3 citations · 5 across the 17 of their papers we have counts for
19 papers
Preference Is Not Permission: Personalizing the Auto-Purchase Line in Agentic Commerce
Ryotaro Shimizu, Sai HtaungKham, Mo Fan
Personalized shopping benchmarks ask which item fits the user; we ask how far an agent may commit on that item, and pose learning the individual's auto-purchase line as a task. The…
Introspecting Alignment Shifts Beyond Behaviors Implanted Through Fine-Tuning
Kotaro Yoshida, Laura Gomezjurado Gonzalez, Yukinori Yamamoto +3
Fine-tuning enables a source model to acquire desired capabilities and behaviors in a target domain while retaining much of its general-purpose competence. However, this adaptation…
ZoRRO: A Zero-Weight Personalized Recommender System for Scalable News Recommendation
Johannes Kruse, Ryotaro Shimizu, Kasper Lindskow +4
We present ZoRRO (Zero-Weight Personalized Recommender System), a zero-weight, training-free framework for personalized news recommendation designed for scalable real-world deploym…
MultiEmo-Bench: Multi-label Visual Emotion Analysis for Multi-modal Large Language Models
Tianwei Chen, Takuya Furusawa, Yuki Hirakawa +3
This paper introduces a multi-label visual emotion analysis benchmark dataset for comprehensively evaluating the ability of multimodal large language models (MLLMs) to predict the…
Reference-Free Image Quality Assessment for Virtual Try-On via Human Feedback
Yuki Hirakawa, Takashi Wada, Ryotaro Shimizu +6
As virtual try-on (VTON) systems become increasingly important in fashion e-commerce, there is a growing need for reliable reference-free evaluation methods, since ground-truth ima…
DisTaC: Conditioning Task Vectors via Distillation for Robust Model Merging
Kotaro Yoshida, Yuji Naraki, Takafumi Horie +2
Model merging has emerged as an efficient and flexible paradigm for multi-task learning, with numerous methods being proposed in recent years. However, these state-of-the-art techn…
Transferring Visual Explainability of Self-Explaining Models to Prediction-Only Models without Additional Training
Yuya Yoshikawa, Ryotaro Shimizu, Takahiro Kawashima +1
In image classification scenarios where both prediction and explanation efficiency are required, self-explaining models that perform both tasks in a single inference are effective.…
Static Word Embeddings for Sentence Semantic Representation
Takashi Wada, Yuki Hirakawa, Ryotaro Shimizu +2
We propose new static word embeddings optimised for sentence semantic representation. We first extract word embeddings from a pre-trained Sentence Transformer, and improve them wit…
On Fairness of Task Arithmetic: The Role of Task Vectors
Hiroki Naganuma, Kotaro Yoshida, Laura Gomezjurado Gonzalez +3
Model editing techniques, particularly task arithmetic with task vectors, offer an efficient alternative to full fine-tuning by enabling direct parameter updates through simple ari…
Masked Language Prompting for Generative Data Augmentation in Few-shot Fashion Style Recognition
Yuki Hirakawa, Ryotaro Shimizu
Constructing dataset for fashion style recognition is challenging due to the inherent subjectivity and ambiguity of style concepts. Recent advances in text-to-image models have fac…
Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base
Linxin Song, Xuwei Ding, Jieyu Zhang +6
Large language models (LLMs) possess impressive linguistic capabilities but often fail to faithfully retain factual knowledge, leading to hallucinations and unreliable outputs. Und…
Fashionability-Enhancing Outfit Image Editing with Conditional Diffusion Models
Qice Qin, Yuki Hirakawa, Ryotaro Shimizu +2
Image generation in the fashion domain has predominantly focused on preserving body characteristics or following input prompts, but little attention has been paid to improving the…
Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model
Shijian Wang, Linxin Song, Jieyu Zhang +9
Current multimodal language model (MLM) training approaches overlook the influence of instruction templates. Previous research deals with this problem by leveraging hand-crafted or…
An Empirical Analysis of GPT-4V's Performance on Fashion Aesthetic Evaluation
Yuki Hirakawa, Takashi Wada, Kazuya Morishita +4
Fashion aesthetic evaluation is the task of estimating how well the outfits worn by individuals in images suit them. In this work, we examine the zero-shot performance of GPT-4V on…
Disentangling Likes and Dislikes in Personalized Generative Explainable Recommendation
Ryotaro Shimizu, Takashi Wada, Yu Wang +9
Recent research on explainable recommendation generally frames the task as a standard text generation problem, and evaluates models simply based on the textual similarity between t…
A Fashion Item Recommendation Model in Hyperbolic Space
Ryotaro Shimizu, Yu Wang, Masanari Kimura +4
In this work, we propose a fashion item recommendation model that incorporates hyperbolic geometry into user and item representations. Using hyperbolic space, our model aims to cap…
Explaining Black-box Model Predictions via Two-level Nested Feature Attributions with Consistency Property
Yuya Yoshikawa, Masanari Kimura, Ryotaro Shimizu +1
Techniques that explain the predictions of black-box machine learning models are crucial to make the models transparent, thereby increasing trust in AI systems. The input features…
Augmenting NER Datasets with LLMs: Towards Automated and Refined Annotation
Yuji Naraki, Ryosuke Yamaki, Yoshikazu Ikeda +4
In the field of Natural Language Processing (NLP), Named Entity Recognition (NER) is recognized as a critical technology, employed across a wide array of applications. Traditional…
On permutation-invariant neural networks
Masanari Kimura, Ryotaro Shimizu, Yuki Hirakawa +2
Conventional machine learning algorithms have traditionally been designed under the assumption that input data follows a vector-based format, with an emphasis on vector-centric par…