arXiv subjects

Ziyang Chen

Publications and source records attributed to Ziyang Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Hadamard Attention Recurrent Transformer: A Strong Baseline for Stereo Matching Transformer

Constrained by the low-rank bottleneck inherent in attention mechanisms, current stereo matching transformers suffer from limited nonlinear expressivity, which renders their feature representations sensitive to challenging conditions such as reflections. To overcome this difficulty, we present the Hadamard Attention Recurrent Stereo Transformer (HART). HART includes a novel attention mechanism that incorporates the following components: 1) The Dense Attention Kernel (DAK) maps the attention weight distribution into a high-dimensional space over (0, +$\infty$). By removing the upper bound constraint on attention weights, DAK enables more flexible modeling of complex feature interactions. This reduces feature collinearity. 2) The Multi Kernel & Order Interaction (MKOI) module extends the attention mechanism by unifying semantic and spatial knowledge learning. This integration improves the ability of HART to learn features in binocular images. Experimental results demonstrate the effectiveness of our HART. In reflective area, HART ranked 1st on the KITTI 2012 benchmark among all published methods at the time of submission. Code is available at https://github.com/ZYangChen/HART.

cs.CV↗

arXiv2025

A Question Answering Dataset for Temporal-Sensitive Retrieval-Augmented Generation

We introduce ChronoQA, a large-scale benchmark dataset for Chinese question answering, specifically designed to evaluate temporal reasoning in Retrieval-Augmented Generation (RAG) systems. ChronoQA is constructed from over 300,000 news articles published between 2019 and 2024, and contains 5,176 high-quality questions covering absolute, aggregate, and relative temporal types with both explicit and implicit time expressions. The dataset supports both single- and multi-document scenarios, reflecting the real-world requirements for temporal alignment and logical consistency. ChronoQA features comprehensive structural annotations and has undergone multi-stage validation, including rule-based, LLM-based, and human evaluation, to ensure data quality. By providing a dynamic, reliable, and scalable resource, ChronoQA enables structured evaluation across a wide range of temporal tasks, and serves as a robust benchmark for advancing time-sensitive retrieval-augmented question answering systems.

cs.CL↗

arXiv2025

From Few to More: Scribble-based Medical Image Segmentation via Masked Context Modeling and Continuous Pseudo Labels

Scribble-based weakly supervised segmentation methods have shown promising results in medical image segmentation, significantly reducing annotation costs. However, existing approaches often rely on auxiliary tasks to enforce semantic consistency and use hard pseudo labels for supervision, overlooking the unique challenges faced by models trained with sparse annotations. These models must predict pixel-wise segmentation maps from limited data, making it crucial to handle varying levels of annotation richness effectively. In this paper, we propose MaCo, a weakly supervised model designed for medical image segmentation, based on the principle of "from few to more." MaCo leverages Masked Context Modeling (MCM) and Continuous Pseudo Labels (CPL). MCM employs an attention-based masking strategy to perturb the input image, ensuring that the model's predictions align with those of the original image. CPL converts scribble annotations into continuous pixel-wise labels by applying an exponential decay function to distance maps, producing confidence maps that represent the likelihood of each pixel belonging to a specific category, rather than relying on hard pseudo labels. We evaluate MaCo on three public datasets, comparing it with other weakly supervised methods. Our results show that MaCo outperforms competing methods across all datasets, establishing a new record in weakly supervised medical image segmentation.

cs.CV↗

arXiv2025

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents

The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success often reinforce flawed or inefficient reasoning paths, a problem we term inefficient exploration. This leads to agents that are brittle and fail to generalize, as they learn to find solutions without learning how to reason coherently. To address this, we introduce RLVMR, a novel framework that integrates dense, process-level supervision into end-to-end RL by rewarding verifiable, meta-reasoning behaviors. RLVMR equips an agent to explicitly tag its cognitive steps, such as planning, exploration, and reflection, and provides programmatic, rule-based rewards for actions that contribute to effective problem-solving. These process-centric rewards are combined with the final outcome signal and optimized using a critic-free policy gradient method. On the challenging ALFWorld and ScienceWorld benchmarks, RLVMR achieves new state-of-the-art results, with our 7B model reaching an 83.6% success rate on the most difficult unseen task split. Our analysis confirms these gains stem from improved reasoning quality, including significant reductions in redundant actions and enhanced error recovery, leading to more robust, efficient, and interpretable agents.

cs.LG↗

arXiv2025

Libra: Large Chinese-based Safeguard for AI Content

Large language models (LLMs) excel in text understanding and generation but raise significant safety and ethical concerns in high-stakes applications. To mitigate these risks, we present Libra-Guard, a cutting-edge safeguard system designed to enhance the safety of Chinese-based LLMs. Leveraging a two-stage curriculum training pipeline, Libra-Guard enhances data efficiency by employing guard pretraining on synthetic samples, followed by fine-tuning on high-quality, real-world data, thereby significantly reducing reliance on manual annotations. To enable rigorous safety evaluations, we also introduce Libra-Test, the first benchmark specifically designed to evaluate the effectiveness of safeguard systems for Chinese content. It covers seven critical harm scenarios and includes over 5,700 samples annotated by domain experts. Experiments show that Libra-Guard achieves 86.79% accuracy, outperforming Qwen2.5-14B-Instruct (74.33%) and ShieldLM-Qwen-14B-Chat (65.69%), and nearing closed-source models like Claude-3.5-Sonnet and GPT-4o. These contributions establish a robust framework for advancing the safety governance of Chinese LLMs and represent a tentative step toward developing safer, more reliable Chinese AI systems.

cs.AI↗

arXiv2025

Time-Frequency Transfer over Optical Fiber

Optical time-frequency transfer establishes the metrological linkage in large-scale clock networks, which facilitates various applications. Fiber-based transfer benefits from the abundant deployment of fiber infrastructures to achieve this advantage. In this Review, we provide an overview of the advances in optical two-way time-frequency transfer, which began with characterizing the time-frequency transfer stability. Then, we discuss the system configuration, key modules, main challenges, and mainstream transfer methods. Finally, the Review concludes with an outlook on further applications toward global-scale high-precision clock networks.

physics.optics↗

arXiv2025

Pre-training Everywhere: Parameter-Efficient Fine-Tuning for Medical Image Analysis via Target Parameter Pre-training

Parameter-efficient fine-tuning (PEFT) techniques have emerged to address overfitting and high computational costs associated with fully fine-tuning in self-supervised learning. Mainstream PEFT methods add a few trainable parameters while keeping the pre-trained backbone parameters fixed. These methods achieve comparative, and often superior, performance to fully fine-tuning, demonstrating the powerful representation ability of the pre-trained backbone. Despite this success, these methods typically ignore the initialization of the new parameters, often relying solely on random initialization. We argue that if pre-training is significantly beneficial, it should be applied to all parameters requiring representational capacity. Motivated by this, we propose Target Parameter Pre-training (TPP), a simple yet effective fine-tuning framework. TPP pre-trains target parameters, i.e., the new parameters introduced during fine-tuning, in an additional stage before PEFT. During this stage, the pre-trained backbone parameters are frozen, and only the new parameters are trainable. A defined pretext task encourages the new parameters to learn specific representations of downstream data. Subsequently, when PEFT is employed, the pre-trained new parameters are loaded to enhance fine-tuning efficiency. The proposed TPP framework is versatile, allowing integration with various pre-trained backbones, pretext tasks, and PEFT methods. We evaluated the fine-tuning performance of our method on seven public datasets, covering four modalities and two task types. The results demonstrate that TPP can be easily integrated into existing PEFT methods, significantly improving performance.

cs.CV↗

arXiv2025

Enjoying Information Dividend: Gaze Track-based Medical Weakly Supervised Segmentation

Weakly supervised semantic segmentation (WSSS) in medical imaging struggles with effectively using sparse annotations. One promising direction for WSSS leverages gaze annotations, captured via eye trackers that record regions of interest during diagnostic procedures. However, existing gaze-based methods, such as GazeMedSeg, do not fully exploit the rich information embedded in gaze data. In this paper, we propose GradTrack, a framework that utilizes physicians' gaze track, including fixation points, durations, and temporal order, to enhance WSSS performance. GradTrack comprises two key components: Gaze Track Map Generation and Track Attention, which collaboratively enable progressive feature refinement through multi-level gaze supervision during the decoding process. Experiments on the Kvasir-SEG and NCI-ISBI datasets demonstrate that GradTrack consistently outperforms existing gaze-based methods, achieving Dice score improvements of 3.21\% and 2.61\%, respectively. Moreover, GradTrack significantly narrows the performance gap with fully supervised models such as nnUNet.

cs.CV↗

arXiv2025

VISTA: Enhancing Vision-Text Alignment in MLLMs via Cross-Modal Mutual Information Maximization

Current multimodal large language models (MLLMs) face a critical challenge in modality alignment, often exhibiting a bias towards textual information at the expense of other modalities like vision. This paper conducts a systematic information-theoretic analysis of the widely used cross-entropy loss in MLLMs, uncovering its implicit alignment objective. Our theoretical investigation reveals that this implicit objective has inherent limitations, leading to a degradation of cross-modal alignment as text sequence length increases, thereby hindering effective multimodal information fusion. To overcome these drawbacks, we propose Vision-Text Alignment (VISTA), a novel approach guided by our theoretical insights. VISTA introduces an explicit alignment objective designed to maximize cross-modal mutual information, preventing the degradation of visual alignment. Notably, VISTA enhances the visual understanding capabilities of existing MLLMs without requiring any additional trainable modules or extra training data, making it both efficient and practical. Our method significantly outperforms baseline models across more than a dozen benchmark datasets, including VQAv2, MMStar, and MME, paving the way for new directions in MLLM modal alignment research.

cs.CV↗

arXiv2025

Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding

Understanding long video content is a complex endeavor that often relies on densely sampled frame captions or end-to-end feature selectors, yet these techniques commonly overlook the logical relationships between textual queries and visual elements. In practice, computational constraints necessitate coarse frame subsampling, a challenge analogous to "finding a needle in a haystack." To address this issue, we introduce a semantics-driven search framework that reformulates keyframe selection under the paradigm of Visual Semantic-Logical Search. Specifically, we systematically define four fundamental logical dependencies: 1) spatial co-occurrence, 2) temporal proximity, 3) attribute dependency, and 4) causal order. These relations dynamically update frame sampling distributions through an iterative refinement process, enabling context-aware identification of semantically critical frames tailored to specific query requirements. Our method establishes new SOTA performance on the manually annotated benchmark in key-frame selection metrics. Furthermore, when applied to downstream video question-answering tasks, the proposed approach demonstrates the best performance gains over existing methods on LongVideoBench and Video-MME, validating its effectiveness in bridging the logical gap between textual queries and visual-temporal reasoning. The code will be publicly available.

cs.CV↗

arXiv2025

Research on trigger technology of MRPC TOF-PET system and imaging results of $^{22}$Na radioactive source

This study focuses on developing a self-triggered data acquisition system and a noise reduction algorithm for the Multi-gap Resistive Plate Chamber (MRPC) Time-of-Flight Positron Emission Tomography (TOF-PET) system. The system integrates a fast front-end amplifier, a waveform digitization module based on the DRS4 chip, and an efficient noise reduction algorithm to address challenges such as high noise trigger rates and precise gamma-ray detection. The proposed self-triggered system, through threshold discrimination, coincidence logic, and continuous oscillation check, reduces the noise trigger rate to 0.004 Hz. Experimental results show that the system accurately localizes and images the $^{22}$Na radioactive source, and has a good time resolution of 162 ps FWHM for 0.511 MeV gamma rays.

physics.ins-det↗

arXiv2025

MoCha-Stereo: Motif Channel Attention Network for Stereo Matching

Learning-based stereo matching techniques have made significant progress. However, existing methods inevitably lose geometrical structure information during the feature channel generation process, resulting in edge detail mismatches. In this paper, the Motif Cha}nnel Attention Stereo Matching Network (MoCha-Stereo) is designed to address this problem. We provide the Motif Channel Correlation Volume (MCCV) to determine more accurate edge matching costs. MCCV is achieved by projecting motif channels, which capture common geometric structures in feature channels, onto feature maps and cost volumes. In addition, edge variations in %potential feature channels of the reconstruction error map also affect details matching, we propose the Reconstruction Error Motif Penalty (REMP) module to further refine the full-resolution disparity estimation. REMP integrates the frequency information of typical channel features from the reconstruction error. MoCha-Stereo ranks 1st on the KITTI-2015 and KITTI-2012 Reflective leaderboards. Our structure also shows excellent performance in Multi-View Stereo. Code is avaliable at https://github.com/ZYangChen/MoCha-Stereo.

cs.CV↗

arXiv2025

Video-Guided Foley Sound Generation with Multimodal Controls

Generating sound effects for videos often requires creating artistic sound effects that diverge significantly from real-life sources and flexible control in the sound design. To address this problem, we introduce MultiFoley, a model designed for video-guided sound generation that supports multimodal conditioning through text, audio, and video. Given a silent video and a text prompt, MultiFoley allows users to create clean sounds (e.g., skateboard wheels spinning without wind noise) or more whimsical sounds (e.g., making a lion's roar sound like a cat's meow). MultiFoley also allows users to choose reference audio from sound effects (SFX) libraries or partial videos for conditioning. A key novelty of our model lies in its joint training on both internet video datasets with low-quality audio and professional SFX recordings, enabling high-quality, full-bandwidth (48kHz) audio generation. Through automated evaluations and human studies, we demonstrate that MultiFoley successfully generates synchronized high-quality sounds across varied conditional inputs and outperforms existing methods. Please see our project page for video results: https://ificl.github.io/MultiFoley/

cs.CV↗

arXiv2025

Meta Curvature-Aware Minimization for Domain Generalization

Domain generalization (DG) aims to enhance the ability of models trained on source domains to generalize effectively to unseen domains. Recently, Sharpness-Aware Minimization (SAM) has shown promise in this area by reducing the sharpness of the loss landscape to obtain more generalized models. However, SAM and its variants sometimes fail to guide the model toward a flat minimum, and their training processes exhibit limitations, hindering further improvements in model generalization. In this paper, we first propose an improved model training process aimed at encouraging the model to converge to a flat minima. To achieve this, we design a curvature metric that has a minimal effect when the model is far from convergence but becomes increasingly influential in indicating the curvature of the minima as the model approaches a local minimum. Then we derive a novel algorithm from this metric, called Meta Curvature-Aware Minimization (MeCAM), to minimize the curvature around the local minima. Specifically, the optimization objective of MeCAM simultaneously minimizes the regular training loss, the surrogate gap of SAM, and the surrogate gap of meta-learning. We provide theoretical analysis on MeCAM's generalization error and convergence rate, and demonstrate its superiority over existing DG methods through extensive experiments on five benchmark DG datasets, including PACS, VLCS, OfficeHome, TerraIncognita, and DomainNet. Code will be available on GitHub.

cs.CV↗

arXiv2025

Long distance local local oscillator continuous variable quantum key distribution with digital signal processing

Quantum key distribution relying on the principles of quantum mechanics enables two parties to produce a shared random secret key, thereby ensuring the security of data transmission. Continuous variable quantum key distribution (CV-QKD) is widely applied because it can be well combined with standard telecommunication technology. Compared to CV-QKD with a transmitting local oscillator, the proposal of CV-QKD with a local local oscillator overcomes the limitation that local oscillator will attenuate as transmission distance increases, providing new possibilities in long-distance transmission. However, challenges still persist in practical long-distance transmission, including data sampling and recovery under low signal-to-noise ratio conditions. In order to better recover data and reduce the additional excess noise, we propose the least squares fitting algorithm to get more accurate sampling data and complete more accurate phase compensation.Herein, we demonstrate the long-distance local local oscillator CV-QKD experiment which have considered the effect of finite-size block over 120 km of standard optical fiber with high efficient real-time post-processing. The results not only verify the good performance of the system over long distance, but also paves the way for large-scale quantum secure communications in the future.

quant-ph↗

arXiv2025

A Survey of fMRI to Image Reconstruction

Functional magnetic resonance imaging (fMRI) based image reconstruction plays a pivotal role in decoding human perception, with applications in neuroscience and brain-computer interfaces. While recent advancements in deep learning and large-scale datasets have driven progress, challenges such as data scarcity, cross-subject variability, and low semantic consistency persist. To address these issues, we introduce the concept of fMRI-to-Image Learning (fMRI2Image) and present the first systematic review in this field. This review highlights key challenges, categorizes methodologies such as fMRI signal encoding, feature mapping, and image generator. Finally, promising research directions are proposed to advance this emerging frontier, providing a reference for future studies.

cs.CV↗

arXiv2025

From Visuals to Vocabulary: Establishing Equivalence Between Image and Text Token Through Autoregressive Pre-training in MLLMs

While MLLMs perform well on perceptual tasks, they lack precise multimodal alignment, limiting performance. To address this challenge, we propose Vision Dynamic Embedding-Guided Pretraining (VDEP), a hybrid autoregressive training paradigm for MLLMs. Utilizing dynamic embeddings from the MLP following the visual encoder, this approach supervises image hidden states and integrates image tokens into autoregressive training. Existing MLLMs primarily focused on recovering information from textual inputs, often neglecting the effective processing of image data. In contrast, the key improvement of this work is the reinterpretation of multimodal alignment as a process of recovering information from input data, with particular emphasis on reconstructing detailed visual features.The proposed method seamlessly integrates into standard models without architectural changes. Experiments on 13 benchmarks show VDEP outperforms baselines, surpassing existing methods.

cs.CV↗

arXiv2025

Advancing General Multimodal Capability of Vision-language Models with Pyramid-descent Visual Position Encoding

Vision-language Models (VLMs) have shown remarkable capabilities in advancing general artificial intelligence, yet the irrational encoding of visual positions persists in inhibiting the models' comprehensive perception performance across different levels of granularity. In this work, we propose Pyramid-descent Visual Position Encoding (PyPE), a novel approach designed to enhance the perception of visual tokens within VLMs. By assigning visual position indexes from the periphery to the center and expanding the central receptive field incrementally, PyPE addresses the limitations of traditional raster-scan methods and mitigates the long-term decay effects induced by Rotary Position Embedding (RoPE). Our method reduces the relative distance between interrelated visual elements and instruction tokens, promoting a more rational allocation of attention weights and allowing for a multi-granularity perception of visual elements and countering the over-reliance on anchor tokens. Extensive experimental evaluations demonstrate that PyPE consistently improves the general capabilities of VLMs across various sizes. Code is available at https://github.com/SakuraTroyChen/PyPE.

cs.CV↗