Related papers: Program synthesis performance constrained by non-l…

Spatial reasoning on multi-view line drawings by state-of-the-art supervised deep networks is recently shown with puzzling low performances on the SPARE3D dataset. Based on the fact that self-supervised learning is helpful when a large…

Program synthesis aims to automatically generate an executable program that conforms to the given specification. Recent advancements have demonstrated that deep neural methodologies and large-scale pretrained language models are highly…

Satellite Image Time Series (SITS) representation learning is complex due to high spatiotemporal resolutions, irregular acquisition times, and intricate spatiotemporal interactions. These challenges result in specialized neural network…

Existing Scene Text Recognition (STR) methods typically use a language model to optimize the joint probability of the 1D character sequence predicted by a visual recognition (VR) model, which ignore the 2D spatial context of visual…

Humans can observe a single, imperfect demonstration and immediately generalize to very different problem settings. Robots, in contrast, often require hundreds of examples and still struggle to generalize beyond the training conditions. We…

In visual place recognition (VPR), filtering and sequence-based matching approaches can improve performance by integrating temporal information across image sequences, especially in challenging conditions. While these methods are commonly…

Vision Language Models (VLMs) often struggle with chart understanding tasks, particularly in accurate chart description and complex reasoning. Synthetic data generation is a promising solution, while usually facing the challenge of noise…

Visual reprogramming (VR) is a prompting technique that aims to re-purpose a pre-trained model (e.g., a classifier on ImageNet) to target tasks (e.g., medical data prediction) by learning a small-scale pattern added into input images…

Scene classification is a fundamental perception task for environmental understanding in today's robotics. In this paper, we have attempted to exploit the use of popular machine learning technique of deep learning to enhance scene…

With recent advances in speech synthesis, synthetic data is becoming a viable alternative to real data for training speech recognition models. However, machine learning with synthetic data is not trivial due to the gap between the synthetic…

Vision language models (VLM) have demonstrated remarkable performance across various downstream tasks. However, understanding fine-grained visual-linguistic concepts, such as attributes and inter-object relationships, remains a significant…

For a variety of regularized optimization problems in machine learning, algorithms computing the entire solution path have been developed recently. Most of these methods are quadratic programs that are parameterized by a single parameter,…

Multimodal Large Language Models (MLLMs) have achieved notable gains in various tasks by incorporating Chain-of-Thought (CoT) reasoning in language spaces. Recent work extends this direction by leveraging external tools for visual editing,…

In the rapidly evolving area of image synthesis, a serious challenge is the presence of complex artifacts that compromise perceptual realism of synthetic images. To alleviate artifacts and improve quality of synthetic images, we fine-tune…

Spatial reasoning is an important component of human intelligence. We can imagine the shapes of 3D objects and reason about their spatial relations by merely looking at their three-view line drawings in 2D, with different levels of…

Visual speech recognition (VSR) systems decode spoken words from an input sequence using only the video data. Practical applications of such systems include medical assistance as well as human-machine interactions. A VSR system is typically…

We propose a novel approach to synthesizing images that are effective for training object detectors. Starting from a small set of real images, our algorithm estimates the rendering parameters required to synthesize similar images given a…

Can Visual Language Models (VLMs) effectively capture human visual preferences? This work addresses this question by training VLMs to think about preferences at test time, employing reinforcement learning methods inspired by DeepSeek R1 and…

Vision-based reinforcement learning (RL) is a promising technique to solve control tasks involving images as the main observation. State-of-the-art RL algorithms still struggle in terms of sample efficiency, especially when using image…

Large language models have achieved substantial progress in mathematical reasoning, yet their advancement is limited by the scarcity of high-quality, high-difficulty training data. Existing synthesis methods largely rely on transforming…