Related papers: VIRL: Volume-Informed Representation Learning towa…

Non-intrusive load monitoring (NILM) aims at energy consumption and appliance state information retrieval from aggregated consumption measurements, with the help of signal processing and machine learning algorithms. Representation learning…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

Inspired by the impressive reasoning capabilities demonstrated by reinforcement learning approaches like DeepSeek-R1, recent emerging research has begun exploring the use of reinforcement learning (RL) to enhance vision-language models…

Reinforcement learning (RL) promises to enable autonomous acquisition of complex behaviors for diverse agents. However, the success of current reinforcement learning algorithms is predicated on an often under-emphasised requirement -- each…

Learned representations in deep reinforcement learning (DRL) have to extract task-relevant information from complex observations, balancing between robustness to distraction and informativeness to the policy. Such stable and rich…

Imitation learning (IL) and reinforcement learning (RL) each offer distinct advantages for robotics policy learning: IL provides stable learning from demonstrations, and RL promotes generalization through exploration. While existing robot…

Representation learning has been widely studied in the context of meta-learning, enabling rapid learning of new tasks through shared representations. Recent works such as MAML have explored using fine-tuning-based metrics, which measure the…

The task of segmentation of multispectral images, which are images with numerous channels or bands, each capturing a specific range of wavelengths of electromagnetic radiation, has been previously explored in contexts with large amounts of…

We propose VRAIL (Vectorized Reward-based Attribution for Interpretable Learning), a bi-level framework for value-based reinforcement learning (RL) that learns interpretable weight representations from state features. VRAIL consists of two…

Masked image modeling (MIM) as pre-training is shown to be effective for numerous vision downstream tasks, but how and where MIM works remain unclear. In this paper, we compare MIM with the long-dominant supervised pre-trained models from…

The success of deep learning in computer vision has been driven by models of increasing scale, from deep Convolutional Neural Networks (CNN) to large Vision Transformers (ViT). While effective, these architectures are parameter-intensive…

Monocular 3D object detection typically relies on pseudo-labeling techniques to reduce dependency on real-world annotations. Recent advances demonstrate that deterministic linguistic cues can serve as effective auxiliary weak supervision…

Pretraining language models with next-token prediction on massive text corpora has delivered phenomenal zero-shot, few-shot, transfer learning and multi-tasking capabilities on both generative and discriminative language tasks. Motivated by…

The recent advancements in Vision Language Models (VLMs) have demonstrated progress toward true intelligence requiring robust reasoning capabilities. Beyond pattern recognition, linguistic reasoning must integrate with visual comprehension,…

Active Learning (AL) is a learning task that requires learners interactively query the labels of the sampled unlabeled instances to minimize the training outputs with human supervisions. In theoretical study, learners approximate the…

Unsupervised multi-object representation learning depends on inductive biases to guide the discovery of object-centric representations that generalize. However, we observe that methods for learning these representations are either…

We introduce VIOLA, an object-centric imitation learning approach to learning closed-loop visuomotor policies for robot manipulation. Our approach constructs object-centric representations based on general object proposals from a…

Learned representations are a central component in modern ML systems, serving a multitude of downstream tasks. When training such representations, it is often the case that computational and statistical constraints for each downstream task…

Vision-Language Models (VLMs) have shown strong performance in tasks like visual question answering and multimodal text generation, but their effectiveness in scientific domains such as materials science remains limited. While some machine…

Classical pixel-based Visual Servoing (VS) approaches offer high accuracy but suffer from a limited convergence area due to optimization nonlinearity. Modern deep learning-based VS methods overcome traditional vision issues but lack…