相关论文: Learning to Anticipate Future with Dynamic Context…

In applications of dynamical systems, situations can arise where it is desired to predict the onset of synchronization as it can lead to characteristic and significant changes in the system performance and behaviors, for better or worse. In…

Modern Code Review (MCR) is a standard in all kinds of organizations that develop software. MCR pays for itself through perceived and proven benefits in quality assurance and knowledge transfer. However, the time invest in MCR is generally…

The open world is inherently dynamic, characterized by ever-evolving concepts and distributions. Continual learning (CL) in this dynamic open-world environment presents a significant challenge in effectively generalizing to unseen test-time…

Predicting and reasoning about the future lie at the heart of many time-series questions. For example, goal-conditioned reinforcement learning can be viewed as learning representations to predict which states are likely to be visited in the…

Humans do not memorize everything. Thus, humans recognize scene changes by exploring the past images. However, available past (i.e., reference) images typically represent nearby viewpoints of the present (i.e., query) scene, rather than the…

Generalization and adaptation of learned skills to novel situations is a core requirement for intelligent autonomous robots. Although contextual reinforcement learning provides a principled framework for learning and generalization of…

Vision-centric autonomous driving has recently raised wide attention due to its lower cost. Pre-training is essential for extracting a universal representation. However, current vision-centric pre-training typically relies on either 2D or…

Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important.…

Deep reinforcement learning (RL) algorithms suffer severe performance degradation when the interaction data is scarce, which limits their real-world application. Recently, visual representation learning has been shown to be effective and…

Reinforcement learning (RL) has demonstrated considerable potential for enhancing reasoning in large language models (LLMs). However, existing methods suffer from Gradient Starvation and Policy Degradation when training directly on samples…

Attention-based architectures trained on internet-scale language data have demonstrated state of the art reasoning ability for various language-based tasks, such as logic problems and textual reasoning. Additionally, these Large Language…

Existing models for extractive summarization are usually trained from scratch with a cross-entropy loss, which does not explicitly capture the global context at the document level. In this paper, we aim to improve this task by introducing…

Large language models (LLMs) aligned for safety often suffer from over-refusal, the tendency to reject seemingly toxic or benign prompts by misclassifying them as toxic. This behavior undermines models' helpfulness and restricts usability…

Anticipating actions before they are executed is crucial for a wide range of practical applications, including autonomous driving and robotics. In this paper, we study the egocentric action anticipation task, which predicts future action…

Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a…

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the…

How to improve the ability of scene representation is a key issue in vision-oriented decision-making applications, and current approaches usually learn task-relevant state representations within visual reinforcement learning to address this…

Reinforcement learning (RL) presents a promising framework to learn policies through environment interaction, but often requires an infeasible amount of interaction data to solve complex tasks from sparse rewards. One direction includes…

The abstract visual reasoning ability in human intelligence benefits discovering underlying rules in the novel environment. Raven's Progressive Matrix (RPM) is a classic test to realize such ability in machine intelligence by selecting from…

Modern deep models are trained on large real-world datasets, where data quality varies and redundancy is common. Data-centric approaches such as dataset pruning have shown promise in improving training efficiency and model performance.…