PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2502.10841공식 코드 · Papers with Code

SkyReels-A1: Expressive Portrait Animation in Video Diffusion Transformers

We present SkyReels-A1, a simple yet effective framework built upon video diffusion Transformer to facilitate portrait image animation. Existing methodologies still encounter issues, including identity distortion, background instability, and unrealistic facial dynamics, particularly in head-only animation scenarios. Besides, extending to accommodate diverse body proportions usually leads to visual inconsistencies or unnatural articulations. To address these challenges, SkyReels-A1 capitalizes on the strong generative capabilities of video DiT, enhancing facial motion transfer precision, identity retention, and temporal coherence. The system incorporates an expression-aware conditioning module that enables seamless video synthesis driven by expression-guided landmark inputs. Integrating the facial image-text alignment module strengthens the fusion of facial attributes with motion trajectories, reinforcing identity preservation. Additionally, SkyReels-A1 incorporates a multi-stage training paradigm to incrementally refine the correlation between expressions and motion while ensuring stable identity reproduction. Extensive empirical evaluations highlight the model's ability to produce visually coherent and compositionally diverse results, making it highly applicable to domains such as virtual avatars, remote communication, and digital media generation.

arXiv:2502.10729공식 코드 · Papers with Code

VarGes: Improving Variation in Co-Speech 3D Gesture Generation via StyleCLIPS

Generating expressive and diverse human gestures from audio is crucial in fields like human-computer interaction, virtual reality, and animation. Though existing methods have achieved remarkable performance, they often exhibit limitations due to constrained dataset diversity and the restricted amount of information derived from audio inputs. To address these challenges, we present VarGes, a novel variation-driven framework designed to enhance co-speech gesture generation by integrating visual stylistic cues while maintaining naturalness. Our approach begins with the Variation-Enhanced Feature Extraction (VEFE) module, which seamlessly incorporates \textcolor{blue}{style-reference} video data into a 3D human pose estimation network to extract StyleCLIPS, thereby enriching the input with stylistic information. Subsequently, we employ the Variation-Compensation Style Encoder (VCSE), a transformer-style encoder equipped with an additive attention mechanism pooling layer, to robustly encode diverse StyleCLIPS representations and effectively manage stylistic variations. Finally, the Variation-Driven Gesture Predictor (VDGP) module fuses MFCC audio features with StyleCLIPS encodings via cross-attention, injecting this fused data into a cross-conditional autoregressive model to modulate 3D human gesture generation based on audio input and stylistic clues. The efficacy of our approach is validated on benchmark datasets, where it outperforms existing methods in terms of gesture diversity and naturalness. The code and video results will be made publicly available upon acceptance:https://github.com/mookerr/VarGES/ .

arXiv:2502.10608공식 코드 · Papers with Code

Universal Lesion Segmentation Challenge 2023: A Comparative Research of Different Algorithms

In recent years, machine learning algorithms have achieved much success in segmenting lesions across various tissues. There is, however, not one satisfying model that works well on all tissue types universally. In response to this need, we attempt to train a model that 1) works well on all tissue types, and 2) is capable of still performing fast inferences. To this end, we design our architectures, test multiple existing architectures, compare their results, and settle upon SwinUnet. We document our rationales, successes, and failures. Finally, we propose some further directions that we think are worth exploring. codes: https://github.com/KWFredShi/ULS2023NGKD.git

arXiv:2502.10601공식 코드 · Papers with Code

Data-driven Super-Resolution of Flood Inundation Maps using Synthetic Simulations

The frequency of extreme flood events is increasing throughout the world. Daily, high-resolution (30m) Flood Inundation Maps (FIM) observed from space play a key role in informing mitigation and preparedness efforts to counter these extreme events. However, the temporal frequency of publicly available high-resolution FIMs, e.g., from Landsat, is at the order of two weeks thus limiting the effective monitoring of flood inundation dynamics. Conversely, global, low-resolution (~300m) Water Fraction Maps (WFM) are publicly available from NOAA VIIRS daily. Motivated by the recent successes of deep learning methods for single image super-resolution, we explore the effectiveness and limitations of similar data-driven approaches to downscaling low-resolution WFMs to high-resolution FIMs. To overcome the scarcity of high-resolution FIMs, we train our models with high-quality synthetic data obtained through physics-based simulations. We evaluate our models on real-world data from flood events in the state of Iowa. The study indicates that data-driven approaches exhibit superior reconstruction accuracy over non-data-driven alternatives and that the use of synthetic data is a viable proxy for training purposes. Additionally, we show that our trained models can exhibit superior zero-shot performance when transferred to regions with hydroclimatological similarity to the U.S. Midwest.

arXiv:2502.10574공식 코드 · Papers with Code

Classifier-free Guidance with Adaptive Scaling

Classifier-free guidance (CFG) is an essential mechanism in contemporary text-driven diffusion models. In practice, in controlling the impact of guidance we can see the trade-off between the quality of the generated images and correspondence to the prompt. When we use strong guidance, generated images fit the conditioned text perfectly but at the cost of their quality. Dually, we can use small guidance to generate high-quality results, but the generated images do not suit our prompt. In this paper, we present $\beta$-CFG ($\beta$-adaptive scaling in Classifier-Free Guidance), which controls the impact of guidance during generation to solve the above trade-off. First, $\beta$-CFG stabilizes the effects of guiding by gradient-based adaptive normalization. Second, $\beta$-CFG uses the family of single-modal ($\beta$-distribution), time-dependent curves to dynamically adapt the trade-off between prompt matching and the quality of samples during the diffusion denoising process. Our model obtained better FID scores, maintaining the text-to-image CLIP similarity scores at a level similar to that of the reference CFG.

arXiv:2502.10498공식 코드 · Papers with Code

The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey

Driving World Model (DWM), which focuses on predicting scene evolution during the driving process, has emerged as a promising paradigm in pursuing autonomous driving. These methods enable autonomous driving systems to better perceive, understand, and interact with dynamic driving environments. In this survey, we provide a comprehensive overview of the latest progress in DWM. We categorize existing approaches based on the modalities of the predicted scenes and summarize their specific contributions to autonomous driving. In addition, high-impact datasets and various metrics tailored to different tasks within the scope of DWM research are reviewed. Finally, we discuss the potential limitations of current research and propose future directions. This survey provides valuable insights into the development and application of DWM, fostering its broader adoption in autonomous driving. The relevant papers are collected at https://github.com/LMD0311/Awesome-World-Model.

arXiv:2502.10339공식 코드 · Papers with Code

STAR: Spectral Truncation and Rescale for Model Merging

Model merging is an efficient way of obtaining a multi-task model from several pretrained models without further fine-tuning, and it has gained attention in various domains, including natural language processing (NLP). Despite the efficiency, a key challenge in model merging is the seemingly inevitable decrease in task performance as the number of models increases. In this paper, we propose $\mathbf{S}$pectral $\mathbf{T}$runcation $\mathbf{A}$nd $\mathbf{R}$escale (STAR) that aims at mitigating ``merging conflicts'' by truncating small components in the respective spectral spaces, which is followed by an automatic parameter rescaling scheme to retain the nuclear norm of the original matrix. STAR requires no additional inference on original training data and is robust to hyperparamater choice. We demonstrate the effectiveness of STAR through extensive model merging cases on diverse NLP tasks. Specifically, STAR works robustly across varying model sizes, and can outperform baselines by 4.2$\%$ when merging 12 models on Flan-T5. Our code is publicly available at https://github.com/IBM/STAR.

arXiv:2502.10325공식 코드 · Papers with Code

Process Reward Models for LLM Agents: Practical Framework and Directions

We introduce Agent Process Reward Models (AgentPRM), a simple and scalable framework for training LLM agents to continually improve through interactions. AgentPRM follows a lightweight actor-critic paradigm, using Monte Carlo rollouts to compute reward targets and optimize policies. It requires minimal modifications to existing RLHF pipelines, making it easy to integrate at scale. Beyond AgentPRM, we propose InversePRM, which learns process rewards directly from demonstrations without explicit outcome supervision. We also explore key challenges and opportunities, including exploration, process reward shaping, and model-predictive reasoning. We evaluate on ALFWorld benchmark, show that small 3B models trained with AgentPRM and InversePRM outperform strong GPT-4o baselines, and analyze test-time scaling, reward hacking, and more. Our code is available at: https://github.com/sanjibanc/agent_prm.

arXiv:2502.08025공식 코드 · Papers with Code

From Brainwaves to Brain Scans: A Robust Neural Network for EEG-to-fMRI Synthesis

While functional magnetic resonance imaging (fMRI) offers rich spatial resolution, it is limited by high operational costs and significant infrastructural demands. In contrast, electroencephalography (EEG) provides millisecond-level precision in capturing electrical activity but lacks the spatial resolution necessary for precise neural localization. To bridge these gaps, we introduce E2fNet, a simple yet effective deep learning model for synthesizing fMRI images from low-cost EEG data. E2fNet is specifically designed to capture and translate meaningful features from EEG across electrode channels into accurate fMRI representations. Extensive evaluations across three datasets demonstrate that E2fNet consistently outperforms existing methods, achieving state-of-the-art results in terms of the structural similarity index measure (SSIM). Our findings suggest that E2fNet is a promising, cost-effective solution for enhancing neuroimaging capabilities. The code is available at https://github.com/kgr20/E2fNet.

arXiv:2502.06367공식 코드 · Papers with Code

FOCUS - Multi-View Foot Reconstruction From Synthetically Trained Dense Correspondences

Surface reconstruction from multiple, calibrated images is a challenging task - often requiring a large number of collected images with significant overlap. We look at the specific case of human foot reconstruction. As with previous successful foot reconstruction work, we seek to extract rich per-pixel geometry cues from multi-view RGB images, and fuse these into a final 3D object. Our method, FOCUS, tackles this problem with 3 main contributions: (i) SynFoot2, an extension of an existing synthetic foot dataset to include a new data type: dense correspondence with the parameterized foot model FIND; (ii) an uncertainty-aware dense correspondence predictor trained on our synthetic dataset; (iii) two methods for reconstructing a 3D surface from dense correspondence predictions: one inspired by Structure-from-Motion, and one optimization-based using the FIND model. We show that our reconstruction achieves state-of-the-art reconstruction quality in a few-view setting, performing comparably to state-of-the-art when many views are available, and runs substantially faster. We release our synthetic dataset to the research community. Code is available at: https://github.com/OllieBoyne/FOCUS

arXiv:2502.00464공식 코드 · Papers with Code

Evaluation of End-to-End Continuous Spanish Lipreading in Different Data Conditions

Visual speech recognition remains an open research problem where different challenges must be considered by dispensing with the auditory sense, such as visual ambiguities, the inter-personal variability among speakers, and the complex modeling of silence. Nonetheless, recent remarkable results have been achieved in the field thanks to the availability of large-scale databases and the use of powerful attention mechanisms. Besides, multiple languages apart from English are nowadays a focus of interest. This paper presents noticeable advances in automatic continuous lipreading for Spanish. First, an end-to-end system based on the hybrid CTC/Attention architecture is presented. Experiments are conducted on two corpora of disparate nature, reaching state-of-the-art results that significantly improve the best performance obtained to date for both databases. In addition, a thorough ablation study is carried out, where it is studied how the different components that form the architecture influence the quality of speech recognition. Then, a rigorous error analysis is carried out to investigate the different factors that could affect the learning of the automatic system. Finally, a new Spanish lipreading benchmark is consolidated. Code and trained models are available at https://github.com/david-gimeno/evaluating-end2end-spanish-lipreading.

arXiv:2502.12154공식 코드 · Papers with Code

Diffusion Models without Classifier-free Guidance

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data distribution to incorporating the posterior probability of conditions. The proposed technique originates from the idea of CFG and is easy yet effective, making it a plug-and-play module for existing models. Our method significantly accelerates the training process, doubles the inference speed, and achieve exceptional quality that parallel and even surpass concurrent diffusion models with CFG. Extensive experiments demonstrate the effectiveness, efficiency, scalability on different models and datasets. Finally, we establish state-of-the-art performance on ImageNet 256 benchmarks with an FID of 1.34. Our code is available at https://github.com/tzco/Diffusion-wo-CFG.

arXiv:2502.12128공식 코드 · Papers with Code

LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities

Generative models are spearheading recent progress in deep learning, showcasing strong promise for trajectory sampling in dynamical systems as well. However, whereas latent space modeling paradigms have transformed image and video generation, similar approaches are more difficult for most dynamical systems. Such systems -- from chemical molecule structures to collective human behavior -- are described by interactions of entities, making them inherently linked to connectivity patterns, entity conservation, and the traceability of entities over time. Our approach, LaM-SLidE (Latent Space Modeling of Spatial Dynamical Systems via Linked Entities), bridges the gap between: (1) keeping the traceability of individual entities in a latent system representation, and (2) leveraging the efficiency and scalability of recent advances in image and video generation, where pre-trained encoder and decoder enable generative modeling directly in latent space. The core idea of LaM-SLidE is the introduction of identifier representations (IDs) that enable the retrieval of entity properties and entity composition from latent system representations, thus fostering traceability. Experimentally, across different domains, we show that LaM-SLidE performs favorably in terms of speed, accuracy, and generalizability. Code is available at https://github.com/ml-jku/LaM-SLidE .

arXiv:2502.11941공식 코드 · Papers with Code

Deep Spatio-Temporal Neural Network for Air Quality Reanalysis

Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We propose AQ-Net, a spatiotemporal reanalysis model for both observed and unobserved stations in the near future. AQ-Net utilizes the LSTM and multi-head attention for the temporal regression. We also propose a cyclic encoding technique to ensure continuous time representation. To learn fine-grained spatial air quality estimation, we incorporate AQ-Net with the neural kNN to explore feature-based interpolation, such that we can fill the spatial gaps given coarse observation stations. To demonstrate the efficiency of our model for spatiotemporal reanalysis, we use data from 2013-2017 collected in northern China for PM2.5 analysis. Extensive experiments show that AQ-Net excels in air quality reanalysis, highlighting the potential of hybrid spatio-temporal models to better capture environmental dynamics, especially in urban areas where both spatial and temporal variability are critical.

arXiv:2502.11897공식 코드 · Papers with Code

DLFR-VAE: Dynamic Latent Frame Rate VAE for Video Generation

In this paper, we propose the Dynamic Latent Frame Rate VAE (DLFR-VAE), a training-free paradigm that can make use of adaptive temporal compression in latent space. While existing video generative models apply fixed compression rates via pretrained VAE, we observe that real-world video content exhibits substantial temporal non-uniformity, with high-motion segments containing more information than static scenes. Based on this insight, DLFR-VAE dynamically adjusts the latent frame rate according to the content complexity. Specifically, DLFR-VAE comprises two core innovations: (1) A Dynamic Latent Frame Rate Scheduler that partitions videos into temporal chunks and adaptively determines optimal frame rates based on information-theoretic content complexity, and (2) A training-free adaptation mechanism that transforms pretrained VAE architectures into a dynamic VAE that can process features with variable frame rates. Our simple but effective DLFR-VAE can function as a plug-and-play module, seamlessly integrating with existing video generation models and accelerating the video generation process.

arXiv:2502.11850공식 코드 · Papers with Code

Steering the LoCoMotif: Using Domain Knowledge in Time Series Motif Discovery

Time Series Motif Discovery (TSMD) identifies repeating patterns in time series data, but its unsupervised nature might result in motifs that are not interesting to the user. To address this, we propose a framework that allows the user to impose constraints on the motifs to be discovered, where constraints can easily be defined according to the properties of the desired motifs in the application domain. We also propose an efficient implementation of the framework, the LoCoMotif-DoK algorithm. We demonstrate that LoCoMotif-DoK can effectively leverage domain knowledge in real and synthetic data, outperforming other TSMD techniques which only support a limited form of domain knowledge.

arXiv:2502.11831공식 코드 · Papers with Code

Intuitive physics understanding emerges from self-supervised pretraining on natural videos

We investigate the emergence of intuitive physics understanding in general-purpose deep neural network models trained to predict masked regions in natural videos. Leveraging the violation-of-expectation framework, we find that video prediction models trained to predict outcomes in a learned representation space demonstrate an understanding of various intuitive physics properties, such as object permanence and shape consistency. In contrast, video prediction in pixel space and multimodal large language models, which reason through text, achieve performance closer to chance. Our comparisons of these architectures reveal that jointly learning an abstract representation space while predicting missing parts of sensory input, akin to predictive coding, is sufficient to acquire an understanding of intuitive physics, and that even models trained on one week of unique video achieve above chance performance. This challenges the idea that core knowledge -- a set of innate systems to help understand the world -- needs to be hardwired to develop an understanding of intuitive physics.

arXiv:2502.11751공식 코드 · Papers with Code

Language Models Can See Better: Visual Contrastive Decoding For LLM Multimodal Reasoning

Although Large Language Models (LLMs) excel in reasoning and generation for language tasks, they are not specifically designed for multimodal challenges. Training Multimodal Large Language Models (MLLMs), however, is resource-intensive and constrained by various training limitations. In this paper, we propose the Modular-based Visual Contrastive Decoding (MVCD) framework to move this obstacle. Our framework leverages LLMs' In-Context Learning (ICL) capability and the proposed visual contrastive-example decoding (CED), specifically tailored for this framework, without requiring any additional training. By converting visual signals into text and focusing on contrastive output distributions during decoding, we can highlight the new information introduced by contextual examples, explore their connections, and avoid over-reliance on prior encoded knowledge. MVCD enhances LLMs' visual perception to make it see and reason over the input visuals. To demonstrate MVCD's effectiveness, we conduct experiments with four LLMs across five question answering datasets. Our results not only show consistent improvement in model accuracy but well explain the effective components inside our decoding strategy. Our code will be available at https://github.com/Pbhgit/MVCD.

arXiv:2502.11680공식 코드 · Papers with Code

Spectral structure learning for clinical time series

We develop and evaluate a structure learning algorithm for clinical time series. Clinical time series are multivariate time series observed in multiple patients and irregularly sampled, challenging existing structure learning algorithms. We assume that our times series are realizations of StructGP, a k-dimensional multi-output or multi-task stationary Gaussian process (GP), with independent patients sharing the same covariance function. StructGP encodes ordered conditional relations between time series, represented in a directed acyclic graph. We implement an adapted NOTEARS algorithm, which based on a differentiable definition of acyclicity, recovers the graph by solving a series of continuous optimization problems. Simulation results show that up to mean degree 3 and 20 tasks, we reach a median recall of 0.93% [IQR, 0.86, 0.97] while keeping a median precision of 0.71% [0.57-0.84], for recovering directed edges. We further show that the regularization path is key to identifying the graph. With StructGP, we proposed a model of time series dependencies, that flexibly adapt to different time series regularity, while enabling us to learn these dependencies from observations.

arXiv:2502.11651공식 코드 · Papers with Code

MMXU: A Multi-Modal and Multi-X-ray Understanding Dataset for Disease Progression

Large vision-language models (LVLMs) have shown great promise in medical applications, particularly in visual question answering (MedVQA) and diagnosis from medical images. However, existing datasets and models often fail to consider critical aspects of medical diagnostics, such as the integration of historical records and the analysis of disease progression over time. In this paper, we introduce MMXU (Multimodal and MultiX-ray Understanding), a novel dataset for MedVQA that focuses on identifying changes in specific regions between two patient visits. Unlike previous datasets that primarily address single-image questions, MMXU enables multi-image questions, incorporating both current and historical patient data. We demonstrate the limitations of current LVLMs in identifying disease progression on MMXU-\textit{test}, even those that perform well on traditional benchmarks. To address this, we propose a MedRecord-Augmented Generation (MAG) approach, incorporating both global and regional historical records. Our experiments show that integrating historical records significantly enhances diagnostic accuracy by at least 20\%, bridging the gap between current LVLMs and human expert performance. Additionally, we fine-tune models with MAG on MMXU-\textit{dev}, which demonstrates notable improvements. We hope this work could illuminate the avenue of advancing the use of LVLMs in medical diagnostics by emphasizing the importance of historical context in interpreting medical images. Our dataset is released at \href{https://github.com/linjiemu/MMXU}{https://github.com/linjiemu/MMXU}.