Related papers: Decoding Data Quality via Synthetic Corruptions: E…

Image-based rendering techniques stand at the core of an immersive experience for the user, as they generate novel views given a set of multiple input images. Since they have shown good performance in terms of objective and subjective…

Large language models (LLMs) have shown impressive promise in code generation, yet their progress remains limited by the shortage of large-scale datasets that are both diverse and well-aligned with human reasoning. Most existing resources…

Large language models (LLMs) have demonstrated significant potential in code generation tasks. However, there remains a performance gap between open-source and closed-source models. To address this gap, existing approaches typically…

Pretrained vision-language models such as CLIP achieve strong zero-shot generalization but remain vulnerable to distribution shifts caused by input corruptions. In this work, we investigate how corruptions affect CLIP's image embeddings and…

Large Language Models (LLMs) demonstrate exceptional capabilities across various tasks, but their deployment is constrained by high computational and memory costs. Model pruning provides an effective means to alleviate these demands.…

Large language models (LLMs) demonstrate strong performance as text embedding models when finetuned with supervised contrastive training. However, their large size balloons inference time and memory requirements. In this paper, we show that…

Large-scale subset selection asks for a small useful set of examples, features, sensors, seed users, or context passages from an enormous ground set. Submodular maximization is a canonical model for such diminishing-returns problems, but…

As deep neural networks include a high number of parameters and operations, it can be a challenge to implement these models on devices with limited computational resources. Despite the development of novel pruning methods toward…

Deep learning is now the gold standard in computer vision-based quality inspection systems. In order to detect defects, supervised learning is often utilized, but necessitates a large amount of annotated images, which can be costly:…

Video Large Language Models (Video LLMs) incur high inference latency due to a large number of visual tokens provided to LLMs. To address this, training-free visual token pruning has emerged as a solution to reduce computational costs;…

Large language models (LLMs) achieve strong performance across diverse tasks, largely driven by high-quality web data used in pre-training. However, recent studies indicate this data source is rapidly depleting. Synthetic data emerges as a…

Due to rapid advancements in technology, datasets are available from various domains. In order to carry out more relevant and appropriate analysis, it is often necessary to project the dataset into a higher or lower dimensional space based…

Network pruning techniques, including weight pruning and filter pruning, reveal that most state-of-the-art neural networks can be accelerated without a significant performance drop. This work focuses on filter pruning which enables…

Source code is usually formatted with elements like indentation and newlines to improve readability for human developers. However, these visual aids do not seem to be beneficial for large language models (LLMs) in the same way since the…

Prior studies in embodied AI consistently show that robust perception is critical for human-robot interaction, yet deploying high-fidelity visual models on resource-constrained agents remains challenging due to limited on-device computation…

Pre-trained models have been shown effective in many code intelligence tasks. These models are pre-trained on large-scale unlabeled corpus and then fine-tuned in downstream tasks. However, as the inputs to pre-training and downstream tasks…

Corrupted training data are ubiquitous. Corrective Machine Unlearning (CMU) seeks to remove the influence of such corruption post-training. Prior CMU typically assumes access to identified corrupted training samples (a "forget set").…

Recent advancements in large language models (LLMs) have significantly improved code generation and program comprehension, accelerating the evolution of software engineering. Current methods primarily enhance model performance by leveraging…

Training next-generation code generation models requires high-quality datasets, yet existing datasets face difficulty imbalance, format inconsistency, and data quality problems. We address these challenges through systematic data processing…

Deep learning's success has been attributed to the training of large, overparameterized models on massive amounts of data. As this trend continues, model training has become prohibitively costly, requiring access to powerful computing…