Related papers: SmartPhone: Exploring Keyword Mnemonic with Auto-g…
Reading and repeatedly retelling a short story is a common and effective approach to learning the meanings and usages of target words. However, learners often struggle with comprehending, recalling, and retelling the story contexts of these…
The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…
We introduce a new dynamic vocabulary for language models. It can involve arbitrary text spans during generation. These text spans act as basic generation bricks, akin to tokens in the traditional static vocabularies. We show that, the…
This paper explores the possibility of learning custom tokens for representing new concepts in Vision-Language Models (VLMs). Our aim is to learn tokens that can be effective for both discriminative and generative tasks while composing well…
The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradigm, reliant on end-to-end generation or explicit,…
Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is…
Cue phrases may be used in a discourse sense to explicitly signal discourse structure, but also in a sentential sense to convey semantic rather than structural information. Correctly classifying cue phrases as discourse or sentential is…
The ability of machine learning models to store input information in hidden layer vector embeddings, analogous to the concept of `memory', is widely employed but not well characterized. We find that language model embeddings typically…
Movies provide us with a mass of visual content as well as attracting stories. Existing methods have illustrated that understanding movie stories through only visual content is still a hard problem. In this paper, for answering questions…
We build a dual-way neural dictionary to retrieve words given definitions, and produce definitions for queried words. The model learns the two tasks simultaneously and handles unknown words via embeddings. It casts a word or a definition to…
A storyboard is a sequence of images to illustrate a story containing multiple sentences, which has been a key process to create different story products. In this paper, we tackle a new multimedia task of automatic storyboard creation to…
Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive…
Humans are able to identify a referred visual object in a complex scene via a few rounds of natural language communications. Success communication requires both parties to engage and learn to adapt for each other. In this paper, we…
Fixed-vocabulary language models fail to account for one of the most characteristic statistical facts of natural language: the frequent creation and reuse of new word types. Although character-level language models offer a partial solution…
Language models are increasingly being deployed as user simulators, but their memory is far more reliable than that of real users. To measure this gap, we run a series of classic memory experiments from psychology on both humans and…
We present a novel approach to multilingual audio-visual speech recognition tasks by introducing a single model on a multilingual dataset. Motivated by a human cognitive system where humans can intuitively distinguish different languages…
Learning to recognize new keywords with just a few examples is essential for personalizing keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS models are typically trained on large datasets and restricted to a…
Visual Question Answering (VQA) emerges as one of the most fascinating topics in computer vision recently. Many state of the art methods naively use holistic visual features with language features into a Long Short-Term Memory (LSTM)…
Large Language Models (LLMs) are reshaping unsupervised learning by offering an unprecedented ability to perform text clustering based on their deep semantic understanding. However, their direct application is fundamentally limited by a…
When language models are trained on textual data, they acquire both knowledge about the structure of language as well as knowledge of facts about the world. At inference time, their knowledge of facts can be leveraged to solve interesting…