arXiv subjects

Qiang Zhang

Publications and source records attributed to Qiang Zhang.

At least 127 records · Page 7Linked to original sources

arXiv2025

MAD: Multi-Alignment MEG-to-Text Decoding

Deciphering language from brain activity is a crucial task in brain-computer interface (BCI) research. Non-invasive cerebral signaling techniques including electroencephalography (EEG) and magnetoencephalography (MEG) are becoming increasingly popular due to their safety and practicality, avoiding invasive electrode implantation. However, current works under-investigated three points: 1) a predominant focus on EEG with limited exploration of MEG, which provides superior signal quality; 2) poor performance on unseen text, indicating the need for models that can better generalize to diverse linguistic contexts; 3) insufficient integration of information from other modalities, which could potentially constrain our capacity to comprehensively understand the intricate dynamics of brain activity. This study presents a novel approach for translating MEG signals into text using a speech-decoding framework with multiple alignments. Our method is the first to introduce an end-to-end multi-alignment framework for totally unseen text generation directly from MEG signals. We achieve an impressive BLEU-1 score on the \textit{GWilliams} dataset, significantly outperforming the baseline from 5.49 to 6.86 on the BLEU-1 metric. This improvement demonstrates the advancement of our model towards real-world applications and underscores its potential in advancing BCI research. Code is available at $\href{https://github.com/NeuSpeech/MAD-MEG2text}{https://github.com/NeuSpeech/MAD-MEG2text}$.

cs.CL↗

arXiv2025

High-Fidelity and Long-Duration Human Image Animation with Diffusion Transformer

Recent progress in diffusion models has significantly advanced the field of human image animation. While existing methods can generate temporally consistent results for short or regular motions, significant challenges remain, particularly in generating long-duration videos. Furthermore, the synthesis of fine-grained facial and hand details remains under-explored, limiting the applicability of current approaches in real-world, high-quality applications. To address these limitations, we propose a diffusion transformer (DiT)-based framework which focuses on generating high-fidelity and long-duration human animation videos. First, we design a set of hybrid implicit guidance signals and a sharpness guidance factor, enabling our framework to additionally incorporate detailed facial and hand features as guidance. Next, we incorporate the time-aware position shift fusion module, modify the input format within the DiT backbone, and refer to this mechanism as the Position Shift Adaptive Module, which enables video generation of arbitrary length. Finally, we introduce a novel data augmentation strategy and a skeleton alignment model to reduce the impact of human shape variations across different identities. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving superior performance in both high-fidelity and long-duration human image animation.

cs.CV↗

arXiv2025

Distillation-Guided Structural Transfer for Continual Learning Beyond Sparse Distributed Memory

Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks via Top-K activation and have shown resilience against catastrophic forgetting. However, their rigid modularity limits cross-task knowledge reuse and leads to performance degradation under high sparsity. We propose Selective Subnetwork Distillation (SSD), a structurally guided continual learning framework that treats distillation not as a regularizer but as a topology-aligned information conduit. SSD identifies neurons with high activation frequency and selectively distills knowledge within previous Top-K subnetworks and output logits, without requiring replay or task labels. This enables structural realignment while preserving sparse modularity. Experiments on Split CIFAR-10, CIFAR-100, and MNIST demonstrate that SSD improves accuracy, retention, and representation coverage, offering a structurally grounded solution for sparse continual learning.

cs.LG↗

arXiv2025

Site Preference and Possible Coexistence of Antiferromagnetic Order and Magnetic Frustration in (Co1-xMgx)10Ge3O16 (0 <= x <= 30%)

Geometrically frustrated magnetism has attracted tremendous attention while chemical doping has been utilized as an important tool to probe frustrated magnetism in various systems. Here we perform a systematic study by doping non-magnetic Mg2+ into a magnetically complicated system, Co10Ge3O16, which contains three frustrated sublattices of Co2+, e.g., triangular Co1, Kagome Co2 and Co3 sublattices. By growing crystals for (Co1-xMgx)10Ge3O16 (0 < x <= 30%), we observed obvious site preference of Mg2+ on Co1 and Co3 sites over the Co2 site. Powder X-ray diffraction (XRD) patterns confirm the high purity of the samples and indicate systematic peak shift, consistent with the loading compositions. Although previously investigated, the magnetic structure and expected magnetic frustration in this system are not fully uncovered. Our temperature-dependent magnetic susceptibility measurements suggest that the high-temperature magnetostructural phase transition with antiferromagnetic ordering and a low-temperature broad peak are suppressed with Mg2+ doping, while two new magnetic features emerge at high Mg2+ level. Moreover, the structural phase transition from high-temperature R-3m to low-temperature C2/m space group is absent at the antiferromagnetic ordering temperature, as confirmed by single-crystal XRD. By analyzing the heat capacity and neutron powder diffraction results of the highest doped sample, (Co0.7Mg0.3)10Ge3O16, we speculate that the Co1 site is responsible for the long-range antiferromagnetic ordering, while the other two sites are short-range correlated in addition to a Mg2+-induced spin-glass state. This study provides more insights into the complex magnetism in Co10Ge3O16 by using the non-magnetic Mg2+ as a probe. However, detailed magnetic structure requires further efforts on growing large single crystals.

cond-mat.str-el↗

arXiv2025

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream

Reconstructing Dynamic 3D Gaussian Splatting (3DGS) from low-framerate RGB videos is challenging. This is because large inter-frame motions will increase the uncertainty of the solution space. For example, one pixel in the first frame might have more choices to reach the corresponding pixel in the second frame. Event cameras can asynchronously capture rapid visual changes and are robust to motion blur, but they do not provide color information. Intuitively, the event stream can provide deterministic constraints for the inter-frame large motion by the event trajectories. Hence, combining low-temporal-resolution images with high-framerate event streams can address this challenge. However, it is challenging to jointly optimize Dynamic 3DGS using both RGB and event modalities due to the significant discrepancy between these two data modalities. This paper introduces a novel framework that jointly optimizes dynamic 3DGS from the two modalities. The key idea is to adopt event motion priors to guide the optimization of the deformation fields. First, we extract the motion priors encoded in event streams by using the proposed LoCM unsupervised fine-tuning framework to adapt an event flow estimator to a certain unseen scene. Then, we present the geometry-aware data association method to build the event-Gaussian motion correspondence, which is the primary foundation of the pipeline, accompanied by two useful strategies, namely motion decomposition and inter-frame pseudo-label. Extensive experiments show that our method outperforms existing image and event-based approaches across synthetic and real scenes and prove that our method can effectively optimize dynamic 3DGS with the help of event data.

cs.CV↗

arXiv2025

Induction Head Toxicity Mechanistically Explains Repetition Curse in Large Language Models

Repetition curse is a phenomenon where Large Language Models (LLMs) generate repetitive sequences of tokens or cyclic sequences. While the repetition curse has been widely observed, its underlying mechanisms remain poorly understood. In this work, we investigate the role of induction heads--a specific type of attention head known for their ability to perform in-context learning--in driving this repetitive behavior. Specifically, we focus on the "toxicity" of induction heads, which we define as their tendency to dominate the model's output logits during repetition, effectively excluding other attention heads from contributing to the generation process. Our findings have important implications for the design and training of LLMs. By identifying induction heads as a key driver of the repetition curse, we provide a mechanistic explanation for this phenomenon and suggest potential avenues for mitigation. We also propose a technique with attention head regularization that could be employed to reduce the dominance of induction heads during generation, thereby promoting more diverse and coherent outputs.

cs.CL↗

arXiv2025

Class-Conditional Distribution Balancing for Group Robust Classification

Spurious correlations that lead models to correct predictions for the wrong reasons pose a critical challenge for robust real-world generalization. Existing research attributes this issue to group imbalance and addresses it by maximizing group-balanced or worst-group accuracy, which heavily relies on expensive bias annotations. A compromise approach involves predicting bias information using extensively pretrained foundation models, which requires large-scale data and becomes impractical for resource-limited rare domains. To address these challenges, we offer a novel perspective by reframing the spurious correlations as imbalances or mismatches in class-conditional distributions, and propose a simple yet effective robust learning method that eliminates the need for both bias annotations and predictions. With the goal of maximizing the conditional entropy (uncertainty) of the label given spurious factors, our method leverages a sample reweighting strategy to achieve class-conditional distribution balancing, which automatically highlights minority groups and classes, effectively dismantling spurious correlations and producing a debiased data distribution for classification. Extensive experiments and analysis demonstrate that our approach consistently delivers state-of-the-art performance, rivaling methods that rely on bias supervision.

cs.LG↗

arXiv2025

Exploring System 1 and 2 communication for latent reasoning in LLMs

Should LLM reasoning live in a separate module, or within a single model's forward pass and representational space? We study dual-architecture latent reasoning, where a fluent Base exchanges latent messages with a Coprocessor, and test two hypotheses aimed at improving latent communication over Liu et al. (2024): (H1) increase channel capacity; (H2) learn communication via joint finetuning. Under matched latent-token budgets on GPT-2 and Qwen-3, H2 is consistently strongest while H1 yields modest gains. A unified soft-embedding baseline, a single model with the same forward pass and shared representations, using the same latent-token budget, nearly matches H2 and surpasses H1, suggesting current dual designs mostly add compute rather than qualitatively improving reasoning. Across GSM8K, ProsQA, and a Countdown stress test with increasing branching factor, scaling the latent-token budget beyond small values fails to improve robustness. Latent analyses show overlapping subspaces with limited specialization, consistent with weak reasoning gains. We conclude dual-model latent reasoning remains promising in principle, but likely requires objectives and training schedules that explicitly shape latent spaces for algorithmic planning.

cs.LG↗

arXiv2025

SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overhead

Vision-Language-Action (VLA) models built on pretrained Vision-Language Models (VLMs) show strong potential but are limited in practicality due to their large parameter counts. To mitigate this issue, using a lightweight VLM has been explored, but it compromises spatiotemporal reasoning. Although some methods suggest that incorporating additional 3D inputs can help, they usually rely on large VLMs to fuse 3D and 2D inputs and still lack temporal understanding. Therefore, we propose SwiftVLA, an architecture that enhances a compact model with 4D understanding while preserving design efficiency. Specifically, our approach features a pretrained 4D visual geometry transformer with a temporal cache that extracts 4D features from 2D images. Then, to enhance the VLM's ability to exploit both 2D images and 4D features, we introduce Fusion Tokens, a set of learnable tokens trained with a future prediction objective to generate unified representations for action generation. Finally, we introduce a mask-and-reconstruct strategy that masks 4D inputs to the VLM and trains the VLA to reconstruct them, enabling the VLM to learn effective 4D representations and allowing the 4D branch to be dropped at inference with minimal performance loss. Experiments in real and simulated environments show that SwiftVLA outperforms lightweight baselines and rivals VLAs up to 7 times larger, achieving comparable performance on edge devices while being 18 times faster and reducing memory footprint by 12 times.

cs.CV↗

arXiv2025

Opening the Black Box: An Explainable, Few-shot AI4E Framework Informed by Physics and Expert Knowledge for Materials Engineering

The industrial adoption of Artificial Intelligence for Engineering (AI4E) faces two fundamental bottlenecks: scarce high-quality data and the lack of interpretability in black-box models-particularly critical in safety-sensitive sectors like aerospace. We present an explainable, few-shot AI4E framework that is systematically informed by physics and expert knowledge throughout its architecture. Starting from only 32 experimental samples in an aerial K439B superalloy castings repair welding case, we first augment physically plausible synthetic data through a three-stage protocol: differentiated noise injection calibrated to process variabilities, enforcement of hard physical constraints, and preservation of inter-parameter relationships. We then employ a nested optimization strategy for constitutive model discovery, where symbolic regression explores equation structures while differential evolution optimizes parameters, followed by intensive parameter refinement using hybrid global-local optimization. The resulting interpretable constitutive equation achieves 88% accuracy in predicting hot-cracking tendency. This equation not only provides quantitative predictions but also delivers explicit physical insight, revealing how thermal, geometric, and metallurgical mechanisms couple to drive cracking-thereby advancing engineers' cognitive understanding of the process. Furthermore, the constitutive equation serves as a multi-functional tool for process optimization and high-fidelity virtual data generation, enabling accuracy improvements in other data-driven models. Our approach provides a general blueprint for developing trustworthy AI systems that embed engineering domain knowledge directly into their architecture, enabling reliable adoption in high-stakes industrial applications where data is limited but physical understanding is available.

cs.LG↗

arXiv2025

Tracking and Segmenting Anything in Any Modality

Tracking and segmentation play essential roles in video understanding, providing basic positional information and temporal association of objects within video sequences. Despite their shared objective, existing approaches often tackle these tasks using specialized architectures or modality-specific parameters, limiting their generalization and scalability. Recent efforts have attempted to unify multiple tracking and segmentation subtasks from the perspectives of any modality input or multi-task inference. However, these approaches tend to overlook two critical challenges: the distributional gap across different modalities and the feature representation gap across tasks. These issues hinder effective cross-task and cross-modal knowledge sharing, ultimately constraining the development of a true generalist model. To address these limitations, we propose a universal tracking and segmentation framework named SATA, which unifies a broad spectrum of tracking and segmentation subtasks with any modality input. Specifically, a Decoupled Mixture-of-Expert (DeMoE) mechanism is presented to decouple the unified representation learning task into the modeling process of cross-modal shared knowledge and specific information, thus enabling the model to maintain flexibility while enhancing generalization. Additionally, we introduce a Task-aware Multi-object Tracking (TaMOT) pipeline to unify all the task outputs as a unified set of instances with calibrated ID information, thereby alleviating the degradation of task-specific knowledge during multi-task training. SATA demonstrates superior performance on 18 challenging tracking and segmentation benchmarks, offering a novel perspective for more generalizable video understanding.

cs.CV↗

arXiv2025

Domain-Shared Learning and Gradual Alignment for Unsupervised Domain Adaptation Visible-Infrared Person Re-Identification

Recently, Visible-Infrared person Re-Identification (VI-ReID) has achieved remarkable performance on public datasets. However, due to the discrepancies between public datasets and real-world data, most existing VI-ReID algorithms struggle in real-life applications. To address this, we take the initiative to investigate Unsupervised Domain Adaptation Visible-Infrared person Re-Identification (UDA-VI-ReID), aiming to transfer the knowledge learned from the public data to real-world data without compromising accuracy and requiring the annotation of new samples. Specifically, we first analyze two basic challenges in UDA-VI-ReID, i.e., inter-domain modality discrepancies and intra-domain modality discrepancies. Then, we design a novel two-stage model, i.e., Domain-Shared Learning and Gradual Alignment (DSLGA), to handle these discrepancies. In the first pre-training stage, DSLGA introduces a Domain-Shared Learning Strategy (DSLS) to mitigate ineffective pre-training caused by inter-domain modality discrepancies via exploiting shared information between the source and target domains. While, in the second fine-tuning stage, DSLGA designs a Gradual Alignment Strategy (GAS) to handle the cross-modality alignment challenges between visible and infrared data caused by the large intra-domain modality discrepancies through a cluster-to-holistic alignment way. Finally, a new UDA-VI-ReID testing method i.e., CMDA-XD, is constructed for training and testing different UDA-VI-ReID models. A large amount of experiments demonstrate that our method significantly outperforms existing domain adaptation methods for VI-ReID and even some supervised methods under various settings.

cs.CV↗

arXiv2025

Multi-Text Guided Few-Shot Semantic Segmentation

Recent CLIP-based few-shot semantic segmentation methods introduce class-level textual priors to assist segmentation by typically using a single prompt (e.g., a photo of class). However, these approaches often result in incomplete activation of target regions, as a single textual description cannot fully capture the semantic diversity of complex categories. Moreover, they lack explicit cross-modal interaction and are vulnerable to noisy support features, further degrading visual prior quality. To address these issues, we propose the Multi-Text Guided Few-Shot Semantic Segmentation Network (MTGNet), a dual-branch framework that enhances segmentation performance by fusing diverse textual prompts to refine textual priors and guide the cross-modal optimization of visual priors. Specifically, we design a Multi-Textual Prior Refinement (MTPR) module that suppresses interference and aggregates complementary semantic cues to enhance foreground activation and expand semantic coverage for structurally complex objects. We introduce a Text Anchor Feature Fusion (TAFF) module, which leverages multi-text embeddings as semantic anchors to facilitate the transfer of discriminative local prototypes from support images to query images, thereby improving semantic consistency and alleviating intra-class variations. Furthermore, a Foreground Confidence-Weighted Attention (FCWA) module is presented to enhance visual prior robustness by leveraging internal self-similarity within support foreground features. It adaptively down-weights inconsistent regions and effectively suppresses interference in the query segmentation process. Extensive experiments on standard FSS benchmarks validate the effectiveness of MTGNet. In the 1-shot setting, it achieves 76.8% mIoU on PASCAL-5i and 57.4% on COCO-20i, with notable improvements in folds exhibiting high intra-class variations.

cs.CV↗

arXiv2025

Playmate2: Training-Free Multi-Character Audio-Driven Animation via Diffusion Transformer with Reward Feedback

Recent advances in diffusion models have significantly improved audio-driven human video generation, surpassing traditional methods in both quality and controllability. However, existing approaches still face challenges in lip-sync accuracy, temporal coherence for long video generation, and multi-character animation. In this work, we propose a diffusion transformer (DiT)-based framework for generating lifelike talking videos of arbitrary length, and introduce a training-free method for multi-character audio-driven animation. First, we employ a LoRA-based training strategy combined with a position shift inference approach, which enables efficient long video generation while preserving the capabilities of the foundation model. Moreover, we combine partial parameter updates with reward feedback to enhance both lip synchronization and natural body motion. Finally, we propose a training-free approach, Mask Classifier-Free Guidance (Mask-CFG), for multi-character animation, which requires no specialized datasets or model modifications and supports audio-driven animation for three or more characters. Experimental results demonstrate that our method outperforms existing state-of-the-art approaches, achieving high-quality, temporally coherent, and multi-character audio-driven video generation in a simple, efficient, and cost-effective manner.

cs.CV↗

arXiv2025

Classification of Fixed Subgroups of Endomorphisms in Free-abelian Times Surface Groups

In this paper, we first study the endomorphisms of free-abelian times surface groups and give a characterization of when they are injective and surjective. Then, we see that free-abelian times hyperbolic groups are Hopfian but not co-Hopfian. Moreover, we give a complete classification of fixed subgroups of endomorphisms in free-abelian times surface groups, which extends that of automorphisms. Finally, we study the endomorphisms of free-abelian times non-elementary torsion-free hyperbolic groups and give an equivalent condition for them to contain, up to isomorphism, finitely many end-fixed subgroups.

math.GR↗

arXiv2025

Memory-Assisted Nonlocal Interferometer Towards Long-Baseline Telescopes

Quantum networks and remote quantum entanglement serve as vital future quantum communication resources with broad applicability. A key direction lies in extending the baseline of optical interferometers to enhance angular resolution in interferometric imaging. Here, by measuring a simulated thermal light field, we report the demonstration of a memory-assisted nonlocal interferometer achieving a fiber-link baseline up to 20 km while simultaneously showing its capability to compensate for a geometric delay equivalent to 1.5 km. This result demonstrates potential for enhancing the angular resolution of interferometric imaging in the optical band with delocalized single-photon entanglement, and paves the way for future application of quantum memories in astronomical observation.

quant-ph↗

arXiv2025

Effects of diode laser photobiomodulation on peri-implant inflammation and stability in orthodontic mini-implants: A randomized controlled trial

Peri-implant inflammation in orthodontic mini-implant may lead to patient discomfort and treatment failure. This study aims to evaluate the effects of diode laser application on the health of mini-implant, preventing peri-implantitis and promoting healing. A randomized controlled trial was conducted involving 30 orthodontic patients (12 males and 18 females, aged 18-32) who had mini-implants implanted on both sides of the maxilla for anterior teeth retraction. One side of each patient was assigned to either an experimental group receiving diode laser irradiation (650 nm, 25 mW) at specific postoperative intervals or a control group receiving simulated radiation. Clinical assessments included plaque index, modified sulcus bleeding index, probing depth, and incidence of peri-implant mucositis and implant mobility, measured at 1, 4, and 12 weeks post-implantation. Additionally, interleukin-1 beta (IL-1\b{eta}) levels in peri-implant fluid were analyzed via enzyme-linked immunosorbent assay (ELISA). Results indicated that the experimental group exhibited significantly lower plaque indices, sulcus bleeding indices, and probing depths (p < 0.05) compared to the control group. Moreover, the experimental group had fewer cases of peri-implant mucositis (p < 0.05), while differences in implant stability were not statistically significant (p > 0.05). IL-1\b{eta} levels were consistently lower in the experimental group throughout the study duration (p < 0.05). In conclusion, adjunctive diode laser therapy appears to enhance peri-implant health and reduce complications associated with orthodontic mini-implants, suggesting a promising direction for improving patient outcomes in orthodontics. Future research should explore long-term effects and the mechanisms underlying these benefits.

physics.med-ph↗

arXiv2025

Knowledge-Augmented Long-CoT Generation for Complex Biomolecular Reasoning

Understanding complex biomolecular mechanisms requires multi-step reasoning across molecular interactions, signaling cascades, and metabolic pathways. While large language models(LLMs) show promise in such tasks, their application to biomolecular problems is hindered by logical inconsistencies and the lack of grounding in domain knowledge. Existing approaches often exacerbate these issues: reasoning steps may deviate from biological facts or fail to capture long mechanistic dependencies. To address these challenges, we propose a Knowledge-Augmented Long-CoT Reasoning framework that integrates LLMs with knowledge graph-based multi-hop reasoning chains. The framework constructs mechanistic chains via guided multi-hop traversal and pruning on the knowledge graph; these chains are then incorporated into supervised fine-tuning to improve factual grounding and further refined with reinforcement learning to enhance reasoning reliability and consistency. Furthermore, to overcome the shortcomings of existing benchmarks, which are often restricted in scale and scope and lack annotations for deep reasoning chains, we introduce PrimeKGQA, a comprehensive benchmark for biomolecular question answering. Experimental results on both PrimeKGQA and existing datasets demonstrate that although larger closed-source models still perform well on relatively simple tasks, our method demonstrates clear advantages as reasoning depth increases, achieving state-of-the-art performance on multi-hop tasks that demand traversal of structured biological knowledge. These findings highlight the effectiveness of combining structured knowledge with advanced reasoning strategies for reliable and interpretable biomolecular reasoning.

cs.AI↗