Related papers: HAAP: Vision-context Hierarchical Attention Autore…

Robust cross-subject emotion recognition from multimodal physiological signals remains a challenging problem, primarily due to modality heterogeneity and inter-subject distribution shift. To tackle these challenges, we propose a novel…

This paper introduces Fast Linearized Adaptive Policy (FLAP), a new meta-reinforcement learning (meta-RL) method that is able to extrapolate well to out-of-distribution tasks without the need to reuse data from training, and adapt almost…

Recently, pre-training multilingual language models has shown great potential in learning multilingual representation, a crucial topic of natural language processing. Prior works generally use a single mixed attention (MA) module, following…

Text-guided image manipulation has experienced notable advancement in recent years. In order to mitigate linguistic ambiguity, few-shot learning with visual examples has been applied for instructions that are underrepresented in the…

Machine learning for tabular data remains constrained by poor schema generalization, a challenge rooted in the lack of semantic understanding of structured variables. This challenge is particularly acute in domains like clinical medicine,…

This paper analyzes the predictions of image captioning models with attention mechanisms beyond visualizing the attention itself. We develop variants of layer-wise relevance propagation (LRP) and gradient-based explanation methods, tailored…

The quadratic cost of scaled dot-product attention is a central obstacle to scaling autoregressive language models to long contexts. Linear-time attention and State Space Models (SSMs) provide scalable alternatives but are typically…

Training reinforcement learning (RL) agents often requires significant computational resources and prolonged training durations. To address this challenge, we build upon prior work that introduced a neural architecture with…

Traditional continual learning methods prioritize knowledge retention and focus primarily on mitigating catastrophic forgetting, implicitly assuming that the data distribution of previously learned tasks remains static. This overlooks the…

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow…

Language modeling (LM) for automatic speech recognition (ASR) does not usually incorporate utterance level contextual information. For some domains like voice assistants, however, additional context, such as the time at which an utterance…

The classification of gigapixel histopathology images with deep multiple instance learning models has become a critical task in digital pathology and precision medicine. In this work, we propose a Transformer-based multiple instance…

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

Accurate prediction of molecular properties is crucial in drug discovery. Traditional methods often overlook that real-world molecules typically exhibit multiple property labels with complex correlations. To this end, we propose a novel…

We present a novel attribute learning framework named Hypergraph-based Attribute Predictor (HAP). In HAP, a hypergraph is leveraged to depict the attribute relations in the data. Then the attribute prediction problem is casted as a…

In this work, we study the problem of word-level confidence calibration for scene-text recognition (STR). Although the topic of confidence calibration has been an active research area for the last several decades, the case of structured and…

Self Supervised Representation Learning (SSRepL) can capture meaningful and robust representations of the Attention Deficit Hyperactivity Disorder (ADHD) data and have the potential to improve the model's performance on also downstream…

Vision-language models (VLMs) have demonstrated exceptional generalization capabilities for downstream tasks. Due to its efficiency, prompt learning has gradually become a more effective and efficient method for transferring VLMs to…

Pruning is an effective method to reduce the memory footprint and computational cost associated with large natural language processing models. However, current pruning algorithms either only focus on one pruning category, e.g., structured…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…