Related papers: Understanding Retrieval Robustness for Retrieval-A…
The advent of vision-language pre-training techniques enhanced substantial progress in the development of models for image captioning. However, these models frequently produce generic captions and may omit semantically important image…
Retrieval augmentation enables large language models to take advantage of external knowledge, for example on tasks like question answering and data imputation. However, the performance of such retrieval-augmented models is limited by the…
The task of dialogue rewriting aims to reconstruct the latest dialogue utterance by copying the missing content from the dialogue context. Until now, the existing models for this task suffer from the robustness issue, i.e., performances…
Large vision-language models (VLMs) enable intuitive visual search using natural language queries. However, improving their performance often requires fine-tuning and scaling to larger model variants. In this work, we propose a mechanism…
Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community. In this paper, we present a novel image captioning architecture to better explore semantics…
Vision language (VL) models like CLIP are robust to natural distribution shifts, in part because CLIP learns on unstructured data using a technique called caption supervision; the model inteprets image-linked texts as ground-truth labels.…
We propose SC-Captioner, a reinforcement learning framework that enables the self-correcting capability of image caption models. Our crucial technique lies in the design of the reward function to incentivize accurate caption corrections.…
Retrieval augmented language models have recently become the standard for knowledge intensive tasks. Rather than relying purely on latent semantics within the parameters of large neural models, these methods enlist a semi-parametric memory…
Trustworthiness is an essential prerequisite for the real-world application of large language models. In this paper, we focus on the trustworthiness of language models with respect to retrieval augmentation. Despite being supported with…
Event-based image retrieval from free-form captions presents a significant challenge: models must understand not only visual features but also latent event semantics, context, and real-world knowledge. Conventional vision-language retrieval…
Ranking consistently emerges as a primary focus in information retrieval research. Retrieval and ranking models serve as the foundation for numerous applications, including web search, open domain QA, enterprise domain QA, and text-based…
Image captioning transforms complex visual information into abstract natural language for representation, which can help computers understanding the world quickly. However, due to the complexity of the real environment, it needs to identify…
Retrieval-augmented language models can better adapt to changes in world state and incorporate long-tail knowledge. However, most existing methods retrieve only short contiguous chunks from a retrieval corpus, limiting holistic…
In the recent years, the dual-encoder vision-language models (\eg CLIP) have achieved remarkable text-to-image retrieval performance. However, we discover that these models usually results in very different retrievals for a pair of…
Augmenting language models with a retrieval mechanism has been shown to significantly improve their performance while keeping the number of parameters low. Retrieval-augmented models commonly rely on a semantic retrieval mechanism based on…
Due to the amount of videos and related captions uploaded every hour, deep learning-based solutions for cross-modal video retrieval are attracting more and more attention. A typical approach consists in learning a joint text-video embedding…
While multimodal large language models excel at tasks that integrate visual perception with symbolic reasoning, their performance is often undermined by a critical vulnerability: perception-induced errors that propagate through the…
Large language models encode impressively broad world knowledge in their parameters. However, the knowledge in static language models falls out of date, limiting the model's effective "shelf life." While online fine-tuning can reduce this…
Despite advancements in text-to-image models, generating images that precisely align with textual descriptions remains challenging due to misalignment in training data. In this paper, we analyze the critical role of caption precision and…
Fine-tuning of Large Language Models (LLMs) for downstream tasks, performed on domain-specific data has shown significant promise. However, commercial use of such LLMs is limited by the high computational cost required for their deployment…