arXiv subjects

Yang Yang

Publications and source records attributed to Yang Yang.

At least 379 records · Page 21Linked to original sources

arXiv2025

Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks

Spiking Neural Networks (SNNs) demonstrate significant potential for energy-efficient neuromorphic computing through an event-driven paradigm. While training methods and computational models have greatly advanced, SNNs struggle to achieve competitive performance in visual long-sequence modeling tasks. In artificial neural networks, the effective receptive field (ERF) serves as a valuable tool for analyzing feature extraction capabilities in visual long-sequence modeling. Inspired by this, we introduce the Spatio-Temporal Effective Receptive Field (ST-ERF) to analyze the ERF distributions across various Transformer-based SNNs. Based on the proposed ST-ERF, we reveal that these models suffer from establishing a robust global ST-ERF, thereby limiting their visual feature modeling capabilities. To overcome this issue, we propose two novel channel-mixer architectures: \underline{m}ulti-\underline{l}ayer-\underline{p}erceptron-based m\underline{ixer} (MLPixer) and \underline{s}plash-and-\underline{r}econstruct \underline{b}lock (SRB). These architectures enhance global spatial ERF through all timesteps in early network stages of Transformer-based SNNs, improving performance on challenging visual long-sequence modeling tasks. Extensive experiments conducted on the Meta-SDT variants and across object detection and semantic segmentation tasks further validate the effectiveness of our proposed method. Beyond these specific applications, we believe the proposed ST-ERF framework can provide valuable insights for designing and optimizing SNN architectures across a broader range of tasks. The code is available at \href{https://github.com/EricZhang1412/Spatial-temporal-ERF}{\faGithub~EricZhang1412/Spatial-temporal-ERF}.

cs.NE↗

arXiv2025

Deep Learning-Powered Electrical Brain Signals Analysis: Advancing Neurological Diagnostics

Neurological disorders pose major global health challenges, driving advances in brain signal analysis. Scalp electroencephalography (EEG) and intracranial EEG (iEEG) are widely used for diagnosis and monitoring. However, dataset heterogeneity and task variations hinder the development of robust deep learning solutions. This review systematically examines recent advances in deep learning approaches for EEG/iEEG-based neurological diagnostics, focusing on applications across 7 neurological conditions using 46 datasets. For each condition, we review representative methods and their quantitative results, integrating performance comparisons with analyses of data usage, model design, and task-specific adaptations, while highlighting the role of pre-trained multi-task models in achieving scalable, generalizable solutions. Finally, we propose a standardized benchmark to evaluate models across diverse datasets and improve reproducibility, emphasizing how recent innovations are transforming neurological diagnostics toward intelligent, adaptable healthcare systems.

q-bio.NC↗

arXiv2025

Kinetics of Peierls dimerization transition: Machine learning force-field approach

We present a machine learning (ML) force-field framework for simulating the non-equilibrium dynamics of charge-density-wave (CDW) order driven by the Peierls instability. Since the Peierls distortion arises from the coupling between lattice displacements and itinerant electrons, evaluating the adiabatic forces during time evolution is computationally intensive, particularly for large systems. To overcome this bottleneck, we develop a generalized Behler-Parrinello neural-network architecture -- originally formulated for ab initio molecular dynamics -- to accurately and efficiently predict forces from local structural environments. Using the locality of electronic responses, the resulting ML force field achieves linear scaling efficiency while maintaining quantitative accuracy. Large-scale dynamical simulations using this framework uncover a two-stage coarsening behavior of CDW domains: an early-time regime characterized by a power-law growth $L \sim t^α$ with an effective exponent $α\approx 0.7$, followed by a crossover to the Allen-Cahn scaling $L \sim \sqrt{t}$ at late times. The enhanced early-time coarsening is attributed to anisotropic domain-wall motion arising from electron-mediated directional interactions. This work demonstrates the promise of ML-based force fields for multiscale dynamical modeling of condensed-matter lattice models.

cond-mat.stat-mech↗

arXiv2025

BrainCognizer: Brain Decoding with Human Visual Cognition Simulation for fMRI-to-Image Reconstruction

Brain decoding is a key neuroscience field that reconstructs the visual stimuli from brain activity with fMRI, which helps illuminate how the brain represents the world. fMRI-to-image reconstruction has achieved impressive progress by leveraging diffusion models. However, brain signals infused with prior knowledge and associations exhibit a significant information asymmetry when compared to raw visual features, still posing challenges for decoding fMRI representations under the supervision of images. Consequently, the reconstructed images often lack fine-grained visual fidelity, such as missing attributes and distorted spatial relationships. To tackle this challenge, we propose BrainCognizer, a novel brain decoding model inspired by human visual cognition, which explores multi-level semantics and correlations without fine-tuning of generative models. Specifically, BrainCognizer introduces two modules: the Cognitive Integration Module which incorporates prior human knowledge to extract hierarchical region semantics; and the Cognitive Correlation Module which captures contextual semantic relationships across regions. Incorporating these two modules enhances intra-region semantic consistency and maintains inter-region contextual associations, thereby facilitating fine-grained brain decoding. Moreover, we quantitatively interpret our components from a neuroscience perspective and analyze the associations between different visual patterns and brain functions. Extensive quantitative and qualitative experiments demonstrate that BrainCognizer outperforms state-of-the-art approaches on multiple evaluation metrics.

q-bio.NC↗

arXiv2025

STARK: Strategic Team of Agents for Refining Kernels

The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, thread scheduling, and hardware-specific characteristics. While recent advances in large language models (LLMs) provide new opportunities for automated code generation, existing approaches largely treat LLMs as single-shot generators or naive refinement tools, limiting their effectiveness in navigating the irregular kernel optimization landscape. We introduce an LLM agentic framework for GPU kernel optimization that systematically explores the design space through multi-agent collaboration, grounded instruction, dynamic context management, and strategic search. This framework mimics the workflow of expert engineers, enabling LLMs to reason about hardware trade-offs, incorporate profiling feedback, and refine kernels iteratively. We evaluate our approach on KernelBench, a benchmark for LLM-based kernel optimization, and demonstrate substantial improvements over baseline agents: our system produces correct solutions where baselines often fail, and achieves kernels with up to 16x faster runtime performance. These results highlight the potential of agentic LLM frameworks to advance fully automated, scalable GPU kernel optimization.

cs.AI↗

arXiv2025

CO in MASsive Spirals (CO-MASS): an IRAM 30m CO emission line survey of the CGM-MASS sample

There exist extremely massive spiral galaxies in isolated environments, with stellar masses several times that of the Milky Way, yet their star formation rates (SFRs) are comparable to or even lower than that of the Milky Way. In this paper, we investigate the molecular gas properties of such galaxies to better understand the origin of their low SFRs. We present IRAM 30m CO observations of five extremely massive spirals from the CGM-MASS sample. We compare their star formation efficiencies (SFEs) with the Kennicutt-Schmidt relation and find that these massive spirals generally exhibit low efficiency in converting molecular gas into stars. We further compare their molecular gas masses with their atomic gas and stellar masses, and also include the CHANG-ES sample galaxies observed with the IRAM 30m telescope in a similar manner for comparison. Our sample galaxies show low efficiency in converting atomic to molecular gas and have lower molecular gas fractions, suggesting that their suppressed star formation stems from both limited gas supply and inefficient star formation. Considering potential cold gas sources in massive spirals, we argue that their current reservoirs likely originate from past starburst or merger events rather than ongoing accretion in present isolated environments. Finally, we examine the location of these galaxies on the baryonic Tully-Fisher relation, finding them baryon-deficient and deviating from the trend of lower-mass galaxies. This suggests either a significant undetected baryonic component or a flattening/turnover of the relation at the high-mass end, consistent with the stellar mass-halo mass relation.

astro-ph.GA↗

arXiv2025

Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks

Early tumor detection save lives. Each year, more than 300 million computed tomography (CT) scans are performed worldwide, offering a vast opportunity for effective cancer screening. However, detecting small or early-stage tumors on these CT scans remains challenging, even for experts. Artificial intelligence (AI) models can assist by highlighting suspicious regions, but training such models typically requires extensive tumor masks--detailed, voxel-wise outlines of tumors manually drawn by radiologists. Drawing these masks is costly, requiring years of effort and millions of dollars. In contrast, nearly every CT scan in clinical practice is already accompanied by medical reports describing the tumor's size, number, appearance, and sometimes, pathology results--information that is rich, abundant, and often underutilized for AI training. We introduce R-Super, which trains AI to segment tumors that match their descriptions in medical reports. This approach scales AI training with large collections of readily available medical reports, substantially reducing the need for manually drawn tumor masks. When trained on 101,654 reports, AI models achieved performance comparable to those trained on 723 masks. Combining reports and masks further improved sensitivity by +13% and specificity by +8%, surpassing radiologists in detecting five of the seven tumor types. Notably, R-Super enabled segmentation of tumors in the spleen, gallbladder, prostate, bladder, uterus, and esophagus, for which no public masks or AI models previously existed. This study challenges the long-held belief that large-scale, labor-intensive tumor mask creation is indispensable, establishing a scalable and accessible path toward early detection across diverse tumor types. We plan to release our trained models, code, and dataset at https://github.com/MrGiovanni/R-Super

cs.CV↗

arXiv2025

Colossal Cryogenic Electro-Optic Response Through Metastability in Strained BaTiO$_{3}$ Thin Films

The search for thin film electro-optic (EO) materials that can retain superior performance under cryogenic conditions has become critical for quantum computing. Barium titanate thin films show large linear EO coefficients in the tetragonal phase at room temperature, which is severely degraded down to ~200 pm V$^{-1}$ in the rhombohedral phase at cryogenic temperatures. There is immense interest in manipulating these phase transformations and retaining superior EO properties down to liquid helium temperature. Utilizing the thermodynamic theory of optical properties, a large low-temperature EO response is designed by engineering the energetic competition between different ferroelectric phases, leading to a low-symmetry monoclinic phase with a massive EO response. The existence of this phase is demonstrated in a strain-tuned BaTiO$_{3}$ thin film that exhibits a linear EO coefficient of 2516 +/- 100 pm V$^{-1}$ at 5 K, which is an order of magnitude higher than the best reported performance thus far. Importantly, the EO coefficient increases by 100x during cooling, unlike the conventional films, where it degrades. Further, at the lowest temperature, significant higher order EO responses also emerge. These results represent a new framework for designing materials with property enhancements by stabilizing highly tunable metastable phases with strain. Copyright 2025 The Author(s). Advanced Materials published by Wiley-VCH GmbH. This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited. (A. Suceava, S. Hazra, A. Ross, et al. "Colossal Cryogenic Electro-Optic Response Through Metastability in Strained BaTiO3 Thin Films." Adv. Mater. (2025): e07564. https://doi.org/10.1002/adma.202507564)

cond-mat.mtrl-sci↗

arXiv2025

LSVOS 2025 Challenge Report: Recent Advances in Complex Video Object Segmentation

This report presents an overview of the 7th Large-scale Video Object Segmentation (LSVOS) Challenge held in conjunction with ICCV 2025. Besides the two traditional tracks of LSVOS that jointly target robustness in realistic video scenarios: Classic VOS (VOS), and Referring VOS (RVOS), the 2025 edition features a newly introduced track, Complex VOS (MOSEv2). Building upon prior insights, MOSEv2 substantially increases difficulty, introducing more challenging but realistic scenarios including denser small objects, frequent disappear/reappear events, severe occlusions, adverse weather and lighting, etc., pushing long-term consistency and generalization beyond curated benchmarks. The challenge retains standard ${J}$, $F$, and ${J\&F}$ metrics for VOS and RVOS, while MOSEv2 adopts ${J\&\dot{F}}$ as the primary ranking metric to better evaluate objects across scales and disappearance cases. We summarize datasets and protocols, highlight top-performing solutions, and distill emerging trends, such as the growing role of LLM/MLLM components and memory-aware propagation, aiming to chart future directions for resilient, language-aware video segmentation in the wild.

cs.CV↗

arXiv2025

LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings

Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to enhance attack performance. However, it is unable to generate human-readable explanations, and exhibits poor generalizability. In the past few years, large language models (LLMs) have demonstrated powerful capabilities in text comprehension, generation, and reasoning. In this paper, we propose LLMAtKGE, a novel LLM-based framework that selects attack targets and generates human-readable explanations. To provide the LLM with sufficient factual context under limited input constraints, we design a structured prompting scheme that explicitly formulates the attack as multiple-choice questions while incorporating KG factual evidence. To address the context-window limitation and hesitation issues, we introduce semantics-based and centrality-based filters, which compress the candidate set while preserving high recall of attack-relevant information. Furthermore, to efficiently integrate both semantic and structural information into the filter, we precompute high-order adjacency and fine-tune the LLM with a triple classification task to enhance filtering performance. Experiments on two widely used knowledge graph datasets demonstrate that our attack outperforms the strongest black-box baselines and provides explanations via reasoning, and showing competitive performance compared with white-box methods. Comprehensive ablation and case studies further validate its capability to generate explanations.

cs.CL↗

arXiv2025

Any-to-Bokeh: Arbitrary-Subject Video Refocusing with Video Diffusion Model

Diffusion models have recently emerged as powerful tools for camera simulation, enabling both geometric transformations and realistic optical effects. Among these, image-based bokeh rendering has shown promising results, but diffusion for video bokeh remains unexplored. Existing image-based methods are plagued by temporal flickering and inconsistent blur transitions, while current video editing methods lack explicit control over the focus plane and bokeh intensity. These issues limit their applicability for controllable video bokeh. In this work, we propose a one-step diffusion framework for generating temporally coherent, depth-aware video bokeh rendering. The framework employs a multi-plane image (MPI) representation adapted to the focal plane to condition the video diffusion model, thereby enabling it to exploit strong 3D priors from pretrained backbones. To further enhance temporal stability, depth robustness, and detail preservation, we introduce a progressive training strategy. Experiments on synthetic and real-world benchmarks demonstrate superior temporal coherence, spatial accuracy, and controllability, outperforming prior baselines. This work represents the first dedicated diffusion framework for video bokeh generation, establishing a new baseline for temporally coherent and controllable depth-of-field effects.

cs.CV↗

arXiv2025

More Than One Teacher: Adaptive Multi-Guidance Policy Optimization for Diverse Exploration

Reinforcement Learning with Verifiable Rewards (RLVR) is a promising paradigm for enhancing the reasoning ability in Large Language Models (LLMs). However, prevailing methods primarily rely on self-exploration or a single off-policy teacher to elicit long chain-of-thought (LongCoT) reasoning, which may introduce intrinsic model biases and restrict exploration, ultimately limiting reasoning diversity and performance. Drawing inspiration from multi-teacher strategies in knowledge distillation, we introduce Adaptive Multi-Guidance Policy Optimization (AMPO), a novel framework that adaptively leverages guidance from multiple proficient teacher models, but only when the on-policy model fails to generate correct solutions. This "guidance-on-demand" approach expands exploration while preserving the value of self-discovery. Moreover, AMPO incorporates a comprehension-based selection mechanism, prompting the student to learn from the reasoning paths that it is most likely to comprehend, thus balancing broad exploration with effective exploitation. Extensive experiments show AMPO substantially outperforms a strong baseline (GRPO), with a 4.3% improvement on mathematical reasoning tasks and 12.2% on out-of-distribution tasks, while significantly boosting Pass@k performance and enabling more diverse exploration. Notably, using four peer-sized teachers, our method achieves comparable results to approaches that leverage a single, more powerful teacher (e.g., DeepSeek-R1) with more data. These results demonstrate a more efficient and scalable path to superior reasoning and generalizability. Our code is available at https://github.com/SII-Enigma/AMPO.

cs.CL↗

arXiv2025

Gradient of White Matter Functional Variability via fALFF Differential Identifiability

Functional variability in both gray matter (GM) and white matter (WM) is closely associated with human brain cognitive and developmental processes, and is commonly assessed using functional connectivity (FC). However, as a correlation-based approach, FC captures the co-fluctuation between brain regions rather than the intensity of neural activity in each region. Consequently, FC provides only a partial view of functional variability, and this limitation is particularly pronounced in WM, where functional signals are weaker and more susceptible to noise. To tackle this limitation, we introduce fractional amplitude of low-frequency fluctuation (fALFF) to measure the intensity of spontaneous neural activity and analyze functional variability in WM. Specifically, we propose a novel method to quantify WM functional variability by estimating the differential identifiability of fALFF. Higher differential identifiability is observed in WM fALFF compared to FC, which indicates that fALFF is more sensitive to WM functional variability. Through fALFF differential identifiability, we evaluate the functional variabilities of both WM and GM, and find the overall functional variability pattern is similar although WM shows slightly lower variability than GM. The regional functional variabilities of WM are associated with structural connectivity, where commissural fiber regions generally exhibit higher variability than projection fiber regions. Furthermore, we discover that WM functional variability demonstrates a spatial gradient ascending from the brainstem to the cortex by hypothesis testing, which aligns well with the evolutionary expansion. The gradient of functional variability in WM provides novel insights for understanding WM function. To the best of our knowledge, this is the first attempt to investigate WM functional variability via fALFF.

q-bio.NC↗

arXiv2025

Noise or Signal? Deconstructing Contradictions and An Adaptive Remedy for Reversible Normalization in Time Series Forecasting

Reversible Instance Normalization (RevIN) is a key technique enabling simple linear models to achieve state-of-the-art performance in time series forecasting. While replacing its non-robust statistics with robust counterparts (termed R$^2$-IN) seems like a straightforward improvement, our findings reveal a far more complex reality. This paper deconstructs the perplexing performance of various normalization strategies by identifying four underlying theoretical contradictions. Our experiments provide two crucial findings: first, the standard RevIN catastrophically fails on datasets with extreme outliers, where its MSE surges by a staggering 683\%. Second, while the simple R$^2$-IN prevents this failure and unexpectedly emerges as the best overall performer, our adaptive model (A-IN), designed to test a diagnostics-driven heuristic, unexpectedly suffers a complete and systemic failure. This surprising outcome uncovers a critical, overlooked pitfall in time series analysis: the instability introduced by a simple or counter-intuitive heuristic can be more damaging than the statistical issues it aims to solve. The core contribution of this work is thus a new, cautionary paradigm for time series normalization: a shift from a blind search for complexity to a diagnostics-driven analysis that reveals not only the surprising power of simple baselines but also the perilous nature of naive adaptation.

cs.LG↗

arXiv2025

Fingerprinting Organic Molecules for the Inverse Design of Two-Dimensional Hybrid Perovskites with Target Energetics

Artificial intelligence (AI)-assisted workflows have transformed materials discovery, enabling rapid exploration of chemical spaces of functional materials. Endowed with extraordinary optoelectronic properties, two-dimensional (2D) hybrid perovskites represent an exciting frontier, but current efforts to design 2D perovskites rely heavily on trial-and-error and expert intuition approaches, leaving most of the chemical space unexplored and compromising the design of hybrid materials with desired properties. Here, we introduce an inverse design workflow for Dion-Jacobson perovskites that is built on an invertible fingerprint representation for millions of conjugated diammonium organic spacers. By incorporating high-throughput density functional theory (DFT) calculations, interpretable machine learning, and synthesis feasibility screening, we identified new organic spacer candidates with deterministic energy level alignment between the organic and the inorganic motifs in the 2D hybrid perovskites. These results highlight the power of integrating invertible, physically meaningful molecular representations into AI-assisted design, streamlining the property-targeted design of hybrid materials.

cond-mat.mtrl-sci↗

arXiv2025

The 1st Solution for MOSEv1 Challenge on LSVOS 2025: CGFSeg

Video Object Segmentation (VOS) aims to track and segment specific objects across entire video sequences, yet it remains highly challenging under complex real-world scenarios. The MOSEv1 and LVOS dataset, adopted in the MOSEv1 challenge on LSVOS 2025, which is specifically designed to enhance the robustness of VOS models in complex real-world scenarios, including long-term object disappearances and reappearances, as well as the presence of small and inconspicuous objects. In this paper, we present our improved method, Confidence-Guided Fusion Segmentation (CGFSeg), for the VOS task in the MOSEv1 Challenge. During training, the feature extractor of SAM2 is frozen, while the remaining components are fine-tuned to preserve strong feature extraction ability and improve segmentation accuracy. In the inference stage, we introduce a pixel-check strategy that progressively refines predictions by exploiting complementary strengths of multiple models, thereby yielding robust final masks. As a result, our method achieves a J&F score of 86.37% on the test set, ranking 1st in the MOSEv1 Challenge at LSVOS 2025. These results highlight the effectiveness of our approach in addressing the challenges of VOS task in complex scenarios.

cs.CV↗

arXiv2025

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

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

cs.LG↗

arXiv2025

Dual-Head Reasoning Distillation: Improving Classifier Accuracy with Train-Time-Only Reasoning

Chain-of-Thought (CoT) prompting often improves classification accuracy, but it introduces a significant throughput penalty with rationale generation (Wei et al., 2022; Cheng and Van Durme, 2024). To resolve this trade-off, we introduce Dual-Head Reasoning Distillation (DHRD), a simple training method for decoder-only language models (LMs) that adds (i) a pooled classification head used during training and inference and (ii) a reasoning head supervised by teacher rationales used only in training. We train with a loss function that is a weighted sum of label cross-entropy and token-level LM loss over input-plus-rationale sequences. On seven SuperGLUE tasks, DHRD yields relative gains of 0.65-5.47% over pooled baselines, with notably larger gains on entailment/causal tasks. Since we disable the reasoning head at test time, inference throughput matches pooled classifiers and exceeds CoT decoding on the same backbones by 96-142 times in QPS.

cs.CL↗