PyTorchKR Papers

최신 논문

총 4,899편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2412.07114

TT-MPD: Test Time Model Pruning and Distillation

Pruning can be an effective method of compressing large pre-trained models for inference speed acceleration. Previous pruning approaches rely on access to the original training dataset for both pruning and subsequent fine-tuning. However, access to the training data can be limited due to concerns such as data privacy and commercial confidentiality. Furthermore, with covariate shift (disparities between test and training data distributions), pruning and finetuning with training datasets can hinder the generalization of the pruned model to test data. To address these issues, pruning and finetuning the model with test time samples becomes essential. However, test-time model pruning and fine-tuning incur additional computation costs and slow down the model's prediction speed, thus posing efficiency issues. Existing pruning methods are not efficient enough for test time model pruning setting, since finetuning the pruned model is needed to evaluate the importance of removable components. To address this, we propose two variables to approximate the fine-tuned accuracy. We then introduce an efficient pruning method that considers the approximated finetuned accuracy and potential inference latency saving. To enhance fine-tuning efficiency, we propose an efficient knowledge distillation method that only needs to generate pseudo labels for a small set of finetuning samples one time, thereby reducing the expensive pseudo-label generation cost. Experimental results demonstrate that our method achieves a comparable or superior tradeoff between test accuracy and inference latency, with a 32% relative reduction in pruning and finetuning time compared to the best existing method.

arXiv:2412.07112공식 코드 · Papers with Code

Maya: An Instruction Finetuned Multilingual Multimodal Model

The rapid development of large Vision-Language Models (VLMs) has led to impressive results on academic benchmarks, primarily in widely spoken languages. However, significant gaps remain in the ability of current VLMs to handle low-resource languages and varied cultural contexts, largely due to a lack of high-quality, diverse, and safety-vetted data. Consequently, these models often struggle to understand low-resource languages and cultural nuances in a manner free from toxicity. To address these limitations, we introduce Maya, an open-source Multimodal Multilingual model. Our contributions are threefold: 1) a multilingual image-text pretraining dataset in eight languages, based on the LLaVA pretraining dataset; 2) a thorough analysis of toxicity within the LLaVA dataset, followed by the creation of a novel toxicity-free version across eight languages; and 3) a multilingual image-text model supporting these languages, enhancing cultural and linguistic comprehension in vision-language tasks. Code available at https://github.com/nahidalam/maya.

arXiv:2412.07446공식 코드 · Papers with Code

A Causal World Model Underlying Next Token Prediction: Exploring GPT in a Controlled Environment

Do generative pre-trained transformer (GPT) models, trained only to predict the next token, implicitly learn a world model from which a sequence is generated one token at a time? We address this question by deriving a causal interpretation of the attention mechanism in GPT, and suggesting a causal world model that arises from this interpretation. Furthermore, we propose that GPT models, at inference time, can be utilized for zero-shot causal structure learning for input sequences and present a confidence score. Empirical evaluation is conducted in a controlled environment using the setup and rules of the Othello and Chess strategy games. A GPT, pre-trained on real-world games played with the intention of winning, is tested on out-of-distribution synthetic data consisting of sequences of random legal moves. We find that the GPT model is likely to generate legal next moves for out-of-distribution sequences for which a causal structure is encoded in the attention mechanism with high confidence. In cases for which the GPT model generates illegal moves it also fails to capture any causal structure.

arXiv:2412.07213공식 코드 · Papers with Code

IntellectSeeker: A Personalized Literature Management System with the Probabilistic Model and Large Language Model

Faced with the burgeoning volume of academic literature, researchers often need help with uncertain article quality and mismatches in term searches using traditional academic engines. We introduce IntellectSeeker, an innovative and personalized intelligent academic literature management platform to address these challenges. This platform integrates a Large Language Model (LLM)--based semantic enhancement bot with a sophisticated probability model to personalize and streamline literature searches. We adopted the GPT-3.5-turbo model to transform everyday language into professional academic terms across various scenarios using multiple rounds of few-shot learning. This adaptation mainly benefits academic newcomers, effectively bridging the gap between general inquiries and academic terminology. The probabilistic model intelligently filters academic articles to align closely with the specific interests of users, which are derived from explicit needs and behavioral patterns. Moreover, IntellectSeeker incorporates an advanced recommendation system and text compression tools. These features enable intelligent article recommendations based on user interactions and present search results through concise one-line summaries and innovative word cloud visualizations, significantly enhancing research efficiency and user experience. IntellectSeeker offers academic researchers a highly customizable literature management solution with exceptional search precision and matching capabilities. The code can be found here: https://github.com/LuckyBian/ISY5001

arXiv:2412.05675공식 코드 · Papers with Code

M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model

Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, we propose using Model Predictive Control (MPC) at test time to leverage the model's own predictive capability to guide its action selection. Empirical results on D4RL and RoboMimic show that our inference-phase MPC significantly improves the decision-making performance of a pretrained trajectory model without any additional parameter training. Furthermore, our framework can be adapted to Offline to Online (O2O) RL and Goal Reaching RL, resulting in more substantial performance gains when an additional online interaction budget is provided, and better generalization capabilities when different task targets are specified. Code is available: https://github.com/wkh923/m3pc.

arXiv:2412.06619공식 코드 · Papers with Code

Copyright-Protected Language Generation via Adaptive Model Fusion

The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown promise in addressing the complexities of copyright regulation. However, they often incur prohibitive computational costs or suffer from performance trade-offs. To overcome these limitations, we introduce Copyright-Protecting Model Fusion (CP-Fuse), a novel approach that combines models trained on disjoint sets of copyrighted material during inference. In particular, CP-Fuse adaptively aggregates the model outputs to minimize the reproduction of copyrighted content, adhering to a crucial balancing property that prevents the regurgitation of memorized data. Through extensive experiments, we show that CP-Fuse significantly reduces the reproduction of protected material without compromising the quality of text and code generation. Moreover, its post-hoc nature allows seamless integration with other protective measures, further enhancing copyright safeguards. Lastly, we show that CP-Fuse is robust against common techniques for extracting training data.

arXiv:2412.05633

Efficient Continuous Video Flow Model for Video Prediction

Multi-step prediction models, such as diffusion and rectified flow models, have emerged as state-of-the-art solutions for generation tasks. However, these models exhibit higher latency in sampling new frames compared to single-step methods. This latency issue becomes a significant bottleneck when adapting such methods for video prediction tasks, given that a typical 60-second video comprises approximately 1.5K frames. In this paper, we propose a novel approach to modeling the multi-step process, aimed at alleviating latency constraints and facilitating the adaptation of such processes for video prediction tasks. Our approach not only reduces the number of sample steps required to predict the next frame but also minimizes computational demands by reducing the model size to one-third of the original size. We evaluate our method on standard video prediction datasets, including KTH, BAIR action robot, Human3.6M and UCF101, demonstrating its efficacy in achieving state-of-the-art performance on these benchmarks.

arXiv:2412.06418공식 코드 · Papers with Code

Continual Learning for Segment Anything Model Adaptation

Although the current different types of SAM adaptation methods have achieved promising performance for various downstream tasks, such as prompt-based ones and adapter-based ones, most of them belong to the one-step adaptation paradigm. In real-world scenarios, we are generally confronted with the dynamic scenario where the data comes in a streaming manner. Driven by the practical need, in this paper, we first propose a novel Continual SAM adaptation (CoSAM) benchmark with 8 different task domains and carefully analyze the limitations of the existing SAM one-step adaptation methods in the continual segmentation scenario. Then we propose a novel simple-yet-effective Mixture of Domain Adapters (MoDA) algorithm which utilizes the Global Feature Tokens (GFT) and Global Assistant Tokens (GAT) modules to help the SAM encoder extract well-separated features for different task domains, and then provide the accurate task-specific information for continual learning. Extensive experiments demonstrate that our proposed MoDA obviously surpasses the existing classic continual learning methods, as well as prompt-based and adapter-based approaches for continual segmentation. Moreover, after sequential learning on the CoSAM benchmark with diverse data distributions, our MoDA maintains highly competitive results in the natural image domain, approaching the zero-shot performance of the original SAM, demonstrating its superior capability in knowledge preservation. Notably, the proposed MoDA can be seamlessly integrated into various one-step adaptation methods of SAM, which can consistently bring obvious performance gains. Code is available at \url{https://github.com/yangjl1215/CoSAM}

arXiv:2412.06295

See Further When Clear: Curriculum Consistency Model

Significant advances have been made in the sampling efficiency of diffusion models and flow matching models, driven by Consistency Distillation (CD), which trains a student model to mimic the output of a teacher model at a later timestep. However, we found that the learning complexity of the student model varies significantly across different timesteps, leading to suboptimal performance in CD.To address this issue, we propose the Curriculum Consistency Model (CCM), which stabilizes and balances the learning complexity across timesteps. Specifically, we regard the distillation process at each timestep as a curriculum and introduce a metric based on Peak Signal-to-Noise Ratio (PSNR) to quantify the learning complexity of this curriculum, then ensure that the curriculum maintains consistent learning complexity across different timesteps by having the teacher model iterate more steps when the noise intensity is low. Our method achieves competitive single-step sampling Fr\'echet Inception Distance (FID) scores of 1.64 on CIFAR-10 and 2.18 on ImageNet 64x64.Moreover, we have extended our method to large-scale text-to-image models and confirmed that it generalizes well to both diffusion models (Stable Diffusion XL) and flow matching models (Stable Diffusion 3). The generated samples demonstrate improved image-text alignment and semantic structure, since CCM enlarges the distillation step at large timesteps and reduces the accumulated error.

arXiv:2412.05983

Chimera: Improving Generalist Model with Domain-Specific Experts

Recent advancements in Large Multi-modal Models (LMMs) underscore the importance of scaling by increasing image-text paired data, achieving impressive performance on general tasks. Despite their effectiveness in broad applications, generalist models are primarily trained on web-scale datasets dominated by natural images, resulting in the sacrifice of specialized capabilities for domain-specific tasks that require extensive domain prior knowledge. Moreover, directly integrating expert models tailored for specific domains is challenging due to the representational gap and imbalanced optimization between the generalist model and experts. To address these challenges, we introduce Chimera, a scalable and low-cost multi-modal pipeline designed to boost the ability of existing LMMs with domain-specific experts. Specifically, we design a progressive training strategy to integrate features from expert models into the input of a generalist LMM. To address the imbalanced optimization caused by the well-aligned general visual encoder, we introduce a novel Generalist-Specialist Collaboration Masking (GSCM) mechanism. This results in a versatile model that excels across the chart, table, math, and document domains, achieving state-of-the-art performance on multi-modal reasoning and visual content extraction tasks, both of which are challenging tasks for assessing existing LMMs.

arXiv:2412.06674공식 코드 · Papers with Code

EMOv2: Pushing 5M Vision Model Frontier

This work focuses on developing parameter-efficient and lightweight models for dense predictions while trading off parameters, FLOPs, and performance. Our goal is to set up the new frontier of the 5M magnitude lightweight model on various downstream tasks. Inverted Residual Block (IRB) serves as the infrastructure for lightweight CNNs, but no counterparts have been recognized by attention-based design. Our work rethinks the lightweight infrastructure of efficient IRB and practical components in Transformer from a unified perspective, extending CNN-based IRB to attention-based models and abstracting a one-residual Meta Mobile Block (MMBlock) for lightweight model design. Following neat but effective design criterion, we deduce a modern Improved Inverted Residual Mobile Block (i2RMB) and improve a hierarchical Efficient MOdel (EMOv2) with no elaborate complex structures. Considering the imperceptible latency for mobile users when downloading models under 4G/5G bandwidth and ensuring model performance, we investigate the performance upper limit of lightweight models with a magnitude of 5M. Extensive experiments on various vision recognition, dense prediction, and image generation tasks demonstrate the superiority of our EMOv2 over state-of-the-art methods, e.g., EMOv2-1M/2M/5M achieve 72.3, 75.8, and 79.4 Top-1 that surpass equal-order CNN-/Attention-based models significantly. At the same time, EMOv2-5M equipped RetinaNet achieves 41.5 mAP for object detection tasks that surpasses the previous EMO-5M by +2.6. When employing the more robust training recipe, our EMOv2-5M eventually achieves 82.9 Top-1 accuracy, which elevates the performance of 5M magnitude models to a new level. Code is available at https://github.com/zhangzjn/EMOv2.

arXiv:2412.04785공식 코드 · Papers with Code

Differentially Private Random Feature Model

Designing privacy-preserving machine learning algorithms has received great attention in recent years, especially in the setting when the data contains sensitive information. Differential privacy (DP) is a widely used mechanism for data analysis with privacy guarantees. In this paper, we produce a differentially private random feature model. Random features, which were proposed to approximate large-scale kernel machines, have been used to study privacy-preserving kernel machines as well. We consider the over-parametrized regime (more features than samples) where the non-private random feature model is learned via solving the min-norm interpolation problem, and then we apply output perturbation techniques to produce a private model. We show that our method preserves privacy and derive a generalization error bound for the method. To the best of our knowledge, we are the first to consider privacy-preserving random feature models in the over-parametrized regime and provide theoretical guarantees. We empirically compare our method with other privacy-preserving learning methods in the literature as well. Our results show that our approach is superior to the other methods in terms of generalization performance on synthetic data and benchmark data sets. Additionally, it was recently observed that DP mechanisms may exhibit and exacerbate disparate impact, which means that the outcomes of DP learning algorithms vary significantly among different groups. We show that both theoretically and empirically, random features have the potential to reduce disparate impact, and hence achieve better fairness.

arXiv:2412.04657

An Efficient Model Maintenance Approach for MLOps

In recent years, many industries have utilized machine learning (ML) models in their systems. Ideally, ML models should be trained on and applied to data from the same distributions. However, the data evolves over time in many application areas, leading to concept drift, which in turn causes the performance of the ML models to degrade over time. Therefore, maintaining up-to-date ML models plays a critical role in the MLOps pipeline. Existing ML model maintenance approaches are often computationally resource-intensive, costly, time-consuming, and model-dependent. Thus, we propose an improved MLOps pipeline, a new model maintenance approach and a Similarity-Based Model Reuse (SimReuse) tool to address the challenges of ML model maintenance. We identify seasonal and recurrent data distribution patterns in time series datasets throughout a preliminary study. Recurrent data distribution patterns enable us to reuse previously trained models for similar distributions in the future, thus avoiding frequent unnecessary retrainings. Then, we integrated the model reuse approach into the MLOps pipeline and proposed our improved MLOps pipeline. Furthermore, we develop SimReuse, a tool to implement the new components of our MLOps pipeline to store models and reuse them for inference of data segments with similar data distributions in the future. Our evaluation results on five time series datasets demonstrate that our model reuse approach can maintain the models' performance while significantly reducing maintenance time, costs, and the number of retrainings. Our model reuse approach achieves ML model performance comparable to the best baselines, while reducing the computation time and costs to 1/8th. Therefore, industries and practitioners can benefit from our approach and use our tool to maintain their ML models' performance in the deployment phase to reduce their maintenance time and costs.

arXiv:2412.04692공식 코드 · Papers with Code

Smoothie: Label Free Language Model Routing

Large language models (LLMs) are increasingly used in applications where LLM inputs may span many different tasks. Recent work has found that the choice of LLM is consequential, and different LLMs may be good for different input samples. Prior approaches have thus explored how engineers might select an LLM to use for each sample (i.e. routing). While existing routing methods mostly require training auxiliary models on human-annotated data, our work explores whether it is possible to perform unsupervised routing. We propose Smoothie, a weak supervision-inspired routing approach that requires no labeled data. Given a set of outputs from different LLMs, Smoothie constructs a latent variable graphical model over embedding representations of observable LLM outputs and unknown "true" outputs. Using this graphical model, we estimate sample-dependent quality scores for each LLM, and route each sample to the LLM with the highest corresponding score. We find that Smoothie's LLM quality-scores correlate with ground-truth model quality (correctly identifying the optimal model on 9/14 tasks), and that Smoothie outperforms baselines for routing by up to 10 points accuracy.

arXiv:2412.04242

LMDM:Latent Molecular Diffusion Model For 3D Molecule Generation

n this work, we propose a latent molecular diffusion model that can make the generated 3D molecules rich in diversity and maintain rich geometric features. The model captures the information of the forces and local constraints between atoms so that the generated molecules can maintain Euclidean transformation and high level of effectiveness and diversity. We also use the lowerrank manifold advantage of the latent variables of the latent model to fuse the information of the forces between atoms to better maintain the geometric equivariant properties of the molecules. Because there is no need to perform information fusion encoding in stages like traditional encoders and decoders, this reduces the amount of calculation in the back-propagation process. The model keeps the forces and local constraints of particle bonds in the latent variable space, reducing the impact of underfitting on the surface of the network on the large position drift of the particle geometry, so that our model can converge earlier. We introduce a distribution control variable in each backward step to strengthen exploration and improve the diversity of generation. In the experiment, the quality of the samples we generated and the convergence speed of the model have been significantly improved.

arXiv:2412.04092

GEITje 7B Ultra: A Conversational Model for Dutch

Language models have rapidly evolved, predominantly focusing on English while often neglecting extensive pretraining in other languages. This approach has required initiatives to adapt powerful, English-centric models to other linguistic contexts through finetuning. For Dutch, such a recent endeavour is ``GEITje'' a model originally derived from the English-based Mistral 7B. Building on this fundamental work, the current research extends the capabilities of GEITje by supervised finetuning on newly created high-quality synthetic conversational datasets, along with an additional preference alignment procedure on a synthetic feedback dataset. Both the developed models and the created datasets are openly available.

arXiv:2412.03780

Community Detection with Heterogeneous Block Covariance Model

Community detection is the task of clustering objects based on their pairwise relationships. Most of the model-based community detection methods, such as the stochastic block model and its variants, are designed for networks with binary (yes/no) edges. In many practical scenarios, edges often possess continuous weights, spanning positive and negative values, which reflect varying levels of connectivity. To address this challenge, we introduce the heterogeneous block covariance model (HBCM) that defines a community structure within the covariance matrix, where edges have signed and continuous weights. Furthermore, it takes into account the heterogeneity of objects when forming connections with other objects within a community. A novel variational expectation-maximization algorithm is proposed to estimate the group membership. The HBCM provides provable consistent estimates of memberships, and its promising performance is observed in numerical simulations with different setups. The model is applied to a single-cell RNA-seq dataset of a mouse embryo and a stock price dataset. Supplementary materials for this article are available online.

arXiv:2412.03134

Generalized Diffusion Model with Adjusted Offset Noise

Diffusion models have become fundamental tools for modeling data distributions in machine learning and have applications in image generation, drug discovery, and audio synthesis. Despite their success, these models face challenges when generating data with extreme brightness values, as evidenced by limitations in widely used frameworks like Stable Diffusion. Offset noise has been proposed as an empirical solution to this issue, yet its theoretical basis remains insufficiently explored. In this paper, we propose a generalized diffusion model that naturally incorporates additional noise within a rigorous probabilistic framework. Our approach modifies both the forward and reverse diffusion processes, enabling inputs to be diffused into Gaussian distributions with arbitrary mean structures. We derive a loss function based on the evidence lower bound, establishing its theoretical equivalence to offset noise with certain adjustments, while broadening its applicability. Experiments on synthetic datasets demonstrate that our model effectively addresses brightness-related challenges and outperforms conventional methods in high-dimensional scenarios.

arXiv:2412.02900공식 코드 · Papers with Code

MACAW: A Causal Generative Model for Medical Imaging

Although deep learning techniques show promising results for many neuroimaging tasks in research settings, they have not yet found widespread use in clinical scenarios. One of the reasons for this problem is that many machine learning models only identify correlations between the input images and the outputs of interest, which can lead to many practical problems, such as encoding of uninformative biases and reduced explainability. Thus, recent research is exploring if integrating a priori causal knowledge into deep learning models is a potential avenue to identify these problems. This work introduces a new causal generative architecture named Masked Causal Flow (MACAW) for neuroimaging applications. Within this context, three main contributions are described. First, a novel approach that integrates complex causal structures into normalizing flows is proposed. Second, counterfactual prediction is performed to identify the changes in effect variables associated with a cause variable. Finally, an explicit Bayesian inference for classification is derived and implemented, providing an inherent uncertainty estimation. The feasibility of the proposed method was first evaluated using synthetic data and then using MRI brain data from more than 23000 participants of the UK biobank study. The evaluation results show that the proposed method can (1) accurately encode causal reasoning and generate counterfactuals highlighting the structural changes in the brain known to be associated with aging, (2) accurately predict a subject's age from a single 2D MRI slice, and (3) generate new samples assuming other values for subject-specific indicators such as age, sex, and body mass index. The code for a toy dataset is available at the following link: https://github.com/vibujithan/macaw-2D.git.

arXiv:2406.10269

Markov Constraint as Large Language Model Surrogate

This paper presents NgramMarkov, a variant of the Markov constraints. It is dedicated to text generation in constraint programming (CP). It involves a set of n-grams (i.e., sequence of n words) associated with probabilities given by a large language model (LLM). It limits the product of the probabilities of the n-gram of a sentence. The propagator of this constraint can be seen as an extension of the ElementaryMarkov constraint propagator, incorporating the LLM distribution instead of the maximum likelihood estimation of n-grams. It uses a gliding threshold, i.e., it rejects n-grams whose local probabilities are too low, to guarantee balanced solutions. It can also be combined with a "look-ahead" approach to remove n-grams that are very unlikely to lead to acceptable sentences for a fixed-length horizon. This idea is based on the MDDMarkovProcess constraint propagator, but without explicitly using an MDD (Multi-Valued Decision Diagram). The experimental results show that the generated text is valued in a similar way to the LLM perplexity function. Using this new constraint dramatically reduces the number of candidate sentences produced, improves computation times, and allows larger corpora or smaller n-grams to be used. A real-world problem has been solved for the first time using 4-grams instead of 5-grams.