相关论文: Im-Promptu: In-Context Composition from Image Prom…

In-Context Learning (ICL) is an intriguing ability of large language models (LLMs). Despite a substantial amount of work on its behavioral aspects and how it emerges in miniature setups, it remains unclear which mechanism assembles task…

As one of the most exciting features of large language models (LLMs), in-context learning is a mixed blessing. While it allows users to fast-prototype a task solver with only a few training examples, the performance is generally sensitive…

In-context Learning (ICL) empowers large language models (LLMs) to swiftly adapt to unseen tasks at inference-time by prefixing a few demonstration examples before queries. Despite its versatility, ICL incurs substantial computational and…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

The collaborative reasoning for understanding each image-question pair is very critical but under-explored for an interpretable Visual Question Answering (VQA) system. Although very recent works also tried the explicit compositional…

Text-to-image (T2I) generation aims to synthesize images from textual prompts, which jointly specify what must be shown and imply what can be inferred, which thus correspond to two core capabilities: \textbf{\textit{composition}} and…

Vision-Language Models (VLMs) have achieved strong performance on implicit and explicit visual grounding and related tasks. However, such abilities are generally tested on simple, single-object phrases. We find that grounding performance…

In-context learning refers to the emerging ability of large language models (LLMs) to perform a target task without additional training, utilizing demonstrations of the task. Recent studies aim to enhance in-context learning performance by…

Content creators often draw inspiration from multiple visual sources, combining distinct elements to craft new compositions. Modern computational approaches now aim to emulate this fundamental creative process. Although recent diffusion…

Composition is a cornerstone of visual aesthetics, influencing the appeal of an image. While its principles operate independently of specific content, in practice, composition is often coupled with semantics. As a result, existing methods…

Humans are highly efficient learners, with the ability to grasp the meaning of a new concept from just a few examples. Unlike popular computer vision systems, humans can flexibly leverage the compositional structure of the visual world,…

Language models exhibit an emergent ability to learn a new task from a small number of input-output demonstrations. However, recent work shows that in-context learners largely rely on their pre-trained knowledge, such as the sentiment of…

Compositionality of semantic concepts in image synthesis and analysis is appealing as it can help in decomposing known and generatively recomposing unknown data. For instance, we may learn concepts of changing illumination, geometry or…

Although psycholinguists and psychologists have long studied the tendency of linguistic strings to evoke mental images in hearers or readers, most computational studies have applied this concept of imageability only to isolated words. Using…

Previous in-context learning (ICL) research has focused on tasks such as classification, machine translation, text2table, etc., while studies on whether ICL can improve human-like dialogue generation are scarce. Our work fills this gap by…

Vision transformers have established a precedent of patchifying images into uniformly-sized chunks before processing. We hypothesize that this design choice may limit models in learning comprehensive and compositional representations from…

In-context learning (ICL) allows a language model to improve its problem-solving capability when provided with suitable information in context. Since the choice of in-context information can be determined based on the problem itself,…

Transformers have demonstrated a strong ability for in-context learning (ICL), enabling models to solve previously unseen tasks using only example input output pairs provided at inference time. While prior theoretical work has established…

In-context learning (ICL) using large language models for tasks with many labels is challenging due to the limited context window, which makes it difficult to fit a sufficient number of examples in the prompt. In this paper, we use a…

Vision-language models (VLMs) like CLIP have showcased a remarkable ability to extract transferable features for downstream tasks. Nonetheless, the training process of these models is usually based on a coarse-grained contrastive loss…