PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2504.00494공식 코드 · Papers with Code

Flow Matching on Lie Groups

Flow Matching (FM) is a recent generative modelling technique: we aim to learn how to sample from distribution $\mathfrak{X}_1$ by flowing samples from some distribution $\mathfrak{X}_0$ that is easy to sample from. The key trick is that this flow field can be trained while conditioning on the end point in $\mathfrak{X}_1$: given an end point, simply move along a straight line segment to the end point (Lipman et al. 2022). However, straight line segments are only well-defined on Euclidean space. Consequently, Chen and Lipman (2023) generalised the method to FM on Riemannian manifolds, replacing line segments with geodesics or their spectral approximations. We take an alternative point of view: we generalise to FM on Lie groups by instead substituting exponential curves for line segments. This leads to a simple, intrinsic, and fast implementation for many matrix Lie groups, since the required Lie group operations (products, inverses, exponentials, logarithms) are simply given by the corresponding matrix operations. FM on Lie groups could then be used for generative modelling with data consisting of sets of features (in $\mathbb{R}^n$) and poses (in some Lie group), e.g. the latent codes of Equivariant Neural Fields (Wessels et al. 2025).

arXiv:2504.00316공식 코드 · Papers with Code

Effect-driven interpretation: Functors for natural language composition

Computer programs are often factored into pure components -- simple, total functions from inputs to outputs -- and components that may have side effects -- errors, changes to memory, parallel threads, abortion of the current loop, etc. We make the case that human languages are similarly organized around the give and pull of pure values and impure processes, and we'll aim to show how denotational techniques from computer science can be leveraged to support elegant and illuminating analyses of natural language composition.

arXiv:2504.00993공식 코드 · Papers with Code

MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs

Medical tasks such as diagnosis and treatment planning require precise and complex reasoning, particularly in life-critical domains. Unlike mathematical reasoning, medical reasoning demands meticulous, verifiable thought processes to ensure reliability and accuracy. However, there is a notable lack of datasets that provide transparent, step-by-step reasoning to validate and enhance the medical reasoning ability of AI models. To bridge this gap, we introduce MedReason, a large-scale high-quality medical reasoning dataset designed to enable faithful and explainable medical problem-solving in large language models (LLMs). We utilize a structured medical knowledge graph (KG) to convert clinical QA pairs into logical chains of reasoning, or ``thinking paths'', which trace connections from question elements to answers via relevant KG entities. Each path is validated for consistency with clinical logic and evidence-based medicine. Our pipeline generates detailed reasoning for various medical questions from 7 medical datasets, resulting in a dataset of 32,682 question-answer pairs, each with detailed, step-by-step explanations. Experiments demonstrate that fine-tuning with our dataset consistently boosts medical problem-solving capabilities, achieving significant gains of up to 7.7% for DeepSeek-Ditill-8B. Our top-performing model, MedReason-8B, outperforms the Huatuo-o1-8B, a state-of-the-art medical reasoning model, by up to 4.2% on the clinical benchmark MedBullets. We also engage medical professionals from diverse specialties to assess our dataset's quality, ensuring MedReason offers accurate and coherent medical reasoning. Our data, models, and code will be publicly available.

arXiv:2504.00676공식 코드 · Papers with Code

GLiNER-BioMed: A Suite of Efficient Models for Open Biomedical Named Entity Recognition

Biomedical named entity recognition (NER) presents unique challenges due to specialized vocabularies, the sheer volume of entities, and the continuous emergence of novel entities. Traditional NER models, constrained by fixed taxonomies and human annotations, struggle to generalize beyond predefined entity types. To address these issues, we introduce GLiNER-BioMed, a domain-adapted suite of Generalist and Lightweight Model for NER (GLiNER) models specifically tailored for biomedicine. In contrast to conventional approaches, GLiNER uses natural language labels to infer arbitrary entity types, enabling zero-shot recognition. Our approach first distills the annotation capabilities of large language models (LLMs) into a smaller, more efficient model, enabling the generation of high-coverage synthetic biomedical NER data. We subsequently train two GLiNER architectures, uni- and bi-encoder, at multiple scales to balance computational efficiency and recognition performance. Experiments on several biomedical datasets demonstrate that GLiNER-BioMed outperforms the state-of-the-art in both zero- and few-shot scenarios, achieving 5.96% improvement in F1-score over the strongest baseline (p-value < 0.001). Ablation studies highlight the effectiveness of our synthetic data generation strategy and emphasize the complementary benefits of synthetic biomedical pre-training combined with fine-tuning on general-domain annotations. All datasets, models, and training pipelines are publicly available at https://github.com/ds4dh/GLiNER-biomed.

arXiv:2504.00478공식 코드 · Papers with Code

FSSUWNet: Mitigating the Fragility of Pre-trained Models with Feature Enhancement for Few-Shot Semantic Segmentation in Underwater Images

Few-Shot Semantic Segmentation (FSS), which focuses on segmenting new classes in images using only a limited number of annotated examples, has recently progressed in data-scarce domains. However, in this work, we show that the existing FSS methods often struggle to generalize to underwater environments. Specifically, the prior features extracted by pre-trained models used as feature extractors are fragile due to the unique challenges of underwater images. To address this, we propose FSSUWNet, a tailored FSS framework for underwater images with feature enhancement. FSSUWNet exploits the integration of complementary features, emphasizing both low-level and high-level image characteristics. In addition to employing a pre-trained model as the primary encoder, we propose an auxiliary encoder called Feature Enhanced Encoder which extracts complementary features to better adapt to underwater scene characteristics. Furthermore, a simple and effective Feature Alignment Module aims to provide global prior knowledge and align low-level features with high-level features in dimensions. Given the scarcity of underwater images, we introduce a cross-validation dataset version based on the Segmentation of Underwater Imagery dataset. Extensive experiments on public underwater segmentation datasets demonstrate that our approach achieves state-of-the-art performance. For example, our method outperforms the previous best method by 2.8% and 2.6% in terms of the mean Intersection over Union metric for 1-shot and 5-shot scenarios in the datasets, respectively. Our implementation is available at https://github.com/lizhh268/FSSUWNet.

arXiv:2504.00142공식 코드 · Papers with Code

LGIN: Defining an Approximately Powerful Hyperbolic GNN

While graph neural networks (GNNs) operating in hyperbolic spaces have shown promise for modeling hierarchical and complex relational data, a critical limitation often overlooked is their potentially limited discriminative power compared to their Euclidean counterparts or fundamental graph isomorphism tests like the Weisfeiler-Lehman (WL) hierarchy. Existing hyperbolic aggregation schemes, while curvature-aware, may not sufficiently capture the intricate structural differences required to robustly distinguish non-isomorphic graphs owing to non-injective aggregation functions. To address this expressiveness gap in hyperbolic graph learning, we introduce the Lorentzian Graph Isomorphic Network (LGIN), a novel GNN designed to achieve enhanced discriminative capabilities within the Lorentzian model of hyperbolic space. LGIN proposes a new update rule that effectively combines local neighborhood information with a richer representation of graph structure designed to preserve the Lorentzian metric tensor. This represents a significant step towards building more expressive GNNs in non-Euclidean geometries, overcoming a common bottleneck in current hyperbolic methods. We conduct extensive evaluations across nine diverse benchmark datasets, including molecular and protein structures. LGIN consistently outperforms or matches state-of-the-art hyperbolic and Euclidean GNNs, showcasing its practical efficacy and validating its superior ability to capture complex graph structures and distinguish between different graphs. To the best of our knowledge, LGIN is the first work to study the framework behind a powerful GNN on the hyperbolic space. The code for our paper can be found at https://github.com/Deceptrax123/LGIN

arXiv:2504.00019공식 코드 · Papers with Code

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding

Language models (LMs) have become a staple of the code-writing toolbox. Their pre-training recipe has, however, remained stagnant over recent years, barring the occasional changes in data sourcing and filtering strategies. In particular, research exploring modifications to Code-LMs' pre-training objectives, geared towards improving data efficiency and better disentangling between syntax and semantics, has been noticeably sparse, especially compared with corresponding efforts in natural language LMs. In this work, we examine grounding on obfuscated code as a means of helping Code-LMs look beyond the surface-form syntax and enhance their pre-training sample efficiency. To this end, we compile ObscuraX, a dataset of approximately 55M source and obfuscated code pairs in seven languages. Subsequently, we pre-train ObscuraCoder models, ranging in size from 255M to 2.8B parameters, on a 272B-token corpus that includes ObscuraX and demonstrate that our obfuscation-based pre-training recipe leads to consistent improvements in Code-LMs' abilities compared to both vanilla autoregressive pre-training as well as existing de-obfuscation (DOBF) objectives. ObscuraCoder demonstrates sizeable gains across multiple tests of syntactic and semantic code understanding, along with improved capabilities in multilingual code completion, multilingual code commit summarization, and multi-purpose library-oriented code generation.

arXiv:2503.23545공식 코드 · Papers with Code

Modelling the impact of phenotypic heterogeneity on cell migration: a continuum framework derived from individual-based principles

Collective cell migration plays a crucial role in numerous biological processes, including tumour growth, wound healing, and the immune response. Often, the migrating population consists of cells with various different phenotypes. This study derives a general mathematical framework for modelling cell migration in the local environment, which is coarse-grained from an underlying individual-based model that captures the dynamics of cell migration that are influenced by the phenotype of the cell, such as random movement, proliferation, phenotypic transitions, and interactions with the local environment. The resulting, flexible, and general model provides a continuum, macroscopic description of cell invasion, which represents the phenotype of the cell as a continuous variable and is much more amenable to simulation and analysis than its individual-based counterpart when considering a large number of phenotypes. We showcase the utility of the generalised framework in three biological scenarios: range expansion; cell invasion into the extracellular matrix; and T cell exhaustion. The results highlight how phenotypic structuring impacts the spatial and temporal dynamics of cell populations, demonstrating that different environmental pressures and phenotypic transition mechanisms significantly influence migration patterns, a phenomenon that would be computationally very expensive to explore using an individual-based model alone. This framework provides a versatile and robust tool for understanding the role of phenotypic heterogeneity in collective cell migration, with potential applications in optimising therapeutic strategies for diseases involving cell migration.

arXiv:2503.23452공식 코드 · Papers with Code

VideoGen-Eval: Agent-based System for Video Generation Evaluation

The rapid advancement of video generation has rendered existing evaluation systems inadequate for assessing state-of-the-art models, primarily due to simple prompts that cannot showcase the model's capabilities, fixed evaluation operators struggling with Out-of-Distribution (OOD) cases, and misalignment between computed metrics and human preferences. To bridge the gap, we propose VideoGen-Eval, an agent evaluation system that integrates LLM-based content structuring, MLLM-based content judgment, and patch tools designed for temporal-dense dimensions, to achieve a dynamic, flexible, and expandable video generation evaluation. Additionally, we introduce a video generation benchmark to evaluate existing cutting-edge models and verify the effectiveness of our evaluation system. It comprises 700 structured, content-rich prompts (both T2V and I2V) and over 12,000 videos generated by 20+ models, among them, 8 cutting-edge models are selected as quantitative evaluation for the agent and human. Extensive experiments validate that our proposed agent-based evaluation system demonstrates strong alignment with human preferences and reliably completes the evaluation, as well as the diversity and richness of the benchmark.

arXiv:2503.23451공식 코드 · Papers with Code

Beyond Academic Benchmarks: Critical Analysis and Best Practices for Visual Industrial Anomaly Detection

Anomaly detection (AD) is essential for automating visual inspection in manufacturing. This field of computer vision is rapidly evolving, with increasing attention towards real-world applications. Meanwhile, popular datasets are typically produced in controlled lab environments with artificially created defects, unable to capture the diversity of real production conditions. New methods often fail in production settings, showing significant performance degradation or requiring impractical computational resources. This disconnect between academic results and industrial viability threatens to misdirect visual anomaly detection research. This paper makes three key contributions: (1) we demonstrate the importance of real-world datasets and establish benchmarks using actual production data, (2) we provide a fair comparison of existing SOTA methods across diverse tasks by utilizing metrics that are valuable for practical applications, and (3) we present a comprehensive analysis of recent advancements in this field by discussing important challenges and new perspectives for bridging the academia-industry gap. The code is publicly available at https://github.com/abc-125/viad-benchmark

arXiv:2503.23422공식 코드 · Papers with Code

Improving underwater semantic segmentation with underwater image quality attention and muti-scale aggregation attention

Underwater image understanding is crucial for both submarine navigation and seabed exploration. However, the low illumination in underwater environments degrades the imaging quality, which in turn seriously deteriorates the performance of underwater semantic segmentation, particularly for outlining the object region boundaries. To tackle this issue, we present UnderWater SegFormer (UWSegFormer), a transformer-based framework for semantic segmentation of low-quality underwater images. Firstly, we propose the Underwater Image Quality Attention (UIQA) module. This module enhances the representation of highquality semantic information in underwater image feature channels through a channel self-attention mechanism. In order to address the issue of loss of imaging details due to the underwater environment, the Multi-scale Aggregation Attention(MAA) module is proposed. This module aggregates sets of semantic features at different scales by extracting discriminative information from high-level features,thus compensating for the semantic loss of detail in underwater objects. Finally, during training, we introduce Edge Learning Loss (ELL) in order to enhance the model's learning of underwater object edges and improve the model's prediction accuracy. Experiments conducted on the SUIM and DUT-USEG (DUT) datasets have demonstrated that the proposed method has advantages in terms of segmentation completeness, boundary clarity, and subjective perceptual details when compared to SOTA methods. In addition, the proposed method achieves the highest mIoU of 82.12 and 71.41 on the SUIM and DUT datasets, respectively. Code will be available at https://github.com/SAWRJJ/UWSegFormer.

arXiv:2503.23367공식 코드 · Papers with Code

FastVAR: Linear Visual Autoregressive Modeling via Cached Token Pruning

Visual Autoregressive (VAR) modeling has gained popularity for its shift towards next-scale prediction. However, existing VAR paradigms process the entire token map at each scale step, leading to the complexity and runtime scaling dramatically with image resolution. To address this challenge, we propose FastVAR, a post-training acceleration method for efficient resolution scaling with VARs. Our key finding is that the majority of latency arises from the large-scale step where most tokens have already converged. Leveraging this observation, we develop the cached token pruning strategy that only forwards pivotal tokens for scale-specific modeling while using cached tokens from previous scale steps to restore the pruned slots. This significantly reduces the number of forwarded tokens and improves the efficiency at larger resolutions. Experiments show the proposed FastVAR can further speedup FlashAttention-accelerated VAR by 2.7$\times$ with negligible performance drop of <1%. We further extend FastVAR to zero-shot generation of higher resolution images. In particular, FastVAR can generate one 2K image with 15GB memory footprints in 1.5s on a single NVIDIA 3090 GPU. Code is available at https://github.com/csguoh/FastVAR.

arXiv:2503.23344공식 코드 · Papers with Code

From Panels to Prose: Generating Literary Narratives from Comics

Comics have long been a popular form of storytelling, offering visually engaging narratives that captivate audiences worldwide. However, the visual nature of comics presents a significant barrier for visually impaired readers, limiting their access to these engaging stories. In this work, we provide a pragmatic solution to this accessibility challenge by developing an automated system that generates text-based literary narratives from manga comics. Our approach aims to create an evocative and immersive prose that not only conveys the original narrative but also captures the depth and complexity of characters, their interactions, and the vivid settings in which they reside. To this end we make the following contributions: (1) We present a unified model, Magiv3, that excels at various functional tasks pertaining to comic understanding, such as localising panels, characters, texts, and speech-bubble tails, performing OCR, grounding characters etc. (2) We release human-annotated captions for over 3300 Japanese comic panels, along with character grounding annotations, and benchmark large vision-language models in their ability to understand comic images. (3) Finally, we demonstrate how integrating large vision-language models with Magiv3, can generate seamless literary narratives that allows visually impaired audiences to engage with the depth and richness of comic storytelling.

arXiv:2503.23330공식 코드 · Papers with Code

EagleVision: Object-level Attribute Multimodal LLM for Remote Sensing

Recent advances in multimodal large language models (MLLMs) have demonstrated impressive results in various visual tasks. However, in remote sensing (RS), high resolution and small proportion of objects pose challenges to existing MLLMs, which struggle with object-centric tasks, particularly in precise localization and fine-grained attribute description for each object. These RS MLLMs have not yet surpassed classical visual perception models, as they only provide coarse image understanding, leading to limited gains in real-world scenarios. To address this gap, we establish EagleVision, an MLLM tailored for remote sensing that excels in object detection and attribute comprehension. Equipped with the Attribute Disentangle module, EagleVision learns disentanglement vision tokens to express distinct attributes. To support object-level visual-language alignment, we construct EVAttrs-95K, the first large-scale object attribute understanding dataset in RS for instruction tuning, along with a novel evaluation benchmark, EVBench. EagleVision achieves state-of-the-art performance on both fine-grained object detection and object attribute understanding tasks, highlighting the mutual promotion between detection and understanding capabilities in MLLMs. The code, model, data, and demo will be available at https://github.com/XiangTodayEatsWhat/EagleVision.

arXiv:2503.23283공식 코드 · Papers with Code

Language Guided Concept Bottleneck Models for Interpretable Continual Learning

Continual learning (CL) aims to enable learning systems to acquire new knowledge constantly without forgetting previously learned information. CL faces the challenge of mitigating catastrophic forgetting while maintaining interpretability across tasks. Most existing CL methods focus primarily on preserving learned knowledge to improve model performance. However, as new information is introduced, the interpretability of the learning process becomes crucial for understanding the evolving decision-making process, yet it is rarely explored. In this paper, we introduce a novel framework that integrates language-guided Concept Bottleneck Models (CBMs) to address both challenges. Our approach leverages the Concept Bottleneck Layer, aligning semantic consistency with CLIP models to learn human-understandable concepts that can generalize across tasks. By focusing on interpretable concepts, our method not only enhances the models ability to retain knowledge over time but also provides transparent decision-making insights. We demonstrate the effectiveness of our approach by achieving superior performance on several datasets, outperforming state-of-the-art methods with an improvement of up to 3.06% in final average accuracy on ImageNet-subset. Additionally, we offer concept visualizations for model predictions, further advancing the understanding of interpretable continual learning.

arXiv:2503.23282공식 코드 · Papers with Code

AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos

Estimating camera motion and intrinsics from casual videos is a core challenge in computer vision. Traditional bundle-adjustment based methods, such as SfM and SLAM, struggle to perform reliably on arbitrary data. Although specialized SfM approaches have been developed for handling dynamic scenes, they either require intrinsics or computationally expensive test-time optimization and often fall short in performance. Recently, methods like Dust3r have reformulated the SfM problem in a more data-driven way. While such techniques show promising results, they are still 1) not robust towards dynamic objects and 2) require labeled data for supervised training. As an alternative, we propose AnyCam, a fast transformer model that directly estimates camera poses and intrinsics from a dynamic video sequence in feed-forward fashion. Our intuition is that such a network can learn strong priors over realistic camera poses. To scale up our training, we rely on an uncertainty-based loss formulation and pre-trained depth and flow networks instead of motion or trajectory supervision. This allows us to use diverse, unlabelled video datasets obtained mostly from YouTube. Additionally, we ensure that the predicted trajectory does not accumulate drift over time through a lightweight trajectory refinement step. We test AnyCam on established datasets, where it delivers accurate camera poses and intrinsics both qualitatively and quantitatively. Furthermore, even with trajectory refinement, AnyCam is significantly faster than existing works for SfM in dynamic settings. Finally, by combining camera information, uncertainty, and depth, our model can produce high-quality 4D pointclouds.

arXiv:2503.23234공식 코드 · Papers with Code

Z-SASLM: Zero-Shot Style-Aligned SLI Blending Latent Manipulation

We introduce Z-SASLM, a Zero-Shot Style-Aligned SLI (Spherical Linear Interpolation) Blending Latent Manipulation pipeline that overcomes the limitations of current multi-style blending methods. Conventional approaches rely on linear blending, assuming a flat latent space leading to suboptimal results when integrating multiple reference styles. In contrast, our framework leverages the non-linear geometry of the latent space by using SLI Blending to combine weighted style representations. By interpolating along the geodesic on the hypersphere, Z-SASLM preserves the intrinsic structure of the latent space, ensuring high-fidelity and coherent blending of diverse styles - all without the need for fine-tuning. We further propose a new metric, Weighted Multi-Style DINO ViT-B/8, designed to quantitatively evaluate the consistency of the blended styles. While our primary focus is on the theoretical and practical advantages of SLI Blending for style manipulation, we also demonstrate its effectiveness in a multi-modal content fusion setting through comprehensive experimental studies. Experimental results show that Z-SASLM achieves enhanced and robust style alignment. The implementation code can be found at: https://github.com/alessioborgi/Z-SASLM.

arXiv:2503.23220공식 코드 · Papers with Code

Large Self-Supervised Models Bridge the Gap in Domain Adaptive Object Detection

The current state-of-the-art methods in domain adaptive object detection (DAOD) use Mean Teacher self-labelling, where a teacher model, directly derived as an exponential moving average of the student model, is used to generate labels on the target domain which are then used to improve both models in a positive loop. This couples learning and generating labels on the target domain, and other recent works also leverage the generated labels to add additional domain alignment losses. We believe this coupling is brittle and excessively constrained: there is no guarantee that a student trained only on source data can generate accurate target domain labels and initiate the positive feedback loop, and much better target domain labels can likely be generated by using a large pretrained network that has been exposed to much more data. Vision foundational models are exactly such models, and they have shown impressive task generalization capabilities even when frozen. We want to leverage these models for DAOD and introduce DINO Teacher, which consists of two components. First, we train a new labeller on source data only using a large frozen DINOv2 backbone and show it generates more accurate labels than Mean Teacher. Next, we align the student's source and target image patch features with those from a DINO encoder, driving source and target representations closer to the generalizable DINO representation. We obtain state-of-the-art performance on multiple DAOD datasets. Code available at https://github.com/TRAILab/DINO_Teacher

arXiv:2503.22748공식 코드 · Papers with Code

Ignite Forecasting with SPARK: An Efficient Generative Framework for Refining LLMs in Temporal Knowledge Graph Forecasting

Temporal Knowledge Graph (TKG) forecasting is crucial for predicting future events using historical data. With the surge of Large Language Models (LLMs), recent studies have begun exploring their integration into TKG forecasting and achieved some success. However, they still face limitations such as limited input length, inefficient output generation, and resource-intensive refinement, which undermine their performance and practical applicability. To address these limitations, we introduce SPARK, a Sequence-level Proxy-Adapting framework for Refining LLMs in TKG forecasting. Inspired by inference-time algorithms adopted in controlling generation, SPARK offers a cost-effective, plug-and-play solution through two key innovations: (1) Beam Sequence-Level Generation, which reframes TKG forecasting as a top-K sequence-level generation task, using beam search for efficiently generating next-entity distribution in a single forward pass. (2) TKG Adapter for Refinement, which employs traditional TKG models as trainable proxy adapters to leverage global graph information and refine LLM outputs, overcoming both the input length and the resource-intensive fine-tuning problems. Experiments across diverse datasets validate SPARK's forecasting performance, robust generalization capabilities, and high efficiency. We release source codes at https://github.com/yin-gz/SPARK.

arXiv:2503.22731공식 코드 · Papers with Code

MoRE-LLM: Mixture of Rule Experts Guided by a Large Language Model

To ensure the trustworthiness and interpretability of AI systems, it is essential to align machine learning models with human domain knowledge. This can be a challenging and time-consuming endeavor that requires close communication between data scientists and domain experts. Recent leaps in the capabilities of Large Language Models (LLMs) can help alleviate this burden. In this paper, we propose a Mixture of Rule Experts guided by a Large Language Model (MoRE-LLM) which combines a data-driven black-box model with knowledge extracted from an LLM to enable domain knowledge-aligned and transparent predictions. While the introduced Mixture of Rule Experts (MoRE) steers the discovery of local rule-based surrogates during training and their utilization for the classification task, the LLM is responsible for enhancing the domain knowledge alignment of the rules by correcting and contextualizing them. Importantly, our method does not rely on access to the LLM during test time and ensures interpretability while not being prone to LLM-based confabulations. We evaluate our method on several tabular data sets and compare its performance with interpretable and non-interpretable baselines. Besides performance, we evaluate our grey-box method with respect to the utilization of interpretable rules. In addition to our quantitative evaluation, we shed light on how the LLM can provide additional context to strengthen the comprehensibility and trustworthiness of the model's reasoning process.