Modeling temporal characteristics plays a significant role in the representation learning of audio waveform. We propose Contrastive Long-form Language-Audio Pretraining (\textbf{CoLLAP}) to significantly extend the perception window for both the input audio (up to 5 minutes) and the language descriptions (exceeding 250 words), while enabling contrastive learning across modalities and temporal dynamics. Leveraging recent Music-LLMs to generate long-form music captions for full-length songs, augmented with musical temporal structures, we collect 51.3K audio-text pairs derived from the large-scale AudioSet training dataset, where the average audio length reaches 288 seconds. We propose a novel contrastive learning architecture that fuses language representations with structured audio representations by segmenting each song into clips and extracting their embeddings. With an attention mechanism, we capture multimodal temporal correlations, allowing the model to automatically weigh and enhance the final fusion score for improved contrastive alignment. Finally, we develop two variants of the CoLLAP model with different types of backbone language models. Through comprehensive experiments on multiple long-form music-text retrieval datasets, we demonstrate consistent performance improvement in retrieval accuracy compared with baselines. We also show the pretrained CoLLAP models can be transferred to various music information retrieval tasks, with heterogeneous long-form multimodal contexts.
Forecasting faithful trajectories of multivariate time series from practical scopes is essential for reasonable decision-making. Recent methods majorly tailor generative conditional diffusion models to estimate the target temporal predictive distribution. However, it remains an obstacle to enhance the exploitation efficiency of given implicit temporal predictive information to bolster conditional diffusion learning. To this end, we propose a generic channel-aware Contrastive Conditional Diffusion model entitled CCDM to achieve desirable Multivariate probabilistic forecasting, obviating the need for curated temporal conditioning inductive biases. In detail, we first design a channel-centric conditional denoising network to manage intra-variate variations and cross-variate correlations, which can lead to scalability on diverse prediction horizons and channel numbers. Then, we devise an ad-hoc denoising-based temporal contrastive learning to explicitly amplify the predictive mutual information between past observations and future forecasts. It can coherently complement naive step-wise denoising diffusion training and improve the forecasting accuracy and generality on unknown test time series. Besides, we offer theoretic insights on the benefits of such auxiliary contrastive training refinement from both neural mutual information and temporal distribution generalization aspects. The proposed CCDM can exhibit superior forecasting capability compared to current state-of-the-art diffusion forecasters over a comprehensive benchmark, with best MSE and CRPS outcomes on $66.67\%$ and $83.33\%$ cases. Our code is publicly available at https://github.com/LSY-Cython/CCDM.
Audio-text models trained via contrastive learning offer a practical approach to perform audio classification through natural language prompts, such as "this is a sound of" followed by category names. In this work, we explore alternative prompt templates for zero-shot audio classification, demonstrating the existence of higher-performing options. First, we find that the formatting of the prompts significantly affects performance so that simply prompting the models with properly formatted class labels performs competitively with optimized prompt templates and even prompt ensembling. Moreover, we look into complementing class labels by audio-centric descriptions. By leveraging large language models, we generate textual descriptions that prioritize acoustic features of sound events to disambiguate between classes, without extensive prompt engineering. We show that prompting with class descriptions leads to state-of-the-art results in zero-shot audio classification across major ambient sound datasets. Remarkably, this method requires no additional training and remains fully zero-shot.
The creation of manufacturable and editable 3D shapes through Computer-Aided Design (CAD) remains a highly manual and time-consuming task, hampered by the complex topology of boundary representations of 3D solids and unintuitive design tools. While most work in the 3D shape generation literature focuses on representations like meshes, voxels, or point clouds, practical engineering applications demand the modifiability and manufacturability of CAD models and the ability for multi-modal conditional CAD model generation. This paper introduces GenCAD, a generative model that employs autoregressive transformers with a contrastive learning framework and latent diffusion models to transform image inputs into parametric CAD command sequences, resulting in editable 3D shape representations. Extensive evaluations demonstrate that GenCAD significantly outperforms existing state-of-the-art methods in terms of the unconditional and conditional generations of CAD models. Additionally, the contrastive learning framework of GenCAD facilitates the retrieval of CAD models using image queries from large CAD databases, which is a critical challenge within the CAD community. Our results provide a significant step forward in highlighting the potential of generative models to expedite the entire design-to-production pipeline and seamlessly integrate different design modalities.
Automatic synthesis of analog circuits presents significant challenges. Existing methods usually treat the task as optimization problems, which limits their transferability and reusability for new requirements. To address this limitation, we introduce a task that directly generates analog circuits based on specified specifications, termed specification-conditioned analog circuit generation. Specifically, we propose CktGen, a simple yet effective variational autoencoder (VAE) model, that maps specifications and circuits into a joint latent space, and reconstructs the circuit from the latent. Moreover, given that a single specification can correspond to multiple distinct circuits, simply minimizing the distance between the mapped latent representations of the circuit and specification does not capture these one-to-many relationships. To address this, we integrate contrastive learning and classifier guidance to prevent model collapse. We conduct comprehensive experiments on the Open Circuit Benchmark (OCB) and introduce new evaluation metrics for cross-model consistency in the specification-to-circuit generation task. Experimental results demonstrate substantial improvements over existing state-of-the-art methods.
NECOMIMI (NEural-COgnitive MultImodal EEG-Informed Image Generation with Diffusion Models) introduces a novel framework for generating images directly from EEG signals using advanced diffusion models. Unlike previous works that focused solely on EEG-image classification through contrastive learning, NECOMIMI extends this task to image generation. The proposed NERV EEG encoder demonstrates state-of-the-art (SoTA) performance across multiple zero-shot classification tasks, including 2-way, 4-way, and 200-way, and achieves top results in our newly proposed Category-based Assessment Table (CAT) Score, which evaluates the quality of EEG-generated images based on semantic concepts. A key discovery of this work is that the model tends to generate abstract or generalized images, such as landscapes, rather than specific objects, highlighting the inherent challenges of translating noisy and low-resolution EEG data into detailed visual outputs. Additionally, we introduce the CAT Score as a new metric tailored for EEG-to-image evaluation and establish a benchmark on the ThingsEEG dataset. This study underscores the potential of EEG-to-image generation while revealing the complexities and challenges that remain in bridging neural activity with visual representation.
Knowledge tracing (KT) is a popular approach for modeling students' learning progress over time, which can enable more personalized and adaptive learning. However, existing KT approaches face two major limitations: (1) they rely heavily on expert-defined knowledge concepts (KCs) in questions, which is time-consuming and prone to errors; and (2) KT methods tend to overlook the semantics of both questions and the given KCs. In this work, we address these challenges and present KCQRL, a framework for automated knowledge concept annotation and question representation learning that can improve the effectiveness of any existing KT model. First, we propose an automated KC annotation process using large language models (LLMs), which generates question solutions and then annotates KCs in each solution step of the questions. Second, we introduce a contrastive learning approach to generate semantically rich embeddings for questions and solution steps, aligning them with their associated KCs via a tailored false negative elimination approach. These embeddings can be readily integrated into existing KT models, replacing their randomly initialized embeddings. We demonstrate the effectiveness of KCQRL across 15 KT algorithms on two large real-world Math learning datasets, where we achieve consistent performance improvements.
Accurately identifying, understanding and describing traffic safety-critical events (SCEs), including crashes, tire strikes, and near-crashes, is crucial for advanced driver assistance systems, automated driving systems, and traffic safety. As SCEs are rare events, most general vision-language models (VLMs) have not been trained sufficiently to link SCE videos and narratives, which could lead to hallucinations and missing key safety characteristics. Here, we introduce ScVLM, a novel hybrid methodology that integrates supervised and contrastive learning techniques to classify the severity and types of SCEs, as well as to generate narrative descriptions of SCEs. This approach utilizes classification to enhance VLMs' comprehension of driving videos and improve the rationality of event descriptions. The proposed approach is trained on and evaluated by more than 8,600 SCEs from the Second Strategic Highway Research Program Naturalistic Driving Study dataset, the largest publicly accessible driving dataset with videos and SCE annotations. The results demonstrate the superiority of the proposed approach in generating contextually accurate event descriptions and mitigating VLM hallucinations. The code will be available at https://github.com/datadrivenwheels/ScVLM.
The scarcity of annotated medical images is a major bottleneck in developing learning models for medical image analysis. Hence, recent studies have focused on pretrained models with fewer annotation requirements that can be fine-tuned for various downstream tasks. However, existing approaches are mainly 3D adaptions of 2D approaches ill-suited for 3D medical imaging data. Motivated by this gap, we propose novel domain-aware multi-task learning tasks to pretrain a 3D Swin Transformer for brain magnetic resonance imaging (MRI). Our method considers the domain knowledge in brain MRI by incorporating brain anatomy and morphology as well as standard pretext tasks adapted for 3D imaging in a contrastive learning setting. We pretrain our model using large-scale brain MRI data of 13,687 samples spanning several large-scale databases. Our method outperforms existing supervised and self-supervised methods in three downstream tasks of Alzheimer's disease classification, Parkinson's disease classification, and age prediction tasks. The ablation study of the proposed pretext tasks shows the effectiveness of our pretext tasks.
Learning agents with reinforcement learning is difficult when dealing with long trajectories that involve a large number of states. To address these learning problems effectively, the number of states can be reduced by abstract representations that cluster states. In principle, deep reinforcement learning can find abstract states, but end-to-end learning is unstable. We propose contrastive abstraction learning to find abstract states, where we assume that successive states in a trajectory belong to the same abstract state. Such abstract states may be basic locations, achieved subgoals, inventory, or health conditions. Contrastive abstraction learning first constructs clusters of state representations by contrastive learning and then applies modern Hopfield networks to determine the abstract states. The first phase of contrastive abstraction learning is self-supervised learning, where contrastive learning forces states with sequential proximity to have similar representations. The second phase uses modern Hopfield networks to map similar state representations to the same fixed point, i.e.\ to an abstract state. The level of abstraction can be adjusted by determining the number of fixed points of the modern Hopfield network. Furthermore, \textit{contrastive abstraction learning} does not require rewards and facilitates efficient reinforcement learning for a wide range of downstream tasks. Our experiments demonstrate the effectiveness of contrastive abstraction learning for reinforcement learning.
X-ray image-based medical report generation (MRG) is a pivotal area in artificial intelligence which can significantly reduce diagnostic burdens and patient wait times. Despite significant progress, we believe that the task has reached a bottleneck due to the limited benchmark datasets and the existing large models' insufficient capability enhancements in this specialized domain. Specifically, the recently released CheXpert Plus dataset lacks comparative evaluation algorithms and their results, providing only the dataset itself. This situation makes the training, evaluation, and comparison of subsequent algorithms challenging. Thus, we conduct a comprehensive benchmarking of existing mainstream X-ray report generation models and large language models (LLMs), on the CheXpert Plus dataset. We believe that the proposed benchmark can provide a solid comparative basis for subsequent algorithms and serve as a guide for researchers to quickly grasp the state-of-the-art models in this field. More importantly, we propose a large model for the X-ray image report generation using a multi-stage pre-training strategy, including self-supervised autoregressive generation and Xray-report contrastive learning, and supervised fine-tuning. Extensive experimental results indicate that the autoregressive pre-training based on Mamba effectively encodes X-ray images, and the image-text contrastive pre-training further aligns the feature spaces, achieving better experimental results. Source code can be found on \url{https://github.com/Event-AHU/Medical_Image_Analysis}.
In the domain of recommendation and collaborative filtering, Graph Contrastive Learning (GCL) has become an influential approach. Nevertheless, the reasons for the effectiveness of contrastive learning are still not well understood. In this paper, we challenge the conventional use of random augmentations on graph structure or embedding space in GCL, which may disrupt the structural and semantic information inherent in Graph Neural Networks. Moreover, fixed-rate data augmentation proves to be less effective compared to augmentation with an adaptive rate. In the initial training phases, significant perturbations are more suitable, while as the training approaches convergence, milder perturbations yield better results. We introduce a twin encoder in place of random augmentations, demonstrating the redundancy of traditional augmentation techniques. The twin encoder updating mechanism ensures the generation of more diverse contrastive views in the early stages, transitioning to views with greater similarity as training progresses. In addition, we investigate the learned representations from the perspective of alignment and uniformity on a hypersphere to optimize more efficiently. Our proposed Twin Graph Contrastive Learning model -- TwinCL -- aligns positive pairs of user and item embeddings and the representations from the twin encoder while maintaining the uniformity of the embeddings on the hypersphere. Our theoretical analysis and experimental results show that the proposed model optimizing alignment and uniformity with the twin encoder contributes to better recommendation accuracy and training efficiency performance. In comprehensive experiments on three public datasets, our proposed TwinCL achieves an average improvement of 5.6% (NDCG@10) in recommendation accuracy with faster training speed, while effectively mitigating popularity bias.
The human visual system is capable of processing continuous streams of visual information, but how the brain encodes and retrieves recent visual memories during continuous visual processing remains unexplored. This study investigates the capacity of working memory to retain past information under continuous visual stimuli. And then we propose a new task Memory Disentangling, which aims to extract and decode past information from fMRI signals. To address the issue of interference from past memory information, we design a disentangled contrastive learning method inspired by the phenomenon of proactive interference. This method separates the information between adjacent fMRI signals into current and past components and decodes them into image descriptions. Experimental results demonstrate that this method effectively disentangles the information within fMRI signals. This research could advance brain-computer interfaces and mitigate the problem of low temporal resolution in fMRI.
Multimodal image-text contrastive learning has shown that joint representations can be learned across modalities. Here, we show how leveraging multiple views of image data with contrastive learning can improve downstream fine-grained classification performance for species recognition, even when one view is absent. We propose ContRastive Image-remote Sensing Pre-training (CRISP)$\unicode{x2014}$a new pre-training task for ground-level and aerial image representation learning of the natural world$\unicode{x2014}$and introduce Nature Multi-View (NMV), a dataset of natural world imagery including $>3$ million ground-level and aerial image pairs for over 6,000 plant taxa across the ecologically diverse state of California. The NMV dataset and accompanying material are available at hf.co/datasets/andyvhuynh/NatureMultiView.
Recent works show that assembling multiple off-the-shelf large language models (LLMs) can harness their complementary abilities. To achieve this, routing is a promising method, which learns a router to select the most suitable LLM for each query. However, existing routing models are ineffective when multiple LLMs perform well for a query. To address this problem, in this paper, we propose a method called query-based Router by Dual Contrastive learning (RouterDC). The RouterDC model consists of an encoder and LLM embeddings, and we propose two contrastive learning losses to train the RouterDC model. Experimental results show that RouterDC is effective in assembling LLMs and largely outperforms individual top-performing LLMs as well as existing routing methods on both in-distribution (+2.76\%) and out-of-distribution (+1.90\%) tasks. Source code is available at https://github.com/shuhao02/RouterDC.
Multimodal contrastive learning uses various data modalities to create high-quality features, but its reliance on extensive data sources on the Internet makes it vulnerable to backdoor attacks. These attacks insert malicious behaviors during training, which are activated by specific triggers during inference, posing significant security risks. Despite existing countermeasures through fine-tuning that reduce the malicious impacts of such attacks, these defenses frequently necessitate extensive training time and degrade clean accuracy. In this study, we propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities, known as Unlearn Backdoor Threats (UBT). We specifically use overfit training to improve backdoor shortcuts and accurately detect suspicious samples in the potential poisoning data set. Then, we select fewer unlearned samples from suspicious samples for rapid forgetting in order to eliminate the backdoor effect and thus improve backdoor defense efficiency. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime. This technique focuses on the model's compromised elements, dissociating backdoor correlations while maintaining the model's overall integrity. Extensive experimental results show that our method effectively defends against various backdoor attack methods in the CLIP model. Compared to SoTA backdoor defense methods, UBT achieves the lowest attack success rate while maintaining a high clean accuracy of the model (attack success rate decreases by 19% compared to SOTA, while clean accuracy increases by 2.57%).
Generative Adversarial Networks (GANs) have been at the forefront of image synthesis, especially in medical fields like histopathology, where they help address challenges such as data scarcity, patient privacy, and class imbalance. However, several inherent and domain-specific issues remain. For GANs, training instability, mode collapse, and insufficient feedback from binary classification can undermine performance. These challenges are particularly pronounced with high-resolution histopathology images due to their complex feature representation and high spatial detail. In response to these challenges, this work proposes a novel framework integrating a contrastive learning-based Multistage Progressive Finetuning Siamese Neural Network (MFT-SNN) with a Reinforcement Learning-based External Optimizer (RL-EO). The MFT-SNN improves feature similarity extraction in histopathology data, while the RL-EO acts as a reward-based guide to balance GAN training, addressing mode collapse and enhancing output quality. The proposed approach is evaluated against state-of-the-art (SOTA) GAN models and demonstrates superior performance across multiple metrics.
SimCLR is one of the most popular contrastive learning methods for vision tasks. It pre-trains deep neural networks based on a large amount of unlabeled data by teaching the model to distinguish between positive and negative pairs of augmented images. It is believed that SimCLR can pre-train a deep neural network to learn efficient representations that can lead to a better performance of future supervised fine-tuning. Despite its effectiveness, our theoretical understanding of the underlying mechanisms of SimCLR is still limited. In this paper, we theoretically introduce a case study of the SimCLR method. Specifically, we consider training a two-layer convolutional neural network (CNN) to learn a toy image data model. We show that, under certain conditions on the number of labeled data, SimCLR pre-training combined with supervised fine-tuning achieves almost optimal test loss. Notably, the label complexity for SimCLR pre-training is far less demanding compared to direct training on supervised data. Our analysis sheds light on the benefits of SimCLR in learning with fewer labels.
Scientific modeling and engineering applications rely heavily on parameter estimation methods to fit physical models and calibrate numerical simulations using real-world measurements. In the absence of analytic statistical models with tractable likelihoods, modern simulation-based inference (SBI) methods first use a numerical simulator to generate a dataset of parameters and simulated outputs. This dataset is then used to approximate the likelihood and estimate the system parameters given observation data. Several SBI methods employ machine learning emulators to accelerate data generation and parameter estimation. However, applying these approaches to high-dimensional physical systems remains challenging due to the cost and complexity of training high-dimensional emulators. This paper introduces Embed and Emulate (E&E): a new SBI method based on contrastive learning that efficiently handles high-dimensional data and complex, multimodal parameter posteriors. E&E learns a low-dimensional latent embedding of the data (i.e., a summary statistic) and a corresponding fast emulator in the latent space, eliminating the need to run expensive simulations or a high dimensional emulator during inference. We illustrate the theoretical properties of the learned latent space through a synthetic experiment and demonstrate superior performance over existing methods in a realistic, non-identifiable parameter estimation task using the high-dimensional, chaotic Lorenz 96 system.
Domain adaptation aims to reduce the model degradation on the target domain caused by the domain shift between the source and target domains. Although encouraging performance has been achieved by combining cognitive learning with the self-training paradigm, they suffer from ambiguous scenarios caused by scale, illumination, or overlapping when deploying deterministic embedding. To address these issues, we propose probabilistic proto-typical pixel contrast (PPPC), a universal adaptation framework that models each pixel embedding as a probability via multivariate Gaussian distribution to fully exploit the uncertainty within them, eventually improving the representation quality of the model. In addition, we derive prototypes from probability estimation posterior probability estimation which helps to push the decision boundary away from the ambiguity points. Moreover, we employ an efficient method to compute similarity between distributions, eliminating the need for sampling and reparameterization, thereby significantly reducing computational overhead. Further, we dynamically select the ambiguous crops at the image level to enlarge the number of boundary points involved in contrastive learning, which benefits the establishment of precise distributions for each category. Extensive experimentation demonstrates that PPPC not only helps to address ambiguity at the pixel level, yielding discriminative representations but also achieves significant improvements in both synthetic-to-real and day-to-night adaptation tasks. It surpasses the previous state-of-the-art (SOTA) by +5.2% mIoU in the most challenging daytime-to-nighttime adaptation scenario, exhibiting stronger generalization on other unseen datasets. The code and models are available at https://github.com/DarlingInTheSV/Probabilistic-Prototypical-Pixel-Contrast.