arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 325 records · Page 18Linked to original sources

arXiv2026

From Ecological Connectivity to Outbreak Risk: A Heterogeneous Graph Network for Epidemiological Reasoning under Sparse Spatiotemporal Data

Estimating population-level prevalence and transmission dynamics of wildlife pathogens can be challenging, partly because surveillance data is sparse, detection-driven, and unevenly sequenced. Using highly pathogenic avian influenza A/H5 clade 2.3.4.4b as a case study, we develop zooNet, a graph-based epidemiological framework that integrates mechanistic transmission simulation, metadata-driven genetic distance imputation, and spatiotemporal graph learning to reconstruct outbreak dynamics from incomplete observations. Applied to wild bird surveillance data from the United States during 2022, zooNet recovered coherent spatiotemporal structure despite intermittent detections, revealing sustained regional circulation across multiple migratory flyways. The framework consistently identified counties with ongoing transmission weeks to months before confirmed detections, including persistent activity in northeastern regions prior to documented re-emergence. These signals were detectable even in areas with sparse sequencing and irregular reporting. These results show that explicitly representing ecological processes and inferred genomic connectivity within a unified graph structure allows persistence and spatial risk structure to be inferred from detection-driven wildlife surveillance data.

q-bio.PE↗

arXiv2026

Brain-Inspired Exploration of Functional Networks and Key Neurons in Large Language Models

In recent years, the rapid advancement of large language models (LLMs) in natural language processing has sparked significant interest among researchers to understand their mechanisms and functional characteristics. Although prior studies have attempted to explain LLM functionalities by identifying and interpreting specific neurons, these efforts mostly focus on individual neuron contributions, neglecting the fact that human brain functions are realized through intricate interaction networks. Inspired by research on functional brain networks (FBNs) in the field of neuroscience, we utilize similar methodologies estabilished in FBN analysis to explore the "functional networks" within LLMs in this study. Experimental results highlight that, much like the human brain, LLMs exhibit certain functional networks that recur frequently during their operation. Further investigation reveals that these functional networks are indispensable for LLM performance. Inhibiting key functional networks severely impairs the model's capabilities. Conversely, amplifying the activity of neurons within these networks can enhance either the model's overall performance or its performance on specific tasks. This suggests that these functional networks are strongly associated with either specific tasks or the overall performance of the LLM. Code is available at https://github.com/WhatAboutMyStar/LLM_ACTIVATION.

q-bio.NC↗

arXiv2026

Unleashing the Potential of Neighbors: Diffusion-based Latent Neighbor Generation for Session-based Recommendation

Session-based recommendation aims to predict the next item that anonymous users may be interested in, based on their current session interactions. Recent studies have demonstrated that retrieving neighbor sessions to augment the current session can effectively alleviate the data sparsity issue and improve recommendation performance. However, existing methods typically rely on explicitly observed session data, neglecting latent neighbors - not directly observed but potentially relevant within the interest space - thereby failing to fully exploit the potential of neighbor sessions in recommendation. To address the above limitation, we propose a novel model of diffusion-based latent neighbor generation for session-based recommendation, named DiffSBR. Specifically, DiffSBR leverages two diffusion modules, including retrieval-augmented diffusion and self-augmented diffusion, to generate high-quality latent neighbors. In the retrieval-augmented diffusion module, we leverage retrieved neighbors as guiding signals to constrain and reconstruct the distribution of latent neighbors. Meanwhile, we adopt a training strategy that enables the retriever to learn from the feedback provided by the generator. In the self-augmented diffusion module, we explicitly guide the generation of latent neighbors by injecting the current session's multi-modal signals through contrastive learning. After obtaining the generated latent neighbors, we utilize them to enhance session representations for improving session-based recommendation. Extensive experiments on four public datasets show that DiffSBR generates effective latent neighbors and improves recommendation performance against state-of-the-art baselines.

cs.IR↗

arXiv2026

High-Performance KV$_3$Sb$_5$/WSe$_2$ van der Waals Photodetectors

Kagome metals AV$_3$Sb$_5$ (A = K, Rb, Cs) have recently emerged as a promising platform for exploring correlated and topological quantum states, yet their potential for optoelectronic applications remains largely unexplored. Here, we report high-performance photodetectors based on van der Waals KV$_3$Sb$_5$/WSe$_2$ heterojunctions. A high-quality Schottky interface readily forms between KV$_3$Sb$_5$ and WSe$_2$, enabling efficient separation and transport of photoinduced carriers. Under 520 nm illumination, the device achieves an open-circuit voltage up to 0.6 V, a responsivity of 809 mA/W, and a fast response time of 18.3 us. This work demonstrates the promising optoelectronic applications of Kagome metals and highlights the potential of KV$_3$Sb$_5$-based van der Waals heterostructures for high-performance photodetection.

cond-mat.mtrl-sci↗

arXiv2026

Pseudospin Formulation of Quench Dynamics in the Semiclassical Holstein Model

We present a pseudospin formulation for the post-quench dynamics of charge-density-wave (CDW) order in the half-filled spinless Holstein model on a square lattice, assuming spatially homogeneous evolution. This Anderson pseudospin description captures the coherent nonequilibrium dynamics of the coupled electron-lattice system. Numerical simulations reveal three distinct dynamical regimes of the CDW order parameter following a quench-locked oscillations, Landau-damped dynamics, and overdamped relaxation-closely paralleling quench dynamics in BCS superconductors and other electronically driven symmetry-breaking phases. Crucially, however, the presence of dynamical lattice degrees of freedom leads to qualitatively different long-time behavior. In particular, while the oscillation amplitude is reduced in the damped regimes, CDW oscillations do not fully decay but instead persist indefinitely due to feedback from the lattice field. We further show that these persistent oscillations are characterized by a nonequilibrium electronic distribution, which provides an intuitive understanding of both their amplitude and the renormalization of the oscillation frequency relative to the bare Holstein phonon frequency. Our results highlight the essential role of lattice dynamics in nonequilibrium ordered phases and establish a clear distinction between electron-lattice-driven CDW dynamics and their purely electronic counterparts.

cond-mat.str-el↗

arXiv2026

Experimental study on an S-band near-field microwave magnetron power transmission system on hundred-watt level

A multi-magnetron microwave source, a metamaterial transmitting antenna, and a large power rectenna array are presented to build a near-field 2.45 GHz microwave power transmission system. The square 1 m2 rectenna array consists of sixteen rectennas with 2048 Schottky diodes for large power microwave rectifying. It receives microwave power and converts them into DC power. The design, structure, and measured performance of a unit rectenna as well as the entail rectenna array are presented in detail. The multi-magnetron microwave power source switches between half and full output power levels, i.e. the half-wave and full-wave modes. The transmission antenna is formed by a double-layer metallic hole array, which is applied to combine the output power of each magnetron. The rectenna array DC output power reaches 67.3 W on a 1.2 ohm DC load at a distance of 5.5 m from the transmission antenna. DC output power is affected by the distance, DC load, and the mode of microwave power source. It shows that conventional low power Schottky diodes can be applied to a microwave power transmission system with simple magnetrons to realise large power microwave rectifying.

physics.app-ph↗

arXiv2025

Fast SAM2 with Text-Driven Token Pruning

Segment Anything Model 2 (SAM2), a vision foundation model has significantly advanced in prompt-driven video object segmentation, yet their practical deployment remains limited by the high computational and memory cost of processing dense visual tokens across time. The SAM2 pipelines typically propagate all visual tokens produced by the image encoder through downstream temporal reasoning modules, regardless of their relevance to the target object, resulting in reduced scalability due to quadratic memory attention overhead. In this work, we introduce a text-guided token pruning framework that improves inference efficiency by selectively reducing token density prior to temporal propagation, without modifying the underlying segmentation architecture. Operating after visual encoding and before memory based propagation, our method ranks tokens using a lightweight routing mechanism that integrates local visual context, semantic relevance derived from object-centric textual descriptions (either user-provided or automatically generated), and uncertainty cues that help preserve ambiguous or boundary critical regions. By retaining only the most informative tokens for downstream processing, the proposed approach reduces redundant computation while maintaining segmentation fidelity. Extensive experiments across multiple challenging video segmentation benchmarks demonstrate that post-encoder token pruning provides a practical and effective pathway to efficient, prompt-aware video segmentation, achieving up to 42.50 percent faster inference and 37.41 percent lower GPU memory usage compared to the unpruned baseline SAM2, while preserving competitive J and F performance. These results highlight the potential of early token selection to improve the scalability of transformer-based video segmentation systems for real-time and resource-constrained applications.

cs.CV↗

arXiv2025

From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration

Background: The House-Tree-Person (HTP) drawing test, introduced by John Buck in 1948, remains a widely used projective technique in clinical psychology. However, it has long faced challenges such as heterogeneous scoring standards, reliance on examiners subjective experience, and a lack of a unified quantitative coding system. Results: Quantitative experiments showed that the mean semantic similarity between Multimodal Large Language Model (MLLM) interpretations and human expert interpretations was approximately 0.75 (standard deviation about 0.05). In structurally oriented expert data sets, this similarity rose to 0.85, indicating expert-level baseline comprehension. Qualitative analyses demonstrated that the multi-agent system, by integrating social-psychological perspectives and destigmatizing narratives, effectively corrected visual hallucinations and produced psychological reports with high ecological validity and internal coherence. Conclusions: The findings confirm the potential of multimodal large models as standardized tools for projective assessment. The proposed multi-agent framework, by dividing roles, decouples feature recognition from psychological inference and offers a new paradigm for digital mental-health services. Keywords: House-Tree-Person test; multimodal large language model; multi-agent collaboration; cosine similarity; computational psychology; artificial intelligence

cs.AI↗

arXiv2025

Binary Event-Driven Spiking Transformer

Transformer-based Spiking Neural Networks (SNNs) introduce a novel event-driven self-attention paradigm that combines the high performance of Transformers with the energy efficiency of SNNs. However, the larger model size and increased computational demands of the Transformer structure limit their practicality in resource-constrained scenarios. In this paper, we integrate binarization techniques into Transformer-based SNNs and propose the Binary Event-Driven Spiking Transformer, i.e. BESTformer. The proposed BESTformer can significantly reduce storage and computational demands by representing weights and attention maps with a mere 1-bit. However, BESTformer suffers from a severe performance drop from its full-precision counterpart due to the limited representation capability of binarization. To address this issue, we propose a Coupled Information Enhancement (CIE) method, which consists of a reversible framework and information enhancement distillation. By maximizing the mutual information between the binary model and its full-precision counterpart, the CIE method effectively mitigates the performance degradation of the BESTformer. Extensive experiments on static and neuromorphic datasets demonstrate that our method achieves superior performance to other binary SNNs, showcasing its potential as a compact yet high-performance model for resource-limited edge devices. The repository of this paper is available at https://github.com/CaoHLin/BESTFormer.

cs.CV↗

arXiv2025

Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution

Chain-of-Thought (CoT) prompting enhances the reasoning of large language models (LLMs) by decomposing problems into sequential steps, mimicking human logic and reducing errors. However, complex tasks with vast solution spaces and vague constraints often exceed the capacity of a single reasoning chain. Inspired by Minimal Free Resolution (MFR) in commutative algebra and algebraic geometry, we propose Syzygy of Thoughts (SoT)-a novel framework that extends CoT by introducing auxiliary, interrelated reasoning paths. SoT captures deeper logical dependencies, enabling more robust and structured problem-solving. MFR decomposes a module into a sequence of free modules with minimal rank, providing a structured analytical approach to complex systems. This method introduces the concepts of "Module", "Betti numbers","Freeness", "Mapping", "Exactness" and "Minimality", enabling the systematic decomposition of the original complex problem into logically complete minimal subproblems while preserving key problem features and reducing reasoning length. We tested SoT across diverse datasets (e.g., GSM8K, MATH) and models (e.g., GPT-4o-mini, Qwen2.5), achieving inference accuracy that matches or surpasses mainstream CoTs standards. Additionally, by aligning the sampling process with algebraic constraints, our approach enhances the scalability of inference time in LLMs, ensuring both transparent reasoning and high performance. Our code will be publicly available at https://github.com/dlMARiA/Syzygy-of-thoughts.

cs.CL↗

arXiv2025

Asymptotically Optimal Aperiodic Doppler Resilient Complementary Sequence Sets Via Generalized Quasi-Florentine Rectangles

Doppler-resilient complementary sequence (DRCS) sets play a vital role in modern communication and sensing systems, particularly in high-mobility environments. This work makes two primary contributions. First, we refine the definition of quasi-Florentine rectangles to a more general form,termed generalized quasi-Florentine rectangles, and propose a systematic method for their construction. Second, we propose several sets of aperiodic DRCS based on generalized quasi Florentine rectangles and Butson-type Hadamard matrices. The proposed aperiodic DRCS sets are shown to be asymptotically optimal with respect to the lower bound of aperiodic DRCS sets.

cs.IT↗

arXiv2025

Zero-shot Hierarchical Plant Segmentation via Foundation Segmentation Models and Text-to-image Attention

Foundation segmentation models achieve reasonable leaf instance extraction from top-view crop images without training (i.e., zero-shot). However, segmenting entire plant individuals with each consisting of multiple overlapping leaves remains challenging. This problem is referred to as a hierarchical segmentation task, typically requiring annotated training datasets, which are often species-specific and require notable human labor. To address this, we introduce ZeroPlantSeg, a zero-shot segmentation for rosette-shaped plant individuals from top-view images. We integrate a foundation segmentation model, extracting leaf instances, and a vision-language model, reasoning about plants' structures to extract plant individuals without additional training. Evaluations on datasets with multiple plant species, growth stages, and shooting environments demonstrate that our method surpasses existing zero-shot methods and achieves better cross-domain performance than supervised methods. Implementations are available at https://github.com/JunhaoXing/ZeroPlantSeg.

cs.CV↗

arXiv2025

Interaction-via-Actions: Cattle Interaction Detection with Joint Learning of Action-Interaction Latent Space

This paper introduces a method and application for automatically detecting behavioral interactions between grazing cattle from a single image, which is essential for smart livestock management in the cattle industry, such as for detecting estrus. Although interaction detection for humans has been actively studied, a non-trivial challenge lies in cattle interaction detection, specifically the lack of a comprehensive behavioral dataset that includes interactions, as the interactions of grazing cattle are rare events. We, therefore, propose CattleAct, a data-efficient method for interaction detection by decomposing interactions into the combinations of actions by individual cattle. Specifically, we first learn an action latent space from a large-scale cattle action dataset. Then, we embed rare interactions via the fine-tuning of the pre-trained latent space using contrastive learning, thereby constructing a unified latent space of actions and interactions. On top of the proposed method, we develop a practical working system integrating video and GPS inputs. Experiments on a commercial-scale pasture demonstrate the accurate interaction detection achieved by our method compared to the baselines. Our implementation is available at https://github.com/rakawanegan/CattleAct.

cs.CV↗

arXiv2025

Toward expert-level motivational interviewing for health behavior improvement with LLMs

Background: Motivational interviewing (MI) is an effective counseling approach for promoting health behavior change, but its impact is constrained by the need for highly trained human counselors. Objective: This study aimed to explore a scalable alternative by developing and evaluating Large Language Models for Motivational Interviewing (MI-LLMs). Methods: We first curated five Chinese psychological counseling corpora and, using GPT-4 with an MI-informed prompt, transcribed multi-turn dialogues from the two highest-quality datasets (CPsyCounD and PsyDTCorpus) into 2,040 MI-style counseling conversations, of which 2,000 were used for training and 40 for testing. Three Chinese-capable open-source LLMs (Baichuan2-7B-Chat, ChatGLM-4-9B-Chat and Llama-3-8B-Chinese-Chat-v2) were fine-tuned on this corpus and were named as MI-LLMs. We evaluated MI-LLMs using round-based automatic metrics and expert manual coding with the Motivational Interviewing Treatment Integrity (MITI) Coding Manual 4.2.1. Results: Across all three models, fine-tuning substantially improved BLEU-4 and ROUGE scores compared with the base models, and manual coding showed that MI-LLMs achieved technical and relational global scores, and MI-adherent ratios that approached those of real MI dialogues, although complex reflections and reflection-to-question ratios remained less frequent. Conclusions: These findings provide initial evidence that MI-oriented fine-tuning can endow general-purpose LLMs with core MI-consistent counseling behaviors, suggesting a scalable pathway toward AI-assisted health behavior change support while underscoring the need for further work on data scale, complex MI skills and real-world intervention trials.

cs.CL↗

arXiv2025

Supervised Classification of LEO Debris Families Using Multi-Set Proper Elements

Machine learning techniques using proper elements to reconnect families of satellite fragmentation debris have recently advanced, becoming key to space sustainability and domain awareness. However, an evolving circumterrestrial environment may limit their applicability, particularly when models are trained on outdated debris representations. In this work, we devise a computational pipeline using synthetic fragmentation data from explosive breakup events, generated via a Standard Breakup Model and propagated under a high-fidelity dynamical model. Proper elements are extracted using adapted algorithms for modified equinoctial (MEE), Poincar'e (PNC), and quaternion (QTN) sets. Extending beyond previous approaches limited to MEE space, we include PNC and QTN sets to broaden the dynamical fingerprints available to the classifier. Neural networks trained on various element combinations are used to determine if fragment pairs share a parent. Crucially, we identify a fundamental limitation when applying standard quaternion sets to neural networks: the loss of orbital size information during feature normalization. We introduce an augmented representation (QTN$_p$) that explicitly restores the semi-latus rectum, improving accuracy from 0.31 to 0.60 compared to the standard set. In synthetic Starlink-like LEO experiments, expanding proper-element sets generally improves discrimination. The best model, using a joint feature set (MEE + PNC + QTN), achieves an ROC-AUC of 0.858 compared to 0.789 for the MEE-only baseline, alongside higher accuracy and F1 scores.

astro-ph.EP↗

arXiv2025

GaussianPlant: Structure-aligned Gaussian Splatting for 3D Reconstruction of Plants

We present a method for jointly recovering the appearance and internal structure of botanical plants from multi-view images based on 3D Gaussian Splatting (3DGS). While 3DGS exhibits robust reconstruction of scene appearance for novel-view synthesis, it lacks structural representations underlying those appearances (e.g., branching patterns of plants), which limits its applicability to tasks such as plant phenotyping. To achieve both high-fidelity appearance and structural reconstruction, we introduce GaussianPlant, a hierarchical 3DGS representation, which disentangles structure and appearance. Specifically, we employ structure primitives (StPs) to explicitly represent branch and leaf geometry, and appearance primitives (ApPs) to the plants' appearance using 3D Gaussians. StPs represent a simplified structure of the plant, i.e., modeling branches as cylinders and leaves as disks. To accurately distinguish the branches and leaves, StP's attributes (i.e., branches or leaves) are optimized in a self-organized manner. ApPs are bound to each StP to represent the appearance of branches or leaves as in conventional 3DGS. StPs and ApPs are jointly optimized using a re-rendering loss on the input multi-view images, as well as the gradient flow from ApP to StP using the binding correspondence information. We conduct experiments to qualitatively evaluate the reconstruction accuracy of both appearance and structure, as well as real-world experiments to qualitatively validate the practical performance. Experiments show that the GaussianPlant achieves both high-fidelity appearance reconstruction via ApPs and accurate structural reconstruction via StPs, enabling the extraction of branch structure and leaf instances.

cs.CV↗

arXiv2025

MeshRipple: Structured Autoregressive Generation of Artist-Meshes

Meshes serve as a primary representation for 3D assets. Autoregressive mesh generators serialize faces into sequences and train on truncated segments with sliding-window inference to cope with memory limits. However, this mismatch breaks long-range geometric dependencies, producing holes and fragmented components. To address this critical limitation, we introduce MeshRipple, which expands a mesh outward from an active generation frontier, akin to a ripple on a surface. MeshRipple rests on three key innovations: a frontier-aware BFS tokenization that aligns the generation order with surface topology; an expansive prediction strategy that maintains coherent, connected surface growth; and a sparse-attention global memory that provides an effectively unbounded receptive field to resolve long-range topological dependencies. This integrated design enables MeshRipple to generate meshes with high surface fidelity and topological completeness, outperforming strong recent baselines.

cs.CV↗

arXiv2025

Distilling Future Temporal Knowledge with Masked Feature Reconstruction for 3D Object Detection

Camera-based temporal 3D object detection has shown impressive results in autonomous driving, with offline models improving accuracy by using future frames. Knowledge distillation (KD) can be an appealing framework for transferring rich information from offline models to online models. However, existing KD methods overlook future frames, as they mainly focus on spatial feature distillation under strict frame alignment or on temporal relational distillation, thereby making it challenging for online models to effectively learn future knowledge. To this end, we propose a sparse query-based approach, Future Temporal Knowledge Distillation (FTKD), which effectively transfers future frame knowledge from an offline teacher model to an online student model. Specifically, we present a future-aware feature reconstruction strategy to encourage the student model to capture future features without strict frame alignment. In addition, we further introduce future-guided logit distillation to leverage the teacher's stable foreground and background context. FTKD is applied to two high-performing 3D object detection baselines, achieving up to 1.3 mAP and 1.3 NDS gains on the nuScenes dataset, as well as the most accurate velocity estimation, without increasing inference cost.

cs.CV↗