-driven simulator for autonomous driving in multi-agent scenes, designed for large-scale simulation and testing. Waymax uses publicly-released, real-world driving data (e. g. , the Waymo Open Motion Dataset) to initialize or play back a diverse set of multi-agent simulated scenarios. It runs entirely on hardware accelerators such as TPUs/GPUs and supports in-graph simulation for training, making it suitable for modern large-scale, distributed machine learning workflows. To support online training and evaluation, Waymax includes several learned and hard-coded behavior models that allow for realistic interaction within simulation. To supplement Waymax, we benchmark a suite of popular imitation and reinforcement learning algorithms with ablation studies on different design decisions, where we highlight the effectiveness of routes as guidance for planning agents and the ability of RL to overfit against simulated agents.

PDF Details

IROS Conference 2022 Conference Paper

Low-drift LiDAR-only Odometry and Mapping for UGVs in Environments with Non-level Roads

Xiangyu Chen
Yinchuan Wang
Chaoqun Wang 0009
Rui Song 0002
Yibin Li 0001

This study focuses on localization and mapping for UGVs when they are deployed in environments with non-level roads. In these scenarios, the vehicles need to travel through flat but not necessarily level grounds, i. e. , ascent or descent, which may cause drifts of the robot pose and distortion of the map. We develop a low-drift LiDAR odometry and mapping approach for the UGV with LiDAR as the only exteroceptive sensor. A factor-graph based pose optimization method is developed with a specifically designed factor named slope factor. This factor includes the slope information that is estimated from a real-time LiDAR data stream. The slope information is also used to enhance the loop-closure detection procedure. Moreover, an incremental pitch estimation mechanism is designed to achieve further pose estimation refinement. We demonstrate the effectiveness of the developed framework in real-world environments. The odometry drift is lower and the map is more precise than experiments with the state-of-the-arts. Notably, on the Kitti dataset, our method also exhibits convincing performance, demonstrating its strength in more general application scenarios.

Details

ICML Conference 2021 Conference Paper

Cyclically Equivariant Neural Decoders for Cyclic Codes

Xiangyu Chen
Min Ye 0005

Neural decoders were introduced as a generalization of the classic Belief Propagation (BP) decoding algorithms, where the Trellis graph in the BP algorithm is viewed as a neural network, and the weights in the Trellis graph are optimized by training the neural network. In this work, we propose a novel neural decoder for cyclic codes by exploiting their cyclically invariant property. More precisely, we impose a shift invariant structure on the weights of our neural decoder so that any cyclic shift of inputs results in the same cyclic shift of outputs. Extensive simulations with BCH codes and punctured Reed-Muller (RM) codes show that our new decoder consistently outperforms previous neural decoders when decoding cyclic codes. Finally, we propose a list decoding procedure that can significantly reduce the decoding error probability for BCH codes and punctured RM codes. For certain high-rate codes, the gap between our list decoder and the Maximum Likelihood decoder is less than $0. 1$dB. Code available at github. com/cyclicallyneuraldecoder

Details

ICRA Conference 2020 Conference Paper

Transferable Active Grasping and Real Embodied Dataset

Xiangyu Chen
Zelin Ye
Jiankai Sun
Yuda Fan
Fang Hu 0002
Chenxi Wang 0003
Cewu Lu

Grasping in cluttered scenes is challenging for robot vision systems, as detection accuracy can be hindered by partial occlusion of objects. We adopt a reinforcement learning (RL) framework and 3D vision architectures to search for feasible viewpoints for grasping by the use of hand-mounted RGB-D cameras. To overcome the disadvantages of photo-realistic environment simulation, we propose a large-scale dataset called Real Embodied Dataset (RED), which includes full-viewpoint real samples on the upper hemisphere with amodal annotation and enables a simulator that has real visual feedback. Based on this dataset, a practical 3-stage transferable active grasping pipeline is developed, that is adaptive to unseen clutter scenes. In our pipeline, we propose a novel mask-guided reward to overcome the sparse reward issue in grasping and ensure category-irrelevant behavior. The grasping pipeline and its possible variants are evaluated with extensive experiments both in simulation and on a real-world UR-5 robotic arm.

Details

ICRA Conference 2019 Conference Paper

Semantic Predictive Control for Explainable and Efficient Policy Learning

Xinlei Pan
Xiangyu Chen
Qi-Zhi Cai
John F. Canny
Fisher Yu 0001

Visual anticipation of ego and object motion over a short time horizons is a key feature of human-level performance in complex environments. We propose a driving policy learning framework that predicts feature representations of future visual inputs; our predictive model infers not only future events but also semantics, which provide a visual explanation of policy decisions. Our Semantic Predictive Control (SPC) framework predicts future semantic segmentation and events by aggregating multi-scale feature maps. A guidance model assists action selection and enables efficient sampling-based optimization. Experiments on multiple simulation environments show that networks which implement SPC can outperform existing model-based reinforcement learning algorithms in terms of data efficiency and total rewards while providing clear explanations for the policy's behavior.

Details

IROS Conference 2019 Conference Paper

TendencyRL: Multi-stage Discriminative Hints for Efficient Goal-Oriented Reverse Curriculum Learning

Chen Wang 0033
Junfeng Ding
Xiangyu Chen
Zelin Ye
Jialu Wang
Ziruo Cai
Cewu Lu

Deep reinforcement learning algorithms have been proven successful in a variety of simulation tasks with dense reward feedback. However, real-world RL applications, e. g. robotic manipulation, remain challenging as most of them are multi-stage and a positive reward can only be received when the final goal is accomplished. In this work, we propose a potential solution to such problems with the introduction of an experience-based tendency reward shaping mechanism, which provides the robot with additional hints based on a discriminative learning on past experience. The reward along with a stage-awareness network help accelerate solving a multistage task split into shorter phases in a reverse curriculum learning manner. We extensively study the advantages of TRL on the standard long-term goal-oriented robotics domains such as pick-and-place, and show that TRL performs more efficiently and robustly than prior approaches in tasks with large state space. In addition, we demonstrate that TRL can solve difficult robot manipulation challenges directly from perception.

Details