相关论文: MInCo: Mitigating Information Conflicts in Distrac…

Inverse reinforcement learning (IRL) infers a reward function from demonstrations, allowing for policy improvement and generalization. However, despite much recent interest in IRL, little work has been done to understand the minimum set of…

While recent model-free Reinforcement Learning (RL) methods have demonstrated human-level effectiveness in gaming environments, their success in everyday tasks like visual navigation has been limited, particularly under significant…

Contrastive learning has become pivotal in unsupervised representation learning, with frameworks like Momentum Contrast (MoCo) effectively utilizing large negative sample sets to extract discriminative features. However, traditional…

Benefiting from large-scale pretrained vision language models (VLMs), the performance of visual question answering (VQA) has approached human oracles. However, finetuning such models on limited data often suffers from overfitting and poor…

Change captioning aims to succinctly describe the semantic change between a pair of similar images, while being immune to distractors (illumination and viewpoint changes). Under these distractors, unchanged objects often appear pseudo…

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

Imitation learning trains control policies by mimicking pre-recorded expert demonstrations. In partially observable settings, imitation policies must rely on observation histories, but many seemingly paradoxical results show better…

The challenges to solving the collision avoidance problem lie in adaptively choosing optimal robot velocities in complex scenarios full of interactive obstacles. In this paper, we propose a distributed approach for multi-robot navigation…

Self-supervised representation learning approaches have recently surpassed their supervised learning counterparts on downstream tasks like object detection and image classification. Somewhat mysteriously the recent gains in performance come…

High-dimensional observations are a major challenge in the application of model-based reinforcement learning (MBRL) to real-world environments. To handle high-dimensional sensory inputs, existing approaches use representation learning to…

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed…

Medical vision-language pretraining (VLP) models have recently been investigated for their generalization to diverse downstream tasks. However, current medical VLP methods typically force the model to learn simple and complex concepts…

Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models,…

Model-based reinforcement learning (MBRL) is recognized with the potential to be significantly more sample-efficient than model-free RL. How an accurate model can be developed automatically and efficiently from raw sensory inputs (such as…

We investigate robust model-free reinforcement learning algorithms designed for environments that may be dynamic or even adversarial. Traditional state-based policies often struggle to accommodate the challenges imposed by the presence of…

Reinforcement learning (RL) has emerged as a promising approach for eliciting reasoning chains before generating final answers. However, multimodal large language models (MLLMs) generate reasoning that lacks integration of visual…

Visual generation is dominated by three paradigms: AutoRegressive (AR), diffusion, and Visual AutoRegressive (VAR) models. Unlike AR and diffusion, VARs operate on heterogeneous input structures across their generation steps, which creates…

Natural videos provide rich visual contents for self-supervised learning. Yet most existing approaches for learning spatio-temporal representations rely on manually trimmed videos, leading to limited diversity in visual patterns and limited…

In recent years, model-based reinforcement learning (MBRL) has emerged as a solution to address sample complexity in multi-agent reinforcement learning (MARL) by modeling agent-environment dynamics to improve sample efficiency. However,…

Multimodal representation learning, exemplified by multimodal contrastive learning (MMCL) using image-text pairs, aims to learn powerful representations by aligning cues across modalities. This approach relies on the core assumption that…