Related papers: Exploring Contur beyond its default mode: a case s…

Contrastive learning based on instance discrimination trains model to discriminate different transformations of the anchor sample from other samples, which does not consider the semantic similarity among samples. This paper proposes a new…

Computational Colour Constancy (CCC) consists of estimating the colour of one or more illuminants in a scene and using them to remove unwanted chromatic distortions. Much research has focused on illuminant estimation for CCC on single…

In recent years, the background-aware correlation filters have achie-ved a lot of research interest in the visual target tracking. However, these methods cannot suitably model the target appearance due to the exploitation of hand-crafted…

The success of Large Language Models (LLMs) in various domains has led researchers to apply them to graph-related problems by converting graph data into natural language text. However, unlike graph data, natural language inherently has…

Temporally contrastive representation learning induces a latent structure capable of reducing long-horizon planning to inference in a low-dimensional linear system. However, existing contrastive planning work learns a single latent geometry…

Human visual brain use three main component such as color, texture and shape to detect or identify environment and objects. Hence, texture analysis has been paid much attention by scientific researchers in last two decades. Texture features…

Accurate road topology reasoning is critical for autonomous driving, as it requires both perceiving road elements and understanding how lanes connect to each other (L2L) and to traffic elements (L2T). Existing methods often focus on either…

Native Omni-modal Large Language Models (OLLMs) have shifted from pipeline architectures to unified representation spaces. However, this native integration gives rise to a critical yet underexplored phenomenon: modality preference. To…

Alignment of large language models (LLMs) via SFT and RLHF/DPO typically ignores the global geometry of the representation space, relying instead on local token likelihoods or scalar scores. We view generation as tracing a semantic…

Multi-token prediction (MTP) has been proposed as an auxiliary objective to improve next-token prediction (NTP) in language model training but shows inconsistent improvements, underperforming in standard NLP benchmarks. We found MTP's exact…

Online learning to rank is a core problem in machine learning. In Lattimore et al. (2018), a novel online learning algorithm was proposed based on topological sorting. In the paper they provided a set of self-normalized inequalities (a) in…

We explore the possibility that $Z'$ couplings can be probed using decay modes which involve neutrinos once Standard Model backgrounds are directly determined by the data itself. For some models, sufficient statistics are available at…

Enhancement is an important step in post-processing digital images for personal use, in medical imaging, and for object recognition. Most existing manual techniques rely on region selection, similarity, and/or thresholding for editing,…

This paper considers arbitrary document detection performed on a mobile device. The classical contour-based approach often fails in cases featuring occlusion, complex background, or blur. The region-based approach, which relies on the…

The widespread adoption of deep learning is often attributed to its automatic feature construction with minimal inductive bias. However, in many real-world tasks, the learned function is intended to satisfy domain-specific constraints. We…

We introduce a simple new approach to the problem of understanding documents where non-trivial layout influences the local semantics. To this end, we modify the Transformer encoder architecture in a way that allows it to use layout features…

Benefiting from powerful convolutional neural networks (CNNs), learning-based image inpainting methods have made significant breakthroughs over the years. However, some nature of CNNs (e.g. local prior, spatially shared parameters) limit…

During language model decoding, it is known that using higher temperature sampling gives more creative responses, while lower temperatures are more factually accurate. However, such models are commonly applied to general instruction…

We theoretically and experimentally investigate tensor-based regression and classification. Our focus is regularization with various tensor norms, including the overlapped trace norm, the latent trace norm, and the scaled latent trace norm.…

In ordinal classification, misclassifying neighboring ranks is common, yet the consequences of these errors are not the same. For example, misclassifying benign tumor categories is less consequential, compared to an error at the…