Related papers: LIVS: A Pluralistic Alignment Dataset for Inclusiv…

Recent progress in generative diffusion models has greatly advanced text-to-video generation. While text-to-video models trained on large-scale, diverse datasets can produce varied outputs, these generations often deviate from user…

Iterative prompt refinement is central to reproducing target images with text to image generative models. Previous studies have incorporated image similarity metrics (ISMs) as additional feedback to human users. Existing ISMs such as LPIPS…

Large language models (LLMs) are currently aligned using techniques such as reinforcement learning from human feedback (RLHF). However, these methods use scalar rewards that can only reflect user preferences on average. Pluralistic…

Large Vision-Language Models (LVLMs) or multimodal large language models represent a significant advancement in artificial intelligence, enabling systems to understand and generate content across both visual and textual modalities. While…

Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across multiple dimensions, such as motion naturalness, lip-sync…

We introduce the Densely Segmented Supermarket (D2S) dataset, a novel benchmark for instance-aware semantic segmentation in an industrial domain. It contains 21,000 high-resolution images with pixel-wise labels of all object instances. The…

Preference learning is a widely adopted post-training technique that aligns large language models (LLMs) to human preferences and improves specific downstream task capabilities. In this work we systematically investigate how specific…

Video-language models (Video-LLMs) excel at understanding video content but struggle with spatial relationships, temporal ordering, and cross-frame continuity. To address these limitations, we introduce VideoPASTA (Preference Alignment with…

In the field of large language models (LLMs), aligning models with the diverse preferences of users is a critical challenge. Direct Preference Optimization (DPO) has played a key role in this area. It works by using pairs of preferences…

Urban inequality, as reflected by uneven spatial allocations of resources, services, and opportunities, has arisen as a major topic for quantitative research and policy intervention. Geographic Information Systems (GIS) provide a solid…

Performance disparities of image recognition across demographic groups are known to exist in deep learning-based models, due to imbalanced group representations or spurious correlation between group and target labels. Previous work has…

Comparing two images in terms of Commonalities and Differences (CaD) is a fundamental human capability that forms the basis of advanced visual reasoning and interpretation. It is essential for the generation of detailed and contextually…

A shared goal of several machine learning communities like continual learning, meta-learning and transfer learning, is to design algorithms and models that efficiently and robustly adapt to unseen tasks. An even more ambitious goal is to…

Visual attributes, which refer to human-labeled semantic annotations, have gained increasing popularity in a wide range of real world applications. Generally, the existing attribute learning methods fall into two categories: one focuses on…

Multimodal Large Language Models (MLLMs) are increasingly applied in Personalized Image Aesthetic Assessment (PIAA) as a scalable alternative to expert evaluations. However, their predictions may reflect subtle biases influenced by…

Human pose estimation faces hurdles in real-world applications due to factors like lighting changes, occlusions, and cluttered environments. We introduce a unique RGB-Thermal Nearly Paired and Annotated 2D Pose Dataset, comprising over…

Visual selective attention, driven by individual preferences, regulates human prioritization of visual stimuli by bridging subjective cognitive mechanisms with objective visual elements, thereby steering the semantic interpretation and…

Low-light videos often exhibit spatiotemporally incoherent noise, compromising visibility and degrading performance in computer vision applications. A major challenge for enhancing such content using deep learning lies in the scarcity of…

Multimodal large language models (MLLMs) have demonstrated remarkable abilities in comprehending visual input alongside text input. Typically, these models are trained on extensive data sourced from the internet, which are sufficient for…

Visibility analysis in urban planning has traditionally relied on line-of-sight (LoS) simulations, which capture geometric occlusion. However, these approaches depend on accurate 3D data that is often unavailable and may not adequately…