Author name cluster

Lei Cheng

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.

13 papers

2 author rows

EAAI Journal 2026 Journal Article

Cross-layer feature consistency and dual-transformer residual framework for underwater image enhancement

Xinbin Li
Lei Cheng
Song Han
Jing Yang
Hui Dang
Muge Li

Underwater imaging suffers from complex degradations (e. g. , color casts, blur, and haze) due to light scattering in water, limiting its utility in engineering applications such as marine exploration and underwater robotics. To address this, we propose the Cross-layer Feature Consistency-guided Dual-Transformer Reconstruction Framework (CFC-DTRF). In terms of artificial intelligence contribution, this work introduces a novel multi-stage framework that leverages feature-consistency supervision to jointly constrain feature and pixel domains, effectively disentangling content and color degradations through dedicated transformers. The framework integrates two innovative modules: a Sliding-Window Content-Attention Transformer (SWCA-Transformer) for detail preservation and a Multi-Scale Color-Attention Transformer (MSCA-Transformer) for color correction, enhancing restoration fidelity with computational efficiency. For engineering applications, this method significantly improves underwater image quality for practical tasks like environmental monitoring and robotic navigation. Extensive experiments show that CFC-DTRF outperforms state-of-the-art methods in content preservation and color accuracy. The code of the proposed CFC-DTRF is available at https: //github. com/ChengLeiYSU/CFC-DTRF.

Details DOI

AAAI Conference 2026 Conference Paper

First Learn, Then Review: Human-Like Continual Learning for Cross-View Geo-Localization with Limited Field of View

Lei Cheng
Daikun Liu
Zhikun Chen
Teng Wang

This paper addresses cross-view geo-localization in real-world scenarios, where the field-of-view (FoV) is restricted and the orientation is unknown for ground-view images. This task is extremely challenging due to the huge domain gap. Existing methods typically treat tasks with different FoVs as independent tasks. These approaches not only require separate retraining for each FoV, but also neglect the strong correlations between different FoVs, leading to poor performance under extremely limited FoV. To overcome these limitations, we propose HCL-Geo, a framework follows human-like continual learning paradigm of "first learn, then review" for geo-localization: in the first "learn" stage, tasks are presented to the model in an easy-to-hard sequence to enable gradual learning and knowledge retention, so that their natural correlations could be exploited to facilitate knowledge transfer. In the second "review" stage, expert modules are incorporated to efficiently handle tasks with varying FoVs. This approach eliminates the need for retraining separate models and demonstrates state-of-the-art performance across different FoVs with strong generalization capabilities. Remarkably, the recall rate@top-1 improves from 49.1% to 68.3% and from 24.6% to 34.3% respectively on CVUSA and CVACT benchmarks with 70° FoV.

PDF Details DOI

AAAI Conference 2026 Conference Paper

G-UBS: Towards Robust Understanding of Implicit Feedback via Group-Aware User Behavior Simulation

Boyu Chen
Siran Chen
Zhengrong Yue
Kainan Yan
Chenyun Yu
Beibei Kong
Lei Cheng
Chengxiang Zhuo

User feedback is critical for refining recommendation systems, yet explicit feedback (e.g., likes or dislikes) remains scarce in practice. As a more feasible alternative, inferring user preferences from massive implicit feedback has shown great potential (e.g., a user quickly skipping a recommended video usually indicates disinterest). Unfortunately, implicit feedback is often noisy: a user might skip a video due to accidental clicks or other reasons, rather than disliking it. Such noise can easily misjudge user interests, thereby undermining recommendation performance. To address this issue, we propose a novel Group-aware User Behavior Simulation (G-UBS) paradigm, which leverages contextual guidance from relevant user groups, enabling robust and in-depth interpretation of implicit feedback for individual users. Specifically, G-UBS operates via two key agents. First, the User Group Manager (UGM) effectively clusters users to generate group profiles utilizing a ``summarize-cluster-reflect" workflow based on LLMs. Second, the User Feedback Modeler (UFM) employs an innovative group-aware reinforcement learning approach, where each user is guided by the associated group profiles during the reinforcement learning process, allowing UFM to robustly and deeply examine the reasons behind implicit feedback. To assess our G-UBS paradigm, we have constructed a Video Recommendation benchmark with Implicit Feedback (IF-VR). To the best of our knowledge, this is the first multi-modal benchmark for implicit feedback evaluation in video recommendation, encompassing 15k users, 25k videos, and 933k interaction records with implicit feedback. Extensive experiments on IF-VR demonstrate that G-UBS significantly outperforms mainstream LLMs and MLLMs, with a 4.0% higher proportion of videos achieving a play rate > 30% and 14.9% higher reasoning accuracy on IF-VR.

PDF Details DOI

AAAI Conference 2026 Conference Paper

VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning

Siran Chen
Boyu Chen
Yuxiao Luo
Chenyun Yu
Yi Ouyang
Lei Cheng
Chengxiang Zhuo
Zang Li

Large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, existing studies predominantly resort to prompt-based simulation using frozen LLMs, which frequently results in suboptimal item modeling and user preference learning, thereby ultimately constraining recommendation performance. To address these challenges, we introduce VRAgent-R1, a novel agent-based paradigm that incorporates human-like intelligence in user simulation. Specifically, VRAgent-R1 comprises two distinct agents: the Item Perception (IP) Agent and the User Simulation (US) Agent, designed for interactive user-item modeling. Firstly, the IP Agent emulates human-like progressive thinking based on MLLMs, effectively capturing hidden recommendation semantics in videos. With a more comprehensive multimodal content understanding provided by the IP Agent, the video recommendation system is equipped to provide higher-quality candidate items. Subsequently, the US Agent refines the recommended video sets based on in-depth chain-of-thought (CoT) reasoning and achieves better alignment with real user preferences through reinforcement learning. Experimental results on a large-scale video recommendation benchmark MicroLens-100k have demonstrated the effectiveness of our proposed VRAgent-R1 method, e.g., the IP Agent achieves a 6.0% improvement in NDCG@10, while the US Agent shows approximately 45.0% higher accuracy in user decision simulation compared to state-of-the-art baselines.

PDF Details DOI

AAAI Conference 2026 Conference Paper

When Top-ranked Recommendations Fail: Modeling Multi-Granular Negative Feedback for Explainable and Robust Video Recommendation

Siran Chen
Boyu Chen
Chenyun Yu
Yi Ouyang
Lei Cheng
Chengxiang Zhuo
Zang Li
Yali Wang

Existing video recommendation systems, relying mainly on ID-based embedding mapping and collaborative filtering, often fail to capture in-depth video content semantics. Moreover, most struggle to address biased user behaviors (e.g., accidental clicks, fast skips), leading to inaccurate interest modeling and frequent negative feedback in top recommendations with unclear causes. To tackle this issue, we collect real-world user video-watching sequences, annotate the reasons for users' dislikes, and construct a benchmark dataset for personalized explanations. We then introduce the Agentic Explainable Negative Feedback (ENF) framework, which integrates three core components: (1) the Profile Agent, extracting behavioral cues from users' historical data to derive psychological and personality profiles; (2) the Video Agent, performing comprehensive multimodal video analysis; and (3) the Reason Agent, synthesizing information from the other two agents to predict user engagement and generate explanations. Additionally, we propose the S-GRPO algorithm, enabling the model to progressively address complex tasks during reinforcement fine-tuning. Experimental results on the collected dataset show that our method significantly outperforms state-of-the-art baselines in negative feedback prediction and reason explanation. Notably, it achieves an 8.6% improvement over GPT-4o in reason classification. Deployment on the business platform further validates its benefits: increasing average user watch time by 6.2%, reducing the fast-skip rate by 9.4%, and significantly enhancing user satisfaction.

PDF Details DOI

AAAI Conference 2025 Conference Paper

DOGR: Leveraging Document-Oriented Contrastive Learning in Generative Retrieval

Penghao Lu
Xin Dong
Yuansheng Zhou
Lei Cheng
Chuan Yuan
Linjian Mo

Generative retrieval constitutes an innovative approach in information retrieval, leveraging generative language models(LM) to generate a ranked list of document identifiers (docid) for a given query. It simplifies the retrieval pipeline by replacing the large external index with model parameters. However, existing works merely learned the relationship between queries and document identifiers, which is unable to directly represent the relevance between queries and documents. To address the above problem, we propose a novel and general generative retrieval framework, namely Leveraging Document-Oriented Contrastive Learning in Generative Retrieval (DOGR), which leverages contrastive learning to improve generative retrieval tasks. It adopts a two-stage learning strategy that captures the relationship between queries and documents comprehensively through direct interactions. Furthermore, negative sampling methods and corresponding contrastive learning objectives are implemented to enhance the learning of semantic representations, thereby promoting a thorough comprehension of the relationship between queries and documents. Experimental results demonstrate that DOGR achieves state-of-the-art performance compared to existing generative retrieval methods on two public benchmark datasets. Further experiments have shown that our framework is generally effective for common identifier construction techniques.

PDF Details DOI

NeurIPS Conference 2025 Conference Paper

Functional Complexity-adaptive Temporal Tensor Decomposition

Panqi Chen
Lei Cheng
Jianlong Li
Weichang Li
Weiqing Liu
Jiang Bian
Shikai Fang

Tensor decomposition is a fundamental tool for analyzing multi-dimensional data by learning low-rank factors to represent high-order interactions. While recent works on temporal tensor decomposition have made significant progress by incorporating continuous timestamps in latent factors, they still struggle with general tensor data with continuous indexes not only in the temporal mode but also in other modes, such as spatial coordinates in climate data. Moreover, the challenge of self-adapting model complexity is largely unexplored in functional temporal tensor models, with existing methods being inapplicable in this setting. To address these limitations, we propose functional Complexity-Adaptive Temporal Tensor dEcomposition (Catte). Our approach encodes continuous spatial indexes as learnable Fourier features and employs neural ODEs in latent space to learn the temporal trajectories of factors. To enable automatic adaptation of model complexity, we introduce a sparsity-inducing prior over the factor trajectories. We develop an efficient variational inference scheme with an analytical evidence lower bound, enabling sampling-free optimization. Through extensive experiments on both synthetic and real-world datasets, we demonstrate that Catte not only reveals the underlying ranks of functional temporal tensors but also significantly outperforms existing methods in prediction performance and robustness against noise.

PDF Details

NeurIPS Conference 2025 Conference Paper

Generating Full-field Evolution of Physical Dynamics from Irregular Sparse Observations

Panqi Chen
Yifan Sun
Lei Cheng
Yang Yang
Weichang Li
Yang Liu
Weiqing Liu
Jiang Bian

Modeling and reconstructing multidimensional physical dynamics from sparse and off-grid observations presents a fundamental challenge in scientific research. Recently, diffusion-based generative modeling shows promising potential for physical simulation. However, current approaches typically operate on on-grid data with preset spatiotemporal resolution, but struggle with the sparsely observed and continuous nature of real-world physical dynamics. To fill the gaps, we present SDIFT, Sequential DIffusion in Functional Tucker space, a novel framework that generates full-field evolution of physical dynamics from irregular sparse observations. SDIFT leverages the functional Tucker model as the latent space representer with proven universal approximation property, and represents sparse observations as latent functions and Tucker core sequences. We then construct a sequential diffusion model with temporally augmented UNet in the functional Tucker space, denoising noise drawn from a Gaussian process to generate the sequence of core tensors. At the posterior sampling stage, we propose a Message-Passing Posterior Sampling mechanism, enabling conditional generation of the entire sequence guided by observations at limited time steps. We validate SDIFT on three physical systems spanning astronomical (supernova explosions, light-year scale), environmental (ocean sound speed fields, kilometer scale), and molecular (organic liquid, millimeter scale) domains, demonstrating significant improvements in both reconstruction accuracy and computational efficiency compared to state-of-the-art approaches.

PDF Details

IROS Conference 2024 Conference Paper

Physically-Based Photometric Bundle Adjustment in Non-Lambertian Environments

Lei Cheng
Junpeng Hu
Haodong Yan
Mariia Gladkova
Tianyu Huang
Yun-Hui Liu 0001
Daniel Cremers
Haoang Li

Photometric bundle adjustment (PBA) is widely used in estimating the camera pose and 3D geometry by assuming a Lambertian world. However, the assumption of photometric consistency is often violated since the non-diffuse reflection is common in real-world environments. The photometric inconsistency significantly affects the reliability of existing PBA methods. To solve this problem, we propose a novel physically-based PBA method. Specifically, we introduce the physically-based weights regarding material, illumination, and light path. These weights distinguish the pixel pairs with different levels of photometric inconsistency. We also design corresponding models for material estimation based on sequential images and illumination estimation based on point clouds. In addition, we establish the first SLAM-related dataset of non-Lambertian scenes with complete ground truth of illumination and material. Extensive experiments demonstrated that our PBA method outperforms existing approaches in accuracy.

Details

ICLR Conference 2023 Conference Paper

ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length

Ruslan Khalitov
Tong Yu
Lei Cheng
Zhirong Yang

Sequential data naturally have different lengths in many domains, with some very long sequences. As an important modeling tool, neural attention should capture long-range interaction in such sequences. However, most existing neural attention models admit only short sequences, or they have to employ chunking or padding to enforce a constant input length. Here we propose a simple neural network building block called ChordMixer which can model the attention for long sequences with variable lengths. Each ChordMixer block consists of a position-wise rotation layer without learnable parameters and an element-wise MLP layer. Repeatedly applying such blocks forms an effective network backbone that mixes the input signals towards the learning targets. We have tested ChordMixer on the synthetic adding problem, long document classification, and DNA sequence-based taxonomy classification. The experiment results show that our method substantially outperforms other neural attention models.

Details

AAAI Conference 2023 Conference Paper

REMIT: Reinforced Multi-Interest Transfer for Cross-Domain Recommendation

Caiqi Sun
Jiewei Gu
Binbin Hu
Xin Dong
Hai Li
Lei Cheng
Linjian Mo

Cold-start problem is one of the most challenging problems for recommender systems. One promising solution to this problem is cross-domain recommendation (CDR) which leverages rich information from an auxiliary source domain to improve the performance of recommender system in the target domain. In particular, the family of embedding and mapping methods for CDR is very effective, which explicitly learn a mapping function from source embeddings to target embeddings to transfer user’s preferences. Recent works usually transfer an overall source embedding by modeling a common or personalized preference bridge for all users. However, a unified user embedding cannot reflect the user’s multiple interests in auxiliary source domain. In this paper, we propose a novel framework called reinforced multi-interest transfer for CDR (REMIT). Specifically, we first construct a heterogeneous information network and employ different meta-path based aggregations to get user’s multiple interests in source domain, then transform different interest embeddings with different meta-generated personalized bridge functions for each user. To better coordinate the transformed user interest embeddings and the item embedding in target domain, we systematically develop a reinforced method to dynamically assign weights to transformed interests for different training instances and optimize the performance of target model. In addition, the REMIT is a general framework that can be applied upon various base models in target domain. Our extensive experimental results on large real-world datasets demonstrate the superior performance and compatibility of REMIT.

PDF Details DOI

ICRA Conference 2016 Conference Paper

Dynamic modeling of cable driven elongated surgical instruments for sensorless grip force estimation

Yangming Li
Muneaki Miyasaka
Mohammad Haghighipanah
Lei Cheng
Blake Hannaford

Haptic feedback plays a key role in surgeries, but it is still a missing component in robotic Minimally Invasive Surgeries. This paper proposes a dynamic model-based sensorless grip force estimation method to address the haptic perception problem for commonly used elongated cable-driven surgical instruments. Cable and cable-pulley properties are studied for dynamic modeling; grip forces, along with driven motor and gripper jaw positions and velocities are jointly estimated with Unscented Kalman Filter and only motor encoder readings and motor output torques are assumed to be known. A bounding filter is used to compensate for model inaccuracy and to improve method robustness. The proposed method was validated on a 10mm gripper which is driven by a Raven-II surgical robot. The gripper was equipped with 1-dimensional force sensors which served as ground truth data. The experimental results showed that the proposed method provides sufficiently good grip force estimation, while only motor encoder and the motor torques are used as observations.

Details

ICRA Conference 2011 Conference Paper

Control of upper-limb power-assist exoskeleton based on motion intention recognition

Weiguang Huo
Jian Huang 0001
Yongji Wang 0001
Jun Wu
Lei Cheng

Recognizing the user motion intention plays an important role in the study of power-assist robots. An intention-guided control strategy is proposed for the upper-limb power-assist exoskeleton. A force sensor system comprised of force sensing resistors (FSRs) is designed to online estimate the motion intention of user upper limb. A new concept called "intentional reaching direction (IRD)" is proposed to quantitatively describe this intention. Both the state model and the observation model of IRD are obtained by enumerating the upper limb behavior modes and analyzing the relationship between the measured force signals and the motion intention. Based on these two models, the IRD can be online inferred by applying filtering technology. Guided by the estimated IRD, an admittance control strategy is assumed to control the motions of three DC motors in the joints of the robotic arm. The effectiveness of the proposed approaches is finally confirmed by the experiments on a 3-DOF robotic exoskeleton.

Details