Related papers: Visually Grounded Neural Syntax Acquisition
In this paper, we propose a transformer based approach for visual grounding. Unlike previous proposal-and-rank frameworks that rely heavily on pretrained object detectors or proposal-free frameworks that upgrade an off-the-shelf one-stage…
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…
Disentangling the encodings of neural models is a fundamental aspect for improving interpretability, semantic control and downstream task performance in Natural Language Processing. Currently, most disentanglement methods are unsupervised…
Humans learn language by listening, speaking, writing, reading, and also, via interaction with the multimodal real world. Existing language pre-training frameworks show the effectiveness of text-only self-supervision while we explore the…
While much research has been done in text-to-image synthesis, little work has been done to explore the usage of linguistic structure of the input text. Such information is even more important for story visualization since its inputs have an…
Today's most accurate language models are trained on orders of magnitude more language data than human language learners receive - but with no supervision from other sensory modalities that play a crucial role in human learning. Can we make…
Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…
We propose a weakly-supervised approach that takes image-sentence pairs as input and learns to visually ground (i.e., localize) arbitrary linguistic phrases, in the form of spatial attention masks. Specifically, the model is trained with…
Leveraging the universal representations of pre-trained LLMs and MLLMs offers a promising path toward brain foundation models. However, visually-evoked EEG datasets remain scarce, leading existing methods to align neural signals mainly with…
Large-scale pre-trained Vision & Language (VL) models have shown remarkable performance in many applications, enabling replacing a fixed set of supported classes with zero-shot open vocabulary reasoning over (almost arbitrary) natural…
We propose a zero-shot method for Natural Language Inference (NLI) that leverages multimodal representations by grounding language in visual contexts. Our approach generates visual representations of premises using text-to-image models and…
Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some…
We introduce a neural network that represents sentences by composing their words according to induced binary parse trees. We use Tree-LSTM as our composition function, applied along a tree structure found by a fully differentiable natural…
Most previous work on grammar induction focuses on learning phrasal or dependency structure purely from text. However, because the signal provided by text alone is limited, recently introduced visually grounded syntax models make use of…
We propose a neural language model capable of unsupervised syntactic structure induction. The model leverages the structure information to form better semantic representations and better language modeling. Standard recurrent neural networks…
Current multimodal LLMs encode images as static visual prefixes and rely on text-based reasoning, lacking goal-driven and adaptive visual access. Inspired by human visual perception-where attention is selectively and sequentially shifted…
Natural language rationales could provide intuitive, higher-level explanations that are easily understandable by humans, complementing the more broadly studied lower-level explanations based on gradients or attention weights. We present the…
Visual Grounding (VG) tasks, such as referring expression detection and segmentation tasks are important for linking visual entities to context, especially in complex reasoning tasks that require detailed query interpretation. This paper…
Visually-grounded models of spoken language understanding extract semantic information directly from speech, without relying on transcriptions. This is useful for low-resource languages, where transcriptions can be expensive or impossible…
Vision-Language Navigation (VLN) requires an embodied agent to navigate complex environments by following natural language instructions, which typically demands tight fusion of visual and language modalities. Existing VLN methods often…