Related papers: Effective weakly supervised semantic frame inducti…

We propose a probabilistic modeling framework for learning the dynamic patterns in the collective behaviors of social agents and developing profiles for different behavioral groups, using data collected from multiple information sources.…

Handwritten Mathematical Expression Recognition (HMER) has wide applications in human-machine interaction scenarios, such as digitized education and automated offices. Recently, sequence-based models with encoder-decoder architectures have…

This paper aims to improve the performance of large language models by addressing the variable computational demands in inference steps, where some tokens require more computational resources than others. We present HARP, a simple…

This study introduces an integrated framework for predictive causal inference designed to overcome limitations inherent in conventional single model approaches. Specifically, we combine a Hidden Markov Model (HMM) for spatial health state…

Harnessing the statistical power of neural networks to perform language understanding and symbolic reasoning is difficult, when it requires executing efficient discrete operations against a large knowledge-base. In this work, we introduce a…

Engaging in smooth conversations with others is a crucial social skill. However, differences in knowledge between conversation participants can sometimes hinder effective communication. To tackle this issue, this study proposes a real-time…

Large Language Models are increasingly deployed inside agentic systems, where they must follow structured protocols, adapt to evolving states, and operate under memory, latency, and cost constraints. In such regimes, prompt extension is…

In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speech phone classification. We combine modern neural networks…

Using only image-sentence pairs, weakly-supervised visual-textual grounding aims to learn region-phrase correspondences of the respective entity mentions. Compared to the supervised approach, learning is more difficult since bounding boxes…

Speech emotion recognition (SER) systems aim to recognize human emotional state during human-computer interaction. Most existing SER systems are trained based on utterance-level labels. However, not all frames in an audio have affective…

We replace the Hidden Markov Model (HMM) which is traditionally used in in continuous speech recognition with a bi-directional recurrent neural network encoder coupled to a recurrent neural network decoder that directly emits a stream of…

Grammar induction has made significant progress in recent years. However, it is not clear how the application of induced grammar could enhance practical performance in downstream tasks. In this work, we introduce an unsupervised grammar…

Context modeling is essential in learned image compression for accurately estimating the distribution of latents. While recent advanced methods have expanded context modeling capacity, they still struggle to efficiently exploit long-range…

Nowadays, neural network models achieve state-of-the-art results in many areas as computer vision or speech processing. For sequential data, especially for Natural Language Processing (NLP) tasks, Recurrent Neural Networks (RNNs) and their…

Conversational recommendation frameworks have gained prominence as a dynamic paradigm for delivering personalized suggestions via interactive dialogues. The incorporation of advanced language understanding techniques has substantially…

Solving text classification in a weakly supervised manner is important for real-world applications where human annotations are scarce. In this paper, we propose to query a masked language model with cloze style prompts to obtain supervision…

Learning and understanding the typical patterns in the daily activities and routines of people from low-level sensory data is an important problem in many application domains such as building smart environments, or providing intelligent…

This paper investigates robot manipulation based on human instruction with ambiguous requests. The intent is to compensate for imperfect natural language via visual observations. Early symbolic methods, based on manually defined symbols,…

Term-based sparse representations dominate the first-stage text retrieval in industrial applications, due to its advantage in efficiency, interpretability, and exact term matching. In this paper, we study the problem of transferring the…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…