arXiv subjects

Gong Chen

Publications and source records attributed to Gong Chen.

At least 37 records · Page 2Linked to original sources

arXiv2026

CoopDiff: A Diffusion-Guided Approach for Cooperation under Corruptions

Cooperative perception lets agents share information to expand coverage and improve scene understanding. However, in real-world scenarios, diverse and unpredictable corruptions undermine its robustness and generalization. To address these challenges, we introduce CoopDiff, a diffusion-based cooperative perception framework that mitigates corruptions via a denoising mechanism. CoopDiff adopts a teacher-student paradigm: the Quality-Aware Teacher performs voxel-level early fusion with Quality of Interest weighting and semantic guidance, then produces clean supervision features via a diffusion denoiser. The Dual-Branch Diffusion Student first separates ego and cooperative streams in encoding to reconstruct the teacher's clean targets. And then, an Ego-Guided Cross-Attention mechanism facilitates balanced decoding under degradation by adaptively integrating ego and cooperative features. We evaluate CoopDiff on two constructed multi-degradation benchmarks, OPV2Vn and DAIR-V2Xn, each incorporating six corruption types, including environmental and sensor-level distortions. Benefiting from the inherent denoising properties of diffusion, CoopDiff consistently outperforms prior methods across all degradation types and lowers the relative corruption error. Furthermore, it offers a tunable balance between precision and inference efficiency.

cs.CV↗

arXiv2026

WhisperNet: A Scalable Solution for Bandwidth-Efficient Collaboration

Collaborative perception is vital for autonomous driving yet remains constrained by tight communication budgets. Earlier work reduced bandwidth by compressing full feature maps with fixed-rate encoders, which adapts poorly to a changing environment, and it further evolved into spatial selection methods that improve efficiency by focusing on salient regions, but this object-centric approach often sacrifices global context, weakening holistic scene understanding. To overcome these limitations, we introduce \textit{WhisperNet}, a bandwidth-aware framework that proposes a novel, receiver-centric paradigm for global coordination across agents. Senders generate lightweight saliency metadata, while the receiver formulates a global request plan that dynamically budgets feature contributions across agents and features, retrieving only the most informative features. A collaborative feature routing module then aligns related messages before fusion to ensure structural consistency. Extensive experiments show that WhisperNet achieves state-of-the-art performance, improving AP@0.7 on OPV2V by 2.4\% with only 0.5\% of the communication cost. As a plug-and-play component, it boosts strong baselines with merely 5\% of full bandwidth while maintaining robustness under localization noise. These results demonstrate that globally-coordinated allocation across \textit{what} and \textit{where} to share is the key to achieving efficient collaborative perception.

cs.CV↗

arXiv2026

TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement Learning

Temporal knowledge graph question answering (TKGQA) aims to answer time-sensitive questions by leveraging temporal knowledge bases. While Large Language Models (LLMs) demonstrate significant potential in TKGQA, current prompting strategies constrain their efficacy in two primary ways. First, they are prone to reasoning hallucinations under complex temporal constraints. Second, static prompting limits model autonomy and generalization, as it lack optimization through dynamic interaction with temporal knowledge graphs (TKGs) environments. To address these limitations, we propose \textbf{TKG-Thinker}, a novel agent equipped with autonomous planning and adaptive retrieval capabilities for reasoning over TKGs. Specifically, TKG-Thinker performs in-depth temporal reasoning through dynamic multi-turn interactions with TKGs via a dual-training strategy. We first apply Supervised Fine-Tuning (SFT) with chain of thought data to instill core planning capabilities, followed by a Reinforcement Learning (RL) stage that leverages multi-dimensional rewards to refine reasoning policies under intricate temporal constraints. Experimental results on benchmark datasets with three open-source LLMs show that TKG-Thinker achieves state-of-the-art performance and exhibits strong generalization across complex TKGQA settings.

cs.AI↗

arXiv2026

Multi-View Adaptive Contrastive Learning for Information Retrieval Based Fault Localization

Most studies focused on information retrieval-based techniques for fault localization, which built representations for bug reports and source code files and matched their semantic vectors through similarity measurement. However, such approaches often ignore some useful information that might help improve localization performance, such as 1) the interaction relationship between bug reports and source code files; 2) the similarity relationship between bug reports; and 3) the co-citation relationship between source code files. In this paper, we propose a novel approach named Multi-View Adaptive Contrastive Learning for Information Retrieval Fault Localization (MACL-IRFL) to learn the above-mentioned relationships for software fault localization. Specifically, we first generate data augmentations from report-code interaction view, report-report similarity view and code-code co-citation view separately, and adopt graph neural network to aggregate the information of bug reports or source code files from the three views in the embedding process. Moreover, we perform contrastive learning across these views. Our design of contrastive learning task will force the bug report representations to encode information shared by report-report and report-code views,and the source code file representations shared by code-code and report-code views, thereby alleviating the noise from auxiliary information. Finally, to evaluate the performance of our approach, we conduct extensive experiments on five open-source Java projects. The results show that our model can improve over the best baseline up to 28.93%, 25.57% and 20.35% on Accuracy@1, MAP and MRR, respectively.

cs.SE↗

arXiv2026

Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation

Compounding errors pose a significant challenge in automatic literature review generation, as inaccuracies can cascade across multi-stage retrieval and generation workflows. Existing self-correction strategies often lack mechanisms to effectively track and consolidate verified information throughout the process, making it difficult to prevent error accumulation and propagation. In this paper, we propose Structure-Guided Memory Consolidation (SGMC), a novel framework that incrementally consolidates and verifies information using structured representations at each stage of the literature review pipeline. SGMC consists of three key modules: Tree-Guided Memory for hierarchical literature retrieval and outline generation, Hub-Guided Memory for evidence extraction and iterative content refinement, and Self-Loop Memory for proactive error correction via historical feedback. Extensive experiments on public benchmarks and a newly constructed large-scale dataset demonstrate that SGMC achieves state-of-the-art performance in citation accuracy and content quality, significantly mitigating compounding errors in long-form literature review generation.

cs.CE↗

arXiv2026

From Darkness to Detail: Frequency-Aware SSMs for Low-Light Vision

Low-light image enhancement remains a persistent challenge in computer vision, where state-of-the-art models are often hampered by hardware constraints and computational inefficiency, particularly at high resolutions. While foundational architectures like transformers and diffusion models have advanced the field, their computational complexity limits their deployment on edge devices. We introduce ExpoMamba, a novel architecture that integrates a frequency-aware state-space model within a modified U-Net. ExpoMamba is designed to address mixed-exposure challenges by decoupling the modeling of amplitude (intensity) and phase (structure) in the frequency domain. This allows for targeted enhancement, making it highly effective for real-time applications, including downstream tasks like object detection and segmentation. Our experiments on six benchmark datasets show that ExpoMamba is up to 2-3x faster than competing models and achieves a 6.8\% PSNR improvement, establishing a new state-of-the-art in efficient, high-quality low-light enhancement. Source code: https://www.github.com/eashanadhikarla/ExpoMamba.

cs.CV↗

arXiv2026

EPD-Serve: A Flexible Multimodal EPD Disaggregation Inference Serving System On Ascend

With the widespread adoption of large multimodal models, efficient inference across text, image, audio, and video modalities has become critical. However, existing multimodal inference systems typically employ monolithic architectures that tightly couple the Encode, Prefill, and Decode stages on homogeneous hardware, neglecting the heterogeneous computational characteristics of each stage. This design leads to inefficient resource utilization and limited system throughput. To address these issues, we propose EPD-Serve, a stage-level disaggregated inference serving system for multimodal models. EPD-Serve decouples the inference pipeline into independent Encode, Prefill, and Decode stages, enabling logical isolation and flexible co-located deployment through dynamic orchestration. Leveraging the Ascend interconnect topology, EPD-Serve introduces asynchronous feature prefetching between Encode and Prefill stages and a hierarchical grouped KV cache transmission mechanism between Prefill and Decode stages to improve cross-node communication efficiency. In addition, EPD-Serve incorporates multi-route scheduling, instance-level load balancing, and multi-stage hardware co-location with spatial multiplexing to better support diverse multimodal workloads. Comprehensive experiments on multimodal understanding models demonstrate that, under high-concurrency scenarios, EPD-Serve improves end-to-end throughput by 57.37-69.48% compared to PD-disaggregated deployment, while satisfying strict SLO constraints, including TTFT below 2000 ms and TPOT below 50 ms. These results highlight the effectiveness of stage-level disaggregation for optimizing multimodal large model inference systems.

cs.DC↗

arXiv2025

CoRA: A Collaborative Robust Architecture with Hybrid Fusion for Efficient Perception

Collaborative perception has garnered significant attention as a crucial technology to overcome the perceptual limitations of single-agent systems. Many state-of-the-art (SOTA) methods have achieved communication efficiency and high performance via intermediate fusion. However, they share a critical vulnerability: their performance degrades under adverse communication conditions due to the misalignment induced by data transmission, which severely hampers their practical deployment. To bridge this gap, we re-examine different fusion paradigms, and recover that the strengths of intermediate and late fusion are not a trade-off, but a complementary pairing. Based on this key insight, we propose CoRA, a novel collaborative robust architecture with a hybrid approach to decouple performance from robustness with low communication. It is composed of two components: a feature-level fusion branch and an object-level correction branch. Its first branch selects critical features and fuses them efficiently to ensure both performance and scalability. The second branch leverages semantic relevance to correct spatial displacements, guaranteeing resilience against pose errors. Experiments demonstrate the superiority of CoRA. Under extreme scenarios, CoRA improves upon its baseline performance by approximately 19% in AP@0.7 with more than 5x less communication volume, which makes it a promising solution for robust collaborative perception.

cs.CV↗

arXiv2025

LENVIZ: A High-Resolution Low-Exposure Night Vision Benchmark Dataset

Low-light image enhancement is crucial for a myriad of applications, from night vision and surveillance, to autonomous driving. However, due to the inherent limitations that come in hand with capturing images in low-illumination environments, the task of enhancing such scenes still presents a formidable challenge. To advance research in this field, we introduce our Low Exposure Night Vision (LENVIZ) Dataset, a comprehensive multi-exposure benchmark dataset for low-light image enhancement comprising of over 230K frames showcasing 24K real-world indoor and outdoor, with-and without human, scenes. Captured using 3 different camera sensors, LENVIZ offers a wide range of lighting conditions, noise levels, and scene complexities, making it the largest publicly available up-to 4K resolution benchmark in the field. LENVIZ includes high quality human-generated ground truth, for which each multi-exposure low-light scene has been meticulously curated and edited by expert photographers to ensure optimal image quality. Furthermore, we also conduct a comprehensive analysis of current state-of-the-art low-light image enhancement techniques on our dataset and highlight potential areas of improvement.

cs.CV↗

arXiv2025

NTIRE 2025 Challenge on Low Light Image Enhancement: Methods and Results

This paper presents a comprehensive review of the NTIRE 2025 Low-Light Image Enhancement (LLIE) Challenge, highlighting the proposed solutions and final outcomes. The objective of the challenge is to identify effective networks capable of producing brighter, clearer, and visually compelling images under diverse and challenging conditions. A remarkable total of 762 participants registered for the competition, with 28 teams ultimately submitting valid entries. This paper thoroughly evaluates the state-of-the-art advancements in LLIE, showcasing the significant progress.

cs.CV↗

arXiv2025

Scattering Theory and dispersive estimates for general $1$d Charge Transfer Models

We continue our study of scattering theory and dispersive properties for one-dimensional charge transfer models, namely linear Schrödinger equations with multiple moving potentials. By the discovery of a refined structure of the construction of distorted Fourier transforms adapted to the multi-potential framework, we remove the large-velocity separation assumption imposed in [8]. This work thus completes the full scattering theory and dispersive analysis for general one-dimensional charge transfer models. These dispersive estimates provide the foundation for analyzing asymptotic stability and collision phenomena for multi-solitons in a general setting.

math.AP↗

arXiv2025

Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration

Automating the end-to-end scientific research process poses a fundamental challenge: it requires both evolving high-level plans that are novel and sound, and executing these plans correctly amidst dynamic and uncertain conditions. To address this bilevel challenge, we propose a novel Double-Loop Multi-Agent (DLMA) framework to solve the given research problem automatically. The leader loop, composed of professor agents, is responsible for evolving research plans. It employs an evolutionary algorithm through involvement, improvement, and integration meetings to iteratively generate and refine a pool of research proposals, exploring the solution space effectively. The follower loop, composed of doctoral student agents, is responsible for executing the best-evolved plan. It dynamically adjusts the plan during implementation via pre-hoc and post-hoc meetings, ensuring each step (e.g., drafting, coding) is well-supported by contextual and external observations. Extensive experiments on benchmarks like ACLAward and Laboratory show that DLMA generates research papers that achieve state-of-the-art scores in automated evaluation, significantly outperforming strong baselines. Ablation studies confirm the critical roles of both loops, with evolution driving novelty and execution ensuring soundness.

cs.AI↗

arXiv2025

MusicScaffold: Bridging Machine Efficiency and Human Growth in Adolescent Creative Education through Generative AI

Adolescence is marked by strong creative impulses but limited strategies for structured expression, often leading to frustration or disengagement. While generative AI lowers technical barriers and delivers efficient outputs, its role in fostering adolescents' expressive growth has been overlooked. We propose MusicScaffold, the first adolescent-centered framework that repositions AI as a guide, coach, and partner, making expressive strategies transparent and learnable, and supporting autonomy. In a four-week study with middle school students (ages 12--14), MusicScaffold enhanced cognitive specificity, behavioral self-regulation, and affective confidence in music creation. By reframing generative AI as a scaffold rather than a generator, this work bridges the machine efficiency of generative systems with human growth in adolescent creative education.

cs.HC↗

arXiv2025

Who Decides How Knowing Becomes Doing? Redistributing Authority in Human-AI Music Co-Creation

In the era of human-AI co-creation, the maxim "knowing is easy, doing is hard" is redefined. AI has the potential to ease execution, yet the essence of "hard" lies in who governs the translation from knowing to doing. Mainstream tools often centralize interpretive authority and homogenize expression, suppressing marginal voices. To address these challenges, we introduce the first systematic framework for redistributing authority in the knowing-doing cycle, built on three principles, namely contestability, agency, and plurality. Through interactive studies with 180 music practitioners, complemented by in-depth interviews, we demonstrate that these principles reshape human-AI authority relations and reactivate human creative expression. The findings establish a new paradigm for critical computing and human-AI co-creation that advances from critique to practice.

cs.HC↗

arXiv2025

Dispersive analysis for one-dimensional charge transfer models

In this paper, we study one-dimensional linear Schrödinger equations with multiple moving potentials, known as transfer charge models. Focusing on the non-self-adjoint setting that arises in the study of solitons, we systematically develop the scattering theory and establish dispersive estimates under the assumption that the potentials move at significantly different velocities, even in the presence of unstable modes. In particular, we prove the existence of wave operators, asymptotic completeness, and pointwise decay of solutions, without requiring the absence of threshold resonances. Our analysis set up the fundamental work for studying the nonlinear dynamics of multi-solitons, including asymptotic stability and collisions.

math.AP↗

arXiv2025

CompLex: Music Theory Lexicon Constructed by Autonomous Agents for Automatic Music Generation

Generative artificial intelligence in music has made significant strides, yet it still falls short of the substantial achievements seen in natural language processing, primarily due to the limited availability of music data. Knowledge-informed approaches have been shown to enhance the performance of music generation models, even when only a few pieces of musical knowledge are integrated. This paper seeks to leverage comprehensive music theory in AI-driven music generation tasks, such as algorithmic composition and style transfer, which traditionally require significant manual effort with existing techniques. We introduce a novel automatic music lexicon construction model that generates a lexicon, named CompLex, comprising 37,432 items derived from just 9 manually input category keywords and 5 sentence prompt templates. A new multi-agent algorithm is proposed to automatically detect and mitigate hallucinations. CompLex demonstrates impressive performance improvements across three state-of-the-art text-to-music generation models, encompassing both symbolic and audio-based methods. Furthermore, we evaluate CompLex in terms of completeness, accuracy, non-redundancy, and executability, confirming that it possesses the key characteristics of an effective lexicon.

cs.SD↗

arXiv2025

PTSM: Physiology-aware and Task-invariant Spatio-temporal Modeling for Cross-Subject EEG Decoding

Cross-subject electroencephalography (EEG) decoding remains a fundamental challenge in brain-computer interface (BCI) research due to substantial inter-subject variability and the scarcity of subject-invariant representations. This paper proposed PTSM (Physiology-aware and Task-invariant Spatio-temporal Modeling), a novel framework for interpretable and robust EEG decoding across unseen subjects. PTSM employs a dual-branch masking mechanism that independently learns personalized and shared spatio-temporal patterns, enabling the model to preserve individual-specific neural characteristics while extracting task-relevant, population-shared features. The masks are factorized across temporal and spatial dimensions, allowing fine-grained modulation of dynamic EEG patterns with low computational overhead. To further address representational entanglement, PTSM enforces information-theoretic constraints that decompose latent embeddings into orthogonal task-related and subject-related subspaces. The model is trained end-to-end via a multi-objective loss integrating classification, contrastive, and disentanglement objectives. Extensive experiments on cross-subject motor imagery datasets demonstrate that PTSM achieves strong zero-shot generalization, outperforming state-of-the-art baselines without subject-specific calibration. Results highlight the efficacy of disentangled neural representations for achieving both personalized and transferable decoding in non-stationary neurophysiological settings.

cs.LG↗

arXiv2025

Perturbation of the nonlinear Schrödinger equation by a localized nonlinearity

We revisit the perturbative theory of infinite dimensional integrable systems developed by P. Deift and X. Zhou \cite{DZ-2}, aiming to provide new and simpler proofs of some key $L^\infty$ bounds and $L^p$ \emph{\textit{a priori}} estimates. Our proofs emphasizes a further step towards understanding focussing problems and extends the applicability to other integrable models. As a concrete application, we examine the perturbation of the one-dimensional defocussing cubic nonlinear Schrödinger equation by a localized higher-order term. We introduce improved estimates to control the power of the perturbative term and demonstrate that the perturbed equation exhibits the same long-time behavior as the completely integrable nonlinear Schrödinger equation.

math.AP↗