Related papers: Symbol Preference Aware Generative Models for Reco…
The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…
The task of Visual Question Answering (VQA) is known to be plagued by the issue of VQA models exploiting biases within the dataset to make its final prediction. Various previous ensemble based debiasing methods have been proposed where an…
Generative models (e.g., GANs, diffusion models) learn the underlying data distribution in an unsupervised manner. However, many applications of interest require sampling from a particular region of the output space or sampling evenly over…
Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…
Graph neural networks (GNNs) have demonstrated superior performance in various applications, such as recommendation systems and financial risk management. However, deploying large-scale GNN models locally is particularly challenging for…
This work explores the binarization of the deconvolution-based generator in a GAN for memory saving and speedup of image construction. Our study suggests that different from convolutional neural networks (including the discriminator) where…
Despite recent advances in Large Language Models (LLMs) for code generation, the quality of LLM-generated code still faces significant challenges. One significant issue is code repetition, which refers to the model's tendency to generate…
Face deidentification is an active topic amongst privacy and security researchers. Early deidentification methods relying on image blurring or pixelization were replaced in recent years with techniques based on formal anonymity models that…
Binary Neural Networks (BNNs), known to be one among the effectively compact network architectures, have achieved great outcomes in the visual tasks. Designing efficient binary architectures is not trivial due to the binary nature of the…
Binary code similarity detection (BCSD) is widely used in various binary analysis tasks such as vulnerability search, malware detection, clone detection, and patch analysis. Recent studies have shown that the learning-based binary code…
Recent work on weighted model counting has been very successfully applied to the problem of probabilistic inference in Bayesian networks. The probability distribution is encoded into a Boolean normal form and compiled to a target language,…
Recent advances in large language models (LLMs) have demonstrated impressive capabilities in code-related tasks, such as code generation and automated program repair. Despite their promising performance, most existing approaches for code…
Active learning improves annotation efficiency by selecting the most informative samples for annotation and model training. While most prior work has focused on selecting informative images for classification tasks, we investigate the more…
Discovering fine-grained categories from coarsely labeled data is a practical and challenging task, which can bridge the gap between the demand for fine-grained analysis and the high annotation cost. Previous works mainly focus on…
A core objective in recommender systems is to accurately model the distribution of user preferences over items to enable personalized recommendations. Recently, driven by the strong generative capabilities of large language models (LLMs),…
Many scientific computing problems can be reduced to Matrix-Matrix Multiplications (MMM), making the General Matrix Multiply (GEMM) kernels in the Basic Linear Algebra Subroutine (BLAS) of interest to the high-performance computing…
Growing interest in modelling complex systems from brains to societies to cities using networks has led to increased efforts to describe generative processes that explain those networks. Recent successes in machine learning have prompted…
Recent advances in score-based generative models have led to a huge spike in the development of downstream applications using generative models ranging from data augmentation over image and video generation to anomaly detection. Despite…
Evaluating identity preservation in generative models remains a critical yet unresolved challenge. Existing metrics rely on global embeddings or coarse VLM prompting, failing to capture fine-grained identity changes and providing limited…
Deep generative models provide a powerful set of tools to understand real-world data. But as these models improve, they increase in size and complexity, so their computational cost in memory and execution time grows. Using binary weights in…