Related papers: DesignPref: Capturing Personal Preferences in Visu…

Sequential recommendation is dedicated to offering items of interest for users based on their history behaviors. The attribute-opinion pairs, expressed by users in their reviews for items, provide the potentials to capture user preferences…

Common image editing tasks typically adopt powerful generative diffusion models as the leading paradigm for real-world content editing. Meanwhile, although reinforcement learning (RL) methods such as Diffusion-DPO and Flow-GRPO have further…

Sequential recommendation aims at understanding user preference by capturing successive behavior correlations, which are usually represented as the item purchasing sequences based on their past interactions. Existing efforts generally…

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…

People have different creative writing preferences, and large language models (LLMs) for these tasks can benefit from adapting to each user's preferences. However, these models are often trained over a dataset that considers varying…

Personalisation is a standard feature of conversational AI systems used by millions; yet, the efficacy of personalisation methods is often evaluated in academic research using simulated users rather than real people. This raises questions…

Recent advancements in Natural Language Processing (NLP) have led to the development of NLP-based recommender systems that have shown superior performance. However, current models commonly treat items as mere IDs and adopt discriminative…

Language models serve as proxies for human preference judgements in alignment and evaluation, yet they exhibit systematic miscalibration, prioritizing superficial patterns over substantive qualities. This bias manifests as overreliance on…

We have recently seen great progress in image classification due to the success of deep convolutional neural networks and the availability of large-scale datasets. Most of the existing work focuses on single-label image classification.…

Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset and not the actual user and their past visualization feedback. These systems recommend the same visualizations for every user,…

Effective collaboration between designers and users is important for fashion design, which can increase the user acceptance of fashion products and thereby create value. However, it remains an enduring challenge, as traditional…

The ability to estimate the perceptual error between images is an important problem in computer vision with many applications. Although it has been studied extensively, however, no method currently exists that can robustly predict visual…

Aligning LLM-based judges with human preferences is a significant challenge, as they are difficult to calibrate and often suffer from rubric sensitivity, bias, and instability. Overcoming this challenge advances key applications, such as…

This paper investigates image inpainting with preference alignment. Instead of introducing a novel method, we go back to basics and revisit fundamental problems in achieving such alignment. We leverage the prominent direct preference…

In automated UI design generation, a key challenge is the lack of support for iterative processes, as most systems focus solely on end-to-end output. This stems from limited capabilities in interpreting design intent and a lack of…

The emergence of large language models (LLMs) has revolutionized the capabilities of text comprehension and generation. Multi-modal generation attracts great attention from both the industry and academia, but there is little work on…

Conventional algorithms for training language models (LMs) with human feedback rely on preferences that are assumed to account for an "average" user, disregarding subjectivity and finer-grained variations. Recent studies have raised…

Following the initial excitement, Text-to-Image (TTI) models are now being examined more critically. While much of the discourse has focused on biases and stereotypes embedded in large-scale training datasets, the sociotechnical dynamics of…

Smart assistants increasingly act proactively, yet mistimed or intrusive behavior often causes users to lose trust and disable these features. Learning user preferences for proactive assistance is difficult because real-world studies are…

Personalized image generation via text prompts has great potential to improve daily life and professional work by facilitating the creation of customized visual content. The aim of image personalization is to create images based on a…