Related papers: Garbage in, garbage out: Zero-shot detection of cr…

Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…

We show that large language models (LLMs) are remarkably good at working with interpretable models that decompose complex outcomes into univariate graph-represented components. By adopting a hierarchical approach to reasoning, LLMs can…

Foundational multimodal models pre-trained on large scale image-text pairs or video-text pairs or both have shown strong generalization abilities on downstream tasks. However unlike image-text models, pretraining video-text models is always…

Zero-Shot Action Recognition has attracted attention in the last years and many approaches have been proposed for recognition of objects, events and actions in images and videos. There is a demand for methods that can classify instances…

Video anomaly detection (VAD) aims to temporally locate abnormal events in a video. Existing works mostly rely on training deep models to learn the distribution of normality with either video-level supervision, one-class supervision, or in…

Large Language Models (LLMs) have become a focal point of research across various domains, including software engineering, where their capabilities are increasingly leveraged. Recent studies have explored the integration of LLMs into…

Finetuning pretrained models on downstream generation tasks often leads to catastrophic forgetting in zero-shot conditions. In this work, we focus on summarization and tackle the problem through the lens of language-independent…

Using Large Language Models (LLMs) in real-world applications presents significant challenges, particularly in balancing computational efficiency with model performance. Optimizing acceleration after fine-tuning and during inference is…

Scene understanding is critical for various downstream tasks in autonomous driving, including facilitating driver-agent communication and enhancing human-centered explainability of autonomous vehicle (AV) decisions. This paper evaluates the…

We propose a novel zero-shot approach for keypoint detection on 3D shapes. Point-level reasoning on visual data is challenging as it requires precise localization capability, posing problems even for powerful models like DINO or CLIP.…

Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part…

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

The target of video moment retrieval (VMR) is predicting temporal spans within a video that semantically match a given linguistic query. Existing VMR methods based on multimodal large language models (MLLMs) overly rely on expensive…

Recent works have shown that unstructured text (documents) from online sources can serve as useful auxiliary information for zero-shot image classification. However, these methods require access to a high-quality source like Wikipedia and…

Large-scale Vision Language Models (LVLMs) exhibit advanced capabilities in tasks that require visual information, including object detection. These capabilities have promising applications in various industrial domains, such as autonomous…

Given a document in a source language, cross-lingual summarization (CLS) aims to generate a summary in a different target language. Recently, the emergence of Large Language Models (LLMs), such as GPT-3.5, ChatGPT and GPT-4, has attracted…

Code review is a crucial practice in software development. As code review nowadays is lightweight, various issues can be identified, and sometimes, they can be trivial. Research has investigated automated approaches to classify review…

Large Language Models (LLMs) have been found to struggle with systematic reasoning. Even on tasks where they appear to perform well, their performance often depends on shortcuts, rather than on genuine reasoning abilities, leading them to…

The design and optimization of hardware have traditionally been resource-intensive, demanding considerable expertise and dependence on established design automation tools. This paper discusses the possibility of exploiting large language…

This work introduces a model that can recognize objects in images even if no training data is available for the objects. The only necessary knowledge about the unseen categories comes from unsupervised large text corpora. In our zero-shot…