Related papers: INarIG: Iterative Non-autoregressive Instruct Gene…

Research on continual learning has led to a variety of approaches to mitigating catastrophic forgetting in feed-forward classification networks. Until now surprisingly little attention has been focused on continual learning of recurrent…

Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image. Most recent researches follow the encoder-decoder framework which depends heavily on the previous generated words for…

Automated speaking assessment in conversation tests (ASAC) aims to evaluate the overall speaking proficiency of an L2 (second-language) speaker in a setting where an interlocutor interacts with one or more candidates. Although prior ASAC…

Text injection for automatic speech recognition (ASR), wherein unpaired text-only data is used to supplement paired audio-text data, has shown promising improvements for word error rate. This study examines the use of text injection for…

Despite the great success of pre-trained language models, it is still a challenge to use these models for continual learning, especially for the class-incremental learning (CIL) setting due to catastrophic forgetting (CF). This paper…

Recent years have witnessed increasing interests in developing interpretable models in Natural Language Processing (NLP). Most existing models aim at identifying input features such as words or phrases important for model predictions.…

Robotic real-world reinforcement learning (RL) with vision-language-action (VLA) models is bottlenecked by sparse, handcrafted rewards and inefficient exploration. We introduce VLAC, a general process reward model built upon InternVL and…

In the realm of education, student evaluation holds equal significance to imparting knowledge. To be evaluated, students usually need to go through text-based academic assessment methods. Instructors need to make a diverse set of questions…

Ensuring data quality in large tabular datasets is a critical challenge, typically addressed through data wrangling tasks. Traditional statistical methods, though efficient, cannot often understand the semantic context and deep learning…

Retrieval-Augmented Generation (RAG) significantly enhances the performance of large language models (LLMs) in downstream tasks by integrating external knowledge. To facilitate researchers in deploying RAG systems, various RAG toolkits have…

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in…

Generative vision-language models (VLMs) have shown impressive performance in zero-shot vision-language tasks like image captioning and visual question answering. However, improving their zero-shot reasoning typically requires second-stage…

Autoregressive (AR) models have achieved remarkable success in natural language and image generation, but their application to 3D shape modeling remains largely unexplored. Unlike diffusion models, AR models enable more efficient and…

Iterative retrieval-augmented generation (iRAG) models offer an effective approach for multi-hop question answering (QA). However, their retrieval process faces two key challenges: (1) it can be disrupted by irrelevant documents or…

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…

In Automatic Speech Recognition it is still challenging to learn useful intermediate representations when using high-level (or abstract) target units such as words. For that reason, character or phoneme based systems tend to outperform…

We propose a conditional non-autoregressive neural sequence model based on iterative refinement. The proposed model is designed based on the principles of latent variable models and denoising autoencoders, and is generally applicable to any…

Large language models are increasingly solving tasks that are commonly believed to require human-level reasoning ability. However, these models still perform very poorly on benchmarks of general intelligence such as the Abstraction and…

Hybrid tabular-textual question answering (QA) requires reasoning from heterogeneous information, and the types of reasoning are mainly divided into numerical reasoning and span extraction. Current numerical reasoning methods…

Current state-of-the-art image captioning models adopt autoregressive decoders, \ie they generate each word by conditioning on previously generated words, which leads to heavy latency during inference. To tackle this issue,…