Related papers: What Linear Probes Miss: Multi-View Probing for We…

Modeling label correlations has always played a pivotal role in multi-label image classification (MLC), attracting significant attention from researchers. However, recent studies have overemphasized co-occurrence relationships among labels,…

Large Vision-Language Models (LVLMs) have demonstrated remarkable capabilities across multimodal tasks such as visual perception and reasoning, leading to good performance on various multimodal evaluation benchmarks. However, these…

Contrastive learning has revolutionized the field of computer vision, learning rich representations from unlabeled data, which generalize well to diverse vision tasks. Consequently, it has become increasingly important to explain these…

Prediction Rule Ensembles (PREs) are robust and interpretable statistical learning techniques with potential for predictive analytics, yet their efficacy in the presence of missing data is untested. This study uses multiple imputation to…

Amid mounting concern about the reliability and credibility of machine learning research, we present a principled framework for making robust and generalizable claims: the multiverse analysis. Our framework builds upon the multiverse…

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies…

Vision-language generative reward models (VL-GenRMs) play a crucial role in aligning and evaluating multimodal AI systems, yet their own evaluation remains under-explored. Current assessment methods primarily rely on AI-annotated preference…

On e-commerce platforms, predicting if two products are compatible with each other is an important functionality to achieve trustworthy product recommendation and search experience for consumers. However, accurately predicting product…

Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operate on full images do not directly enable the user to "point…

Large Vision-Language Models (LVLMs) rely on dense visual tokens to capture fine-grained visual information, but processing all these tokens incurs substantial computational and memory overhead during inference. To address this issue, we…

Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance on vision-language understanding tasks, yet their inference efficiency is often hampered by the large number of visual tokens, particularly in…

Multi-view learning integrates diverse representations of the same instances to improve performance. Most existing kernel-based multi-view learning methods use fusion techniques without enforcing an explicit collaboration type across views…

Seeing clearly with high resolution is a foundation of Large Multimodal Models (LMMs), which has been proven to be vital for visual perception and reasoning. Existing works usually employ a straightforward resolution upscaling method, where…

Current visual representation learning remains bifurcated: vision-language models (e.g., CLIP) excel at global semantic alignment but lack spatial precision, while self-supervised methods (e.g., MAE, DINO) capture intricate local structures…

We address the problem of weakly supervised object localization where only image-level annotations are available for training object detectors. Numerous methods have been proposed to tackle this problem through mining object proposals.…

Power-law scaling indicates that large-scale training with uniform sampling is prohibitively slow. Active learning methods aim to increase data efficiency by prioritizing learning on the most relevant examples. Despite their appeal, these…

Vision-Language Models (VLMs) continue to struggle to make morally salient judgments in multimodal and socially ambiguous contexts. Prior works typically rely on binary or pairwise supervision, which often fail to capture the continuous and…

We learn about the world from a diverse range of sensory information. Automated systems lack this ability as investigation has centred on processing information presented in a single form. Adapting architectures to learn from multiple…

A well-executed graphic design typically achieves harmony in two levels, from the fine-grained design elements (color, font and layout) to the overall design. This complexity makes the comprehension of graphic design challenging, for it…

As Large Vision-Language Models (LVLMs) are increasingly deployed in domains such as shopping, health, and news, they are exposed to pervasive persuasive content. A critical question is how these models function as persuadees-how and why…