PyTorchKR Papers

최신 논문

총 139,336편
태그·기간 등 상세 필터

카테고리 탐색

arXiv:2503.14795공식 코드 · Papers with Code

The Hardness of Validating Observational Studies with Experimental Data

Observational data is often readily available in large quantities, but can lead to biased causal effect estimates due to the presence of unobserved confounding. Recent works attempt to remove this bias by supplementing observational data with experimental data, which, when available, is typically on a smaller scale due to the time and cost involved in running a randomised controlled trial. In this work, we prove a theorem that places fundamental limits on this ``best of both worlds'' approach. Using the framework of impossible inference, we show that although it is possible to use experimental data to \emph{falsify} causal effect estimates from observational data, in general it is not possible to \emph{validate} such estimates. Our theorem proves that while experimental data can be used to detect bias in observational studies, without additional assumptions on the smoothness of the correction function, it can not be used to remove it. We provide a practical example of such an assumption, developing a novel Gaussian Process based approach to construct intervals which contain the true treatment effect with high probability, both inside and outside of the support of the experimental data. We demonstrate our methodology on both simulated and semi-synthetic datasets and make the \href{https://github.com/Jakefawkes/Obs_and_exp_data}{code available}.

arXiv:2503.14535공식 코드 · Papers with Code

Interpretable Unsupervised Joint Denoising and Enhancement for Real-World low-light Scenarios

Real-world low-light images often suffer from complex degradations such as local overexposure, low brightness, noise, and uneven illumination. Supervised methods tend to overfit to specific scenarios, while unsupervised methods, though better at generalization, struggle to model these degradations due to the lack of reference images. To address this issue, we propose an interpretable, zero-reference joint denoising and low-light enhancement framework tailored for real-world scenarios. Our method derives a training strategy based on paired sub-images with varying illumination and noise levels, grounded in physical imaging principles and retinex theory. Additionally, we leverage the Discrete Cosine Transform (DCT) to perform frequency domain decomposition in the sRGB space, and introduce an implicit-guided hybrid representation strategy that effectively separates intricate compounded degradations. In the backbone network design, we develop retinal decomposition network guided by implicit degradation representation mechanisms. Extensive experiments demonstrate the superiority of our method. Code will be available at https://github.com/huaqlili/unsupervised-light-enhance-ICLR2025.

arXiv:2503.16309공식 코드 · Papers with Code

Rapid patient-specific neural networks for intraoperative X-ray to volume registration

The integration of artificial intelligence in image-guided interventions holds transformative potential, promising to extract 3D geometric and quantitative information from conventional 2D imaging modalities during complex procedures. Achieving this requires the rapid and precise alignment of 2D intraoperative images (e.g., X-ray) with 3D preoperative volumes (e.g., CT, MRI). However, current 2D/3D registration methods fail across the broad spectrum of procedures dependent on X-ray guidance: traditional optimization techniques require custom parameter tuning for each subject, whereas neural networks trained on small datasets do not generalize to new patients or require labor-intensive manual annotations, increasing clinical burden and precluding application to new anatomical targets. To address these challenges, we present xvr, a fully automated framework for training patient-specific neural networks for 2D/3D registration. xvr uses physics-based simulation to generate abundant high-quality training data from a patient's own preoperative volumetric imaging, thereby overcoming the inherently limited ability of supervised models to generalize to new patients and procedures. Furthermore, xvr requires only 5 minutes of training per patient, making it suitable for emergency interventions as well as planned procedures. We perform the largest evaluation of a 2D/3D registration algorithm on real X-ray data to date and find that xvr robustly generalizes across a diverse dataset comprising multiple anatomical structures, imaging modalities, and hospitals. Across surgical tasks, xvr achieves submillimeter-accurate registration at intraoperative speeds, improving upon existing methods by an order of magnitude. xvr is released as open-source software freely available at https://github.com/eigenvivek/xvr.

arXiv:2503.16302공식 코드 · Papers with Code

Unleashing Vecset Diffusion Model for Fast Shape Generation

3D shape generation has greatly flourished through the development of so-called "native" 3D diffusion, particularly through the Vecset Diffusion Model (VDM). While recent advancements have shown promising results in generating high-resolution 3D shapes, VDM still struggles with high-speed generation. Challenges exist because of difficulties not only in accelerating diffusion sampling but also VAE decoding in VDM, areas under-explored in previous works. To address these challenges, we present FlashVDM, a systematic framework for accelerating both VAE and DiT in VDM. For DiT, FlashVDM enables flexible diffusion sampling with as few as 5 inference steps and comparable quality, which is made possible by stabilizing consistency distillation with our newly introduced Progressive Flow Distillation. For VAE, we introduce a lightning vecset decoder equipped with Adaptive KV Selection, Hierarchical Volume Decoding, and Efficient Network Design. By exploiting the locality of the vecset and the sparsity of shape surface in the volume, our decoder drastically lowers FLOPs, minimizing the overall decoding overhead. We apply FlashVDM to Hunyuan3D-2 to obtain Hunyuan3D-2 Turbo. Through systematic evaluation, we show that our model significantly outperforms existing fast 3D generation methods, achieving comparable performance to the state-of-the-art while reducing inference time by over 45x for reconstruction and 32x for generation. Code and models are available at https://github.com/Tencent/FlashVDM.

arXiv:2503.16278공식 코드 · Papers with Code

Uni-3DAR: Unified 3D Generation and Understanding via Autoregression on Compressed Spatial Tokens

Recent advancements in large language models and their multi-modal extensions have demonstrated the effectiveness of unifying generation and understanding through autoregressive next-token prediction. However, despite the critical role of 3D structural generation and understanding (3D GU) in AI for science, these tasks have largely evolved independently, with autoregressive methods remaining underexplored. To bridge this gap, we introduce Uni-3DAR, a unified framework that seamlessly integrates 3D GU tasks via autoregressive prediction. At its core, Uni-3DAR employs a novel hierarchical tokenization that compresses 3D space using an octree, leveraging the inherent sparsity of 3D structures. It then applies an additional tokenization for fine-grained structural details, capturing key attributes such as atom types and precise spatial coordinates in microscopic 3D structures. We further propose two optimizations to enhance efficiency and effectiveness. The first is a two-level subtree compression strategy, which reduces the octree token sequence by up to 8x. The second is a masked next-token prediction mechanism tailored for dynamically varying token positions, significantly boosting model performance. By combining these strategies, Uni-3DAR successfully unifies diverse 3D GU tasks within a single autoregressive framework. Extensive experiments across multiple microscopic 3D GU tasks, including molecules, proteins, polymers, and crystals, validate its effectiveness and versatility. Notably, Uni-3DAR surpasses previous state-of-the-art diffusion models by a substantial margin, achieving up to 256\% relative improvement while delivering inference speeds up to 21.8x faster. The code is publicly available at https://github.com/dptech-corp/Uni-3DAR.

arXiv:2503.16055공식 코드 · Papers with Code

SALT: Singular Value Adaptation with Low-Rank Transformation

The complex nature of medical image segmentation calls for models that are specifically designed to capture detailed, domain-specific features. Large foundation models offer considerable flexibility, yet the cost of fine-tuning these models remains a significant barrier. Parameter-Efficient Fine-Tuning (PEFT) methods, such as Low-Rank Adaptation (LoRA), efficiently update model weights with low-rank matrices but may suffer from underfitting when the chosen rank is insufficient to capture domain-specific nuances. Conversely, full-rank Singular Value Decomposition (SVD) based methods provide comprehensive updates by modifying all singular values, yet they often lack flexibility and exhibit variable performance across datasets. We propose SALT (Singular Value Adaptation with Low-Rank Transformation), a method that selectively adapts the most influential singular values using trainable scale and shift parameters while complementing this with a low-rank update for the remaining subspace. This hybrid approach harnesses the advantages of both LoRA and SVD, enabling effective adaptation without relying on increasing model size or depth. Evaluated on 5 challenging medical datasets, ranging from as few as 20 samples to 1000, SALT outperforms state-of-the-art PEFT (LoRA and SVD) by 2% to 5% in Dice with only 3.9% trainable parameters, demonstrating robust adaptation even in low-resource settings. The code for SALT is available at: https://github.com/BioMedIA-MBZUAI/SALT

arXiv:2503.15823공식 코드 · Papers with Code

A Unified Stability Analysis of Safety-Critical Control using Multiple Control Barrier Functions

Ensuring liveness and safety of autonomous and cyber-physical systems remains a fundamental challenge, particularly when multiple safety constraints are present. This letter advances the theoretical foundations of safety-filter Quadratic Programs (QP) and Control Lyapunov Function (CLF)-Control Barrier Function (CBF) controllers by establishing a unified analytical framework for studying their stability properties. We derive sufficient feasibility conditions for QPs with multiple CBFs and formally characterize the conditions leading to undesirable equilibrium points at possible intersecting safe set boundaries. Additionally, we introduce a stability criterion for equilibrium points, providing a systematic approach to identifying conditions under which they can be destabilized or eliminated. Our analysis extends prior theoretical results, deepening the understanding of the conditions of feasibility and stability of CBF-based safety filters and the CLF-CBF QP framework.

arXiv:2503.15581공식 코드 · Papers with Code

Performance-bounded Online Ensemble Learning Method Based on Multi-armed bandits and Its Applications in Real-time Safety Assessment

Ensemble learning plays a crucial role in practical applications of online learning due to its enhanced classification performance and adaptable adjustment mechanisms. However, most weight allocation strategies in ensemble learning are heuristic, making it challenging to theoretically guarantee that the ensemble classifier outperforms its base classifiers. To address this issue, a performance-bounded online ensemble learning method based on multi-armed bandits, named PB-OEL, is proposed in this paper. Specifically, multi-armed bandit with expert advice is incorporated into online ensemble learning, aiming to update the weights of base classifiers and make predictions. A theoretical framework is established to bound the performance of the ensemble classifier relative to base classifiers. By setting expert advice of bandits, the bound exceeds the performance of any base classifier when the length of data stream is sufficiently large. Additionally, performance bounds for scenarios with limited annotations are also derived. Numerous experiments on benchmark datasets and a dataset of real-time safety assessment tasks are conducted. The experimental results validate the theoretical bound to a certain extent and demonstrate that the proposed method outperforms existing state-of-the-art methods.

arXiv:2503.15576공식 코드 · Papers with Code

A Bird Song Detector for improving bird identification through Deep Learning: a case study from Doñana

Passive Acoustic Monitoring is a key tool for biodiversity conservation, but the large volumes of unsupervised audio it generates present major challenges for extracting meaningful information. Deep Learning offers promising solutions. BirdNET, a widely used bird identification model, has shown success in many study systems but is limited at local scale due to biases in its training data, which focus on specific locations and target sounds rather than entire soundscapes. A key challenge in bird species identification is that many recordings either lack target species or contain overlapping vocalizations, complicating automatic identification. To address these problems, we developed a multi-stage pipeline for automatic bird vocalization identification in Do\~nana National Park (SW Spain), a wetland of high conservation concern. We deployed AudioMoth recorders in three main habitats across nine locations and manually annotated 461 minutes of audio, resulting in 3749 labeled segments spanning 34 classes. We first applied a Bird Song Detector to isolate bird vocalizations using spectrogram-based image processing. Then, species were classified using custom models trained at the local scale. Applying the Bird Song Detector before classification improved species identification, as all models performed better when analyzing only the segments where birds were detected. Specifically, the combination of detector and fine-tuned BirdNET outperformed the baseline without detection. This approach demonstrates the effectiveness of integrating a Bird Song Detector with local classification models. These findings highlight the need to adapt general-purpose tools to specific ecological challenges. Automatically detecting bird species helps track the health of this threatened ecosystem, given birds sensitivity to environmental change, and supports conservation planning to reduce biodiversity loss.

arXiv:2503.15416공식 코드 · Papers with Code

The value of hedging against energy storage uncertainties when designing energy parks

Energy storage is needed to match renewable generation to industrial loads in energy parks. However, the future performance of bulk storage technologies is currently highly uncertain. Due to the urgency of decarbonization targets, energy park projects must be designed and begun now. But, as uncertainty in storage performance reduces, a different technology than identified during initial design may turn out cheaper. Enabling flexibility so that design adaptations can be made as better information becomes available would lower the cost of decarbonizing industry. But having this flexibility is itself costly. This raises the question, "Is it worth it?" This study quantifies the benefit of retaining flexibility to adapt energy park designs and optionality over storage technology choice as uncertainty reduces, to determine whether it is economically worthwhile. It applies the Value of Information analysis framework to the sizing of wind, solar, and storage in an illustrative energy park model based on a real-world proposal near Rotterdam, considering uncertainty in storage efficiency, lifetime, and capital cost. Updating asset sizings after storage uncertainty reduced is found to reduce total costs by 18% on average. Having the option to switch storage technology choice as well reduces costs by a further 13%, which is substantially greater than the cost of providing storage optionality. Using two storage technologies in the energy park reduces costs by 14%, and in this case storage optionality is not worthwhile. These results are robust to the level of uncertainty reduction in storage performance, and the risk aversion of the system designer.

arXiv:2503.15288공식 코드 · Papers with Code

Beacon2Science: Enhancing STEREO/HI beacon data1 with machine learning for efficient CME tracking

Observing and forecasting coronal mass ejections (CME) in real-time is crucial due to the strong geomagnetic storms they can generate that can have a potentially damaging effect, for example, on satellites and electrical devices. With its near-real-time availability, STEREO/HI beacon data is the perfect candidate for early forecasting of CMEs. However, previous work concluded that CME arrival prediction based on beacon data could not achieve the same accuracy as with high-resolution science data due to data gaps and lower quality. We present our novel pipeline entitled ''Beacon2Science'', bridging the gap between beacon and science data to improve CME tracking. Through this pipeline, we first enhance the quality (signal-to-noise ratio and spatial resolution) of beacon data. We then increase the time resolution of enhanced beacon images through learned interpolation to match science data's 40-minute resolution. We maximize information coherence between consecutive frames with adapted model architecture and loss functions through the different steps. The improved beacon images are comparable to science data, showing better CME visibility than the original beacon data. Furthermore, we compare CMEs tracked in beacon, enhanced beacon, and science images. The tracks extracted from enhanced beacon data are closer to those from science images, with a mean average error of $\sim 0.5 ^\circ$ of elongation compared to $1^\circ$ with original beacon data. The work presented in this paper paves the way for its application to forthcoming missions such as Vigil and PUNCH.

arXiv:2503.15013공식 코드 · Papers with Code

Ambient Noise Full Waveform Inversion with Neural Operators

Numerical simulations of seismic wave propagation are crucial for investigating velocity structures and improving seismic hazard assessment. However, standard methods such as finite difference or finite element are computationally expensive. Recent studies have shown that a new class of machine learning models, called neural operators, can solve the elastodynamic wave equation orders of magnitude faster than conventional methods. Full waveform inversion is a prime beneficiary of the accelerated simulations. Neural operators, as end-to-end differentiable operators, combined with automatic differentiation, provide an alternative approach to the adjoint-state method. Since neural operators do not involve the Born approximation, when used for full waveform inversion they have the potential to include additional phases and alleviate cycle-skipping problems present in traditional adjoint-state formulations. In this study, we demonstrate the first application of neural operators for full waveform inversion on a real seismic dataset, which consists of several nodal transects collected across the San Gabriel, Chino, and San Bernardino basins in the Los Angeles metropolitan area.

arXiv:2503.14966공식 코드 · Papers with Code

Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models

Ultrasound video classification enables automated diagnosis and has emerged as an important research area. However, publicly available ultrasound video datasets remain scarce, hindering progress in developing effective video classification models. We propose addressing this shortage by synthesizing plausible ultrasound videos from readily available, abundant ultrasound images. To this end, we introduce a latent dynamic diffusion model (LDDM) to efficiently translate static images to dynamic sequences with realistic video characteristics. We demonstrate strong quantitative results and visually appealing synthesized videos on the BUSV benchmark. Notably, training video classification models on combinations of real and LDDM-synthesized videos substantially improves performance over using real data alone, indicating our method successfully emulates dynamics critical for discrimination. Our image-to-video approach provides an effective data augmentation solution to advance ultrasound video analysis. Code is available at https://github.com/MedAITech/U_I2V.

arXiv:2503.14630공식 코드 · Papers with Code

Assessing Large Language Models for Automated Feedback Generation in Learning Programming Problem Solving

Providing effective feedback is important for student learning in programming problem-solving. In this sense, Large Language Models (LLMs) have emerged as potential tools to automate feedback generation. However, their reliability and ability to identify reasoning errors in student code remain not well understood. This study evaluates the performance of four LLMs (GPT-4o, GPT-4o mini, GPT-4-Turbo, and Gemini-1.5-pro) on a benchmark dataset of 45 student solutions. We assessed the models' capacity to provide accurate and insightful feedback, particularly in identifying reasoning mistakes. Our analysis reveals that 63\% of feedback hints were accurate and complete, while 37\% contained mistakes, including incorrect line identification, flawed explanations, or hallucinated issues. These findings highlight the potential and limitations of LLMs in programming education and underscore the need for improvements to enhance reliability and minimize risks in educational applications.

arXiv:2503.14523공식 코드 · Papers with Code

SDF-TopoNet: A Two-Stage Framework for Tubular Structure Segmentation via SDF Pre-training and Topology-Aware Fine-Tuning

Accurate segmentation of tubular and curvilinear structures, such as blood vessels, neurons, and road networks, is crucial in various applications. A key challenge is ensuring topological correctness while maintaining computational efficiency. Existing approaches often employ topological loss functions based on persistent homology, such as Betti error, to enforce structural consistency. However, these methods suffer from high computational costs and are insensitive to pixel-level accuracy, often requiring additional loss terms like Dice or MSE to compensate. To address these limitations, we propose \textbf{SDF-TopoNet}, an improved topology-aware segmentation framework that enhances both segmentation accuracy and training efficiency. Our approach introduces a novel two-stage training strategy. In the pre-training phase, we utilize the signed distance function (SDF) as an auxiliary learning target, allowing the model to encode topological information without directly relying on computationally expensive topological loss functions. In the fine-tuning phase, we incorporate a dynamic adapter alongside a refined topological loss to ensure topological correctness while mitigating overfitting and computational overhead. We evaluate our method on five benchmark datasets. Experimental results demonstrate that SDF-TopoNet outperforms existing methods in both topological accuracy and quantitative segmentation metrics, while significantly reducing training complexity.

arXiv:2503.16413공식 코드 · Papers with Code

M3: 3D-Spatial MultiModal Memory

We present 3D Spatial MultiModal Memory (M3), a multimodal memory system designed to retain information about medium-sized static scenes through video sources for visual perception. By integrating 3D Gaussian Splatting techniques with foundation models, M3 builds a multimodal memory capable of rendering feature representations across granularities, encompassing a wide range of knowledge. In our exploration, we identify two key challenges in previous works on feature splatting: (1) computational constraints in storing high-dimensional features for each Gaussian primitive, and (2) misalignment or information loss between distilled features and foundation model features. To address these challenges, we propose M3 with key components of principal scene components and Gaussian memory attention, enabling efficient training and inference. To validate M3, we conduct comprehensive quantitative evaluations of feature similarity and downstream tasks, as well as qualitative visualizations to highlight the pixel trace of Gaussian memory attention. Our approach encompasses a diverse range of foundation models, including vision-language models (VLMs), perception models, and large multimodal and language models (LMMs/LLMs). Furthermore, to demonstrate real-world applicability, we deploy M3's feature field in indoor scenes on a quadruped robot. Notably, we claim that M3 is the first work to address the core compression challenges in 3D feature distillation.

arXiv:2503.15819공식 코드 · Papers with Code

Control Pneumatic Soft Bending Actuator with Online Learning Pneumatic Physical Reservoir Computing

The intrinsic nonlinearities of soft robots present significant control but simultaneously provide them with rich computational potential. Reservoir computing (RC) has shown effectiveness in online learning systems for controlling nonlinear systems such as soft actuators. Conventional RC can be extended into physical reservoir computing (PRC) by leveraging the nonlinear dynamics of soft actuators for computation. This paper introduces a PRC-based online learning framework to control the motion of a pneumatic soft bending actuator, utilizing another pneumatic soft actuator as the PRC model. Unlike conventional designs requiring two RC models, the proposed control system employs a more compact architecture with a single RC model. Additionally, the framework enables zero-shot online learning, addressing limitations of previous PRC-based control systems reliant on offline training. Simulations and experiments validated the performance of the proposed system. Experimental results indicate that the PRC model achieved superior control performance compared to a linear model, reducing the root-mean-square error (RMSE) by an average of over 37% in bending motion control tasks. The proposed PRC-based online learning control framework provides a novel approach for harnessing physical systems' inherent nonlinearities to enhance the control of soft actuators.

arXiv:2503.15621공식 코드 · Papers with Code

LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning

Recent progress in Multimodal Large Language Models (MLLMs) has highlighted the critical roles of both the visual backbone and the underlying language model. While prior work has primarily focused on scaling these components to billions of parameters, the trade-offs between model size, architecture, and performance remain underexplored. Additionally, inconsistencies in training data and evaluation protocols have hindered direct comparisons, making it difficult to derive optimal design choices. In this paper, we introduce LLaVA-MORE, a new family of MLLMs that integrates recent language models with diverse visual backbones. To ensure fair comparisons, we employ a unified training protocol applied consistently across all architectures. Our analysis systematically explores both small- and medium-scale LLMs -- including Phi-4, LLaMA-3.1, and Gemma-2 -- to evaluate multimodal reasoning, generation, and instruction following, while examining the relationship between model size and performance. Beyond evaluating the LLM impact on final results, we conduct a comprehensive study of various visual encoders, ranging from CLIP-based architectures to alternatives such as DINOv2, SigLIP, and SigLIP2. Additional experiments investigate the effects of increased image resolution and variations in pre-training datasets. Overall, our results provide insights into the design of more effective MLLMs, offering a reproducible evaluation framework that facilitates direct comparisons and can guide future model development. Our source code and trained models are publicly available at: https://github.com/aimagelab/LLaVA-MORE.

arXiv:2503.15558공식 코드 · Papers with Code

Cosmos-Reason1: From Physical Common Sense To Embodied Reasoning

Physical AI systems need to perceive, understand, and perform complex actions in the physical world. In this paper, we present the Cosmos-Reason1 models that can understand the physical world and generate appropriate embodied decisions (e.g., next step action) in natural language through long chain-of-thought reasoning processes. We begin by defining key capabilities for Physical AI reasoning, with a focus on physical common sense and embodied reasoning. To represent physical common sense, we use a hierarchical ontology that captures fundamental knowledge about space, time, and physics. For embodied reasoning, we rely on a two-dimensional ontology that generalizes across different physical embodiments. Building on these capabilities, we develop two multimodal large language models, Cosmos-Reason1-7B and Cosmos-Reason1-56B. We curate data and train our models in two stages: Physical AI supervised fine-tuning (SFT) and Physical AI reinforcement learning (RL). To evaluate our models, we build comprehensive benchmarks for physical common sense and embodied reasoning according to our ontologies. Evaluation results show that Physical AI SFT and RL bring significant improvements. To facilitate the development of Physical AI, we make our code and pre-trained models available under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-reason1.

arXiv:2503.15338공식 코드 · Papers with Code

Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context

Large Language Models (LLMs) have recently shown remarkable ability to process not only text but also multimodal inputs such as speech and audio. However, most existing models primarily focus on analyzing input signals using text instructions, overlooking scenarios in which speech instructions and audio are mixed and serve as inputs to the model. To address these challenges, we introduce Solla, a novel framework designed to understand speech-based questions and hear the acoustic context concurrently. Solla incorporates an audio tagging module to effectively identify and represent audio events, as well as an ASR-assisted prediction method to improve comprehension of spoken content. To rigorously evaluate Solla and other publicly available models, we propose a new benchmark dataset called SA-Eval, which includes three tasks: audio event classification, audio captioning, and audio question answering. SA-Eval has diverse speech instruction with various speaking styles, encompassing two difficulty levels, easy and hard, to capture the range of real-world acoustic conditions. Experimental results show that Solla performs on par with or outperforms baseline models on both the easy and hard test sets, underscoring its effectiveness in jointly understanding speech and audio.