PyTorchKR Papers

최신 논문

총 4,899편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2409.14363

MANTA -- Model Adapter Native generations that's Affordable

The presiding model generation algorithms rely on simple, inflexible adapter selection to provide personalized results. We propose the model-adapter composition problem as a generalized problem to past work factoring in practical hardware and affordability constraints, and introduce MANTA as a new approach to the problem. Experiments on COCO 2014 validation show MANTA to be superior in image task diversity and quality at the cost of a modest drop in alignment. Our system achieves a $94\%$ win rate in task diversity and a $80\%$ task quality win rate versus the best known system, and demonstrates strong potential for direct use in synthetic data generation and the creative art domains.

arXiv:2409.13972

Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch

Current common interactions with language models is through full inference. This approach may not necessarily align with the model's internal knowledge. Studies show discrepancies between prompts and internal representations. Most focus on sentence understanding. We study the discrepancy of word semantics understanding in internal and external mismatch across Encoder-only, Decoder-only, and Encoder-Decoder pre-trained language models.

arXiv:2409.13920공식 코드 · Papers with Code

One Model is All You Need: ByT5-Sanskrit, a Unified Model for Sanskrit NLP Tasks

Morphologically rich languages are notoriously challenging to process for downstream NLP applications. This paper presents a new pretrained language model, ByT5-Sanskrit, designed for NLP applications involving the morphologically rich language Sanskrit. We evaluate ByT5-Sanskrit on established Sanskrit word segmentation tasks, where it outperforms previous data-driven approaches by a considerable margin and matches the performance of the current best lexicon-based model. It is easier to deploy and more robust to data not covered by external linguistic resources. It also achieves new state-of-the-art results in Vedic Sanskrit dependency parsing and OCR post-correction tasks. Additionally, based on the Digital Corpus of Sanskrit, we introduce a novel multitask dataset for the joint training of Sanskrit word segmentation, lemmatization, and morphosyntactic tagging tasks. We fine-tune ByT5-Sanskrit on this dataset, creating a versatile multitask model for various downstream Sanskrit applications. We have used this model in Sanskrit linguistic annotation projects, in information retrieval setups, and as a preprocessing step in a Sanskrit machine translation pipeline. We also show that our approach yields new best scores for lemmatization and dependency parsing of other morphologically rich languages. We thus demonstrate that byte-level pretrained language models can achieve excellent performance for morphologically rich languages, outperforming tokenizer-based models and presenting an important vector of exploration when constructing NLP pipelines for such languages.

arXiv:2409.12724

PVContext: Hybrid Context Model for Point Cloud Compression

Efficient storage of large-scale point cloud data has become increasingly challenging due to advancements in scanning technology. Recent deep learning techniques have revolutionized this field; However, most existing approaches rely on single-modality contexts, such as octree nodes or voxel occupancy, limiting their ability to capture information across large regions. In this paper, we propose PVContext, a hybrid context model for effective octree-based point cloud compression. PVContext comprises two components with distinct modalities: the Voxel Context, which accurately represents local geometric information using voxels, and the Point Context, which efficiently preserves global shape information from point clouds. By integrating these two contexts, we retain detailed information across large areas while controlling the context size. The combined context is then fed into a deep entropy model to accurately predict occupancy. Experimental results demonstrate that, compared to G-PCC, our method reduces the bitrate by 37.95\% on SemanticKITTI LiDAR point clouds and by 48.98\% and 36.36\% on dense object point clouds from MPEG 8i and MVUB, respectively.

arXiv:2409.12470공식 코드 · Papers with Code

HSIGene: A Foundation Model For Hyperspectral Image Generation

Hyperspectral image (HSI) plays a vital role in various fields such as agriculture and environmental monitoring. However, due to the expensive acquisition cost, the number of hyperspectral images is limited, degenerating the performance of downstream tasks. Although some recent studies have attempted to employ diffusion models to synthesize HSIs, they still struggle with the scarcity of HSIs, affecting the reliability and diversity of the generated images. Some studies propose to incorporate multi-modal data to enhance spatial diversity, but the spectral fidelity cannot be ensured. In addition, existing HSI synthesis models are typically uncontrollable or only support single-condition control, limiting their ability to generate accurate and reliable HSIs. To alleviate these issues, we propose HSIGene, a novel HSI generation foundation model which is based on latent diffusion and supports multi-condition control, allowing for more precise and reliable HSI generation. To enhance the spatial diversity of the training data while preserving spectral fidelity, we propose a new data augmentation method based on spatial super-resolution, in which HSIs are upscaled first, and thus abundant training patches could be obtained by cropping the high-resolution HSIs. In addition, to improve the perceptual quality of the augmented data, we introduce a novel two-stage HSI super-resolution framework, which first applies RGB bands super-resolution and then utilizes our proposed Rectangular Guided Attention Network (RGAN) for guided HSI super-resolution. Experiments demonstrate that the proposed model is capable of generating a vast quantity of realistic HSIs for downstream tasks such as denoising and super-resolution. The code and models are available at https://github.com/LiPang/HSIGene.

arXiv:2409.12272공식 코드 · Papers with Code

Mastering Chess with a Transformer Model

Transformer models have demonstrated impressive capabilities when trained at scale, excelling at difficult cognitive tasks requiring complex reasoning and rational decision-making. In this paper, we explore the application of transformers to chess, focusing on the critical role of the position representation within the attention mechanism. We show that transformers endowed with a sufficiently expressive position representation can match existing chess-playing models at a fraction of the computational cost. Our architecture, which we call the Chessformer, significantly outperforms AlphaZero in both playing strength and puzzle solving ability with 8x less computation and matches prior grandmaster-level transformer-based agents in those metrics with 30x less computation. Our models also display an understanding of chess dissimilar and orthogonal to that of top traditional engines, detecting high-level positional features like trapped pieces and fortresses that those engines struggle with. This work demonstrates that domain-specific enhancements can in large part replace the need for model scale, while also highlighting that deep learning can make strides even in areas dominated by search-based methods.

arXiv:2409.12903공식 코드 · Papers with Code

Scaling Smart: Accelerating Large Language Model Pre-training with Small Model Initialization

The pre-training phase of language models often begins with randomly initialized parameters. With the current trends in scaling models, training their large number of parameters can be extremely slow and costly. In contrast, small language models are less expensive to train, but they often cannot achieve the accuracy of large models. In this paper, we explore an intriguing idea to connect these two different regimes: Can we develop a method to initialize large language models using smaller pre-trained models? Will such initialization bring any benefits in terms of training time and final accuracy? In this paper, we introduce HyperCloning, a method that can expand the parameters of a pre-trained language model to those of a larger model with increased hidden dimensions. Our method ensures that the larger model retains the functionality of the smaller model. As a result, the larger model already inherits the predictive power and accuracy of the smaller model before the training starts. We demonstrate that training such an initialized model results in significant savings in terms of GPU hours required for pre-training large language models.

arXiv:2409.12403

Preference Alignment Improves Language Model-Based TTS

Recent advancements in text-to-speech (TTS) have shown that language model (LM)-based systems offer competitive performance to their counterparts. Further optimization can be achieved through preference alignment algorithms, which adjust LMs to align with the preferences of reward models, enhancing the desirability of the generated content. This study presents a thorough empirical evaluation of how preference alignment algorithms, particularly Direct Preference Optimization (DPO), enhance LM-based TTS. With a 1.15B parameter LM-based TTS model, we demonstrate that preference alignment consistently improves intelligibility, speaker similarity, and proxy subjective evaluation scores, with the latter two metrics surpassing even human speech in certain evaluations. We also show preference alignment is applicable to low-resource scenarios and effectively generalized to out-of-domain applications.

arXiv:2409.11145공식 코드 · Papers with Code

High-Resolution Speech Restoration with Latent Diffusion Model

Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and high-frequency harmonics, leading to breathing and gasping artifacts that reduce the intelligibility of reconstructed speech. These models are also computationally demanding, and many solutions are restricted to producing outputs in the wide-band frequency range, which limits their suitability for professional applications. To address these challenges, we propose Hi-ResLDM, a novel generative model based on latent diffusion designed to remove multiple distortions and restore speech recordings to studio quality, sampled at 48kHz. We benchmark Hi-ResLDM against state-of-the-art methods that leverage GAN and Conditional Flow Matching (CFM) components, demonstrating superior performance in regenerating high-frequency-band details. Hi-ResLDM not only excels in non-instrusive metrics but is also consistently preferred in human evaluation and performs competitively on intrusive evaluations, making it ideal for high-resolution speech restoration.

arXiv:2409.10585

Motion Forecasting via Model-Based Risk Minimization

Forecasting the future trajectories of surrounding agents is crucial for autonomous vehicles to ensure safe, efficient, and comfortable route planning. While model ensembling has improved prediction accuracy in various fields, its application in trajectory prediction is limited due to the multi-modal nature of predictions. In this paper, we propose a novel sampling method applicable to trajectory prediction based on the predictions of multiple models. We first show that conventional sampling based on predicted probabilities can degrade performance due to missing alignment between models. To address this problem, we introduce a new method that generates optimal trajectories from a set of neural networks, framing it as a risk minimization problem with a variable loss function. By using state-of-the-art models as base learners, our approach constructs diverse and effective ensembles for optimal trajectory sampling. Extensive experiments on the nuScenes prediction dataset demonstrate that our method surpasses current state-of-the-art techniques, achieving top ranks on the leaderboard. We also provide a comprehensive empirical study on ensembling strategies, offering insights into their effectiveness. Our findings highlight the potential of advanced ensembling techniques in trajectory prediction, significantly improving predictive performance and paving the way for more reliable predicted trajectories.

arXiv:2409.11356

RenderWorld: World Model with Self-Supervised 3D Label

End-to-end autonomous driving with vision-only is not only more cost-effective compared to LiDAR-vision fusion but also more reliable than traditional methods. To achieve a economical and robust purely visual autonomous driving system, we propose RenderWorld, a vision-only end-to-end autonomous driving framework, which generates 3D occupancy labels using a self-supervised gaussian-based Img2Occ Module, then encodes the labels by AM-VAE, and uses world model for forecasting and planning. RenderWorld employs Gaussian Splatting to represent 3D scenes and render 2D images greatly improves segmentation accuracy and reduces GPU memory consumption compared with NeRF-based methods. By applying AM-VAE to encode air and non-air separately, RenderWorld achieves more fine-grained scene element representation, leading to state-of-the-art performance in both 4D occupancy forecasting and motion planning from autoregressive world model.

arXiv:2409.10431

Hippocampal synchronization in a realistic CA1 neuron model

This work delves into studying the synchronization in two realistic neuron models using Hodgkin-Huxley dynamics. Unlike simplistic point-like models, excitatory synapses are here randomly distributed along the dendrites, introducing strong stochastic contributions into their signal propagation. To focus on the role of different excitatory positions, we use two copies of the same neuron whose synapses are located at different distances from the soma and are exposed to identical Poissonian distributed current pulses. The synchronization is investigated through a specifically defined spiking correlation function, and its behavior is analyzed as a function of several parameters: inhibition weight, distance from the soma of one synaptic group, excitatory inactivation delay, and weight of the excitatory synapses.

arXiv:2409.09818

Revisiting the state-space model of unawareness

We propose a knowledge operator based on the agent's possibility correspondence which preserves her non-trivial unawareness within the standard state-space model. Our approach may provide a solution to the classical impossibility result that 'an unaware agent must be aware of everything'.

arXiv:2409.08347

Sensitivity analysis of the perturbed utility stochastic traffic equilibrium

This paper develops a novel sensitivity analysis framework for the perturbed utility route choice (PURC) model and the accompanying stochastic traffic equilibrium model. We provide general results that determine the marginal change in link flows following a marginal change in link costs across the network in the cases of flow-independent and flow-dependent link costs. We derive analytical sensitivity expressions for the Jacobian of the individual optimal PURC flow and equilibrium link flows with respect to link cost parameters under mild differentiability assumptions. Numerical examples illustrate the robustness of our method, demonstrating its use for estimating equilibrium link flows after link cost shifts, identifying critical design parameters, and quantifying uncertainty in performance predictions. The findings have implications for network design, pricing strategies, and policy analysis in transportation planning and economics, providing a bridge between theoretical models and real-world applications.

arXiv:2409.10215

Synchronization-Based Cooperative Distributed Model Predictive Control

Distributed control algorithms are known to reduce overall computation time compared to centralized control algorithms. However, they can result in inconsistent solutions leading to the violation of safety-critical constraints. Inconsistent solutions can arise when two or more agents compute concurrently while making predictions on each others control actions. To address this issue, we propose an iterative algorithm called Synchronization-Based Cooperative Distributed Model Predictive Control, which we presented in [1]. The algorithm consists of two steps: 1. computing the optimal control inputs for each agent and 2. synchronizing the predicted states across all agents. We demonstrate the efficacy of our algorithm in the control of multiple small-scale vehicles in our Cyber-Physical Mobility Lab.

arXiv:2409.09076

A Dynamic Cooler Model for Cement Clinker Production

We present a 2D model for a grate belt cooler in the pyro-section of a cement plant. The model is formulated as an index-1 differential-algebraic equation (DAE) model based on first engineering principles. The model systematically integrates thermo-physical aspects, transport phenomena, reaction kinetics, mass and energy balances, and algebraic volume and energy relations. The model is used for dynamic simulation of the cooler and the paper provides dynamic and steady-state simulation results matching the expected behavior. The cooler model is one part of a full pyro-section model for dynamical simulations. The model can serve as a basis for the design of optimization and control systems towards improving energy efficiency and CO2 emission.

arXiv:2409.09674

Model Selection Through Model Sorting

We propose a novel approach to select the best model of the data. Based on the exclusive properties of the nested models, we find the most parsimonious model containing the risk minimizer predictor. We prove the existence of probable approximately correct (PAC) bounds on the difference of the minimum empirical risk of two successive nested models, called successive empirical excess risk (SEER). Based on these bounds, we propose a model order selection method called nested empirical risk (NER). By the sorted NER (S-NER) method to sort the models intelligently, the minimum risk decreases. We construct a test that predicts whether expanding the model decreases the minimum risk or not. With a high probability, the NER and S-NER choose the true model order and the most parsimonious model containing the risk minimizer predictor, respectively. We use S-NER model selection in the linear regression and show that, the S-NER method without any prior information can outperform the accuracy of feature sorting algorithms like orthogonal matching pursuit (OMP) that aided with prior knowledge of the true model order. Also, in the UCR data set, the NER method reduces the complexity of the classification of UCR datasets dramatically, with a negligible loss of accuracy.

arXiv:2409.10044공식 코드 · Papers with Code

Benchmarking Large Language Model Uncertainty for Prompt Optimization

Prompt optimization algorithms for Large Language Models (LLMs) excel in multi-step reasoning but still lack effective uncertainty estimation. This paper introduces a benchmark dataset to evaluate uncertainty metrics, focusing on Answer, Correctness, Aleatoric, and Epistemic Uncertainty. Through analysis of models like GPT-3.5-Turbo and Meta-Llama-3.1-8B-Instruct, we show that current metrics align more with Answer Uncertainty, which reflects output confidence and diversity, rather than Correctness Uncertainty, highlighting the need for improved metrics that are optimization-objective-aware to better guide prompt optimization. Our code and dataset are available at https://github.com/0Frett/PO-Uncertainty-Benchmarking.

arXiv:2409.08907

Affective Computing Has Changed: The Foundation Model Disruption

The dawn of Foundation Models has on the one hand revolutionised a wide range of research problems, and, on the other hand, democratised the access and use of AI-based tools by the general public. We even observe an incursion of these models into disciplines related to human psychology, such as the Affective Computing domain, suggesting their affective, emerging capabilities. In this work, we aim to raise awareness of the power of Foundation Models in the field of Affective Computing by synthetically generating and analysing multimodal affective data, focusing on vision, linguistics, and speech (acoustics). We also discuss some fundamental problems, such as ethical issues and regulatory aspects, related to the use of Foundation Models in this research area.

arXiv:2409.04378

An MPEC Estimator for the Sequential Search Model

This paper proposes a constrained maximum likelihood estimator for sequential search models, using the MPEC (Mathematical Programming with Equilibrium Constraints) approach. This method enhances numerical accuracy while avoiding ad hoc components and errors related to equilibrium conditions. Monte Carlo simulations show that the estimator performs better in small samples, with lower bias and root-mean-squared error, though less effectively in large samples. Despite these mixed results, the MPEC approach remains valuable for identifying candidate parameters comparable to the benchmark, without relying on ad hoc look-up tables, as it generates the table through solved equilibrium constraints.