26 accepted papers
Large vision-language models (LVLMs) achieve impressive performance, yet their internal decision-making processes remain opaque, making it difficult to determine if the success stems from true multimodal fusion or reliance on unimodal priors. To address this attribution gap, we introduce a novel fra…
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 optimization approach for alignment training and employ public rew…
Understanding hand gestures is essential for human communication, yet it remains unclear how well multimodal large language models (MLLMs) comprehend them. In this paper, we examine MLLMs’ ability to interpret indexical gestures, which require external referential grounding, in comparison to iconic…
Controlling diversity in LLM-agent simulations is essential for balancing stability in structured tasks with variability in open-ended interactions. However, we observe that dialogue diversity tends to degrade over long-term simulations. To explore the role of prompt design in this phenomenon, we mo
Recently, Text-to-speech (TTS) models based on large language models (LLMs) that translate natural language text into sequences of discrete audio tokens have gained great research attention, with advances in neural audio codec (NAC) mod- els using residual vector quantization (RVQ). However, long-fo…
Multi-session persona-based dialogue generation presents challenges in maintaining long-term consistency and generating diverse, personalized responses. While large language models (LLMs) excel in single-session dialogues, they struggle to preserve persona fidelity and conversational coherence acros
"3D Gaussian Splatting (3DGS) has shown remarkable success in synthesizing novel views given multiple views of a static scene. Yet, 3DGS faces challenges when applied to dynamic scenes because 3D Gaussian parameters need to be updated per timestep, requiring a large amount of memory and at least a d…
Large language models (LLMs)-based image captioning has the capability of describing objects not explicitly observed in training data; yet novel objects occur frequently necessitating the requirement of sustaining up-to-date object knowledge for open-world comprehension. Instead of relying on large…
"Finding a suitable layout represents a crucial task for diverse applications in graphic design. Motivated by simpler and smoother sampling trajectories, we explore the use of Flow Matching as an alternative to current diffusion-based layout generation models. Specifically, we propose LayoutFlow, an…
Enhancing user engagement through personalization in conversational agents has gained significance, especially with the advent of large language models that generate fluent responses. Personalized dialogue generation, however, is multifaceted and varies in its definition – ranging from instilling a…
Humans possess the capacity to reason about the future based on a sparse collection of visual cues acquired over time. In order to emulate this ability, we introduce a novel task called Anticipation Captioning, which generates a caption for an unseen oracle image using a sparsely temporally-ordered…
Bias mitigation in image classification has been widely researched, and existing methods have yielded notable results. However, most of these methods implicitly assume that a given image contains only one type of known or unknown bias, failing to consider the complexities of real-world biases. We in…
This paper explores the task of Temporal Video Grounding (TVG) where, given an untrimmed video and a query sentence, the goal is to recognize and determine temporal boundaries of action instances in the video described by natural language queries. Recent works tackled this task by improving query in…
Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand long text inputs, and 2) produce a globally consistent image sequence that illustrates the contents of the story. A key…
Novel object captioning aims at describing objects absent from training data, with the key ingredient being the provision of object vocabulary to the model. Although existing methods heavily rely on an object detection model, we view the detection step as vocabulary retrieval from an external knowle…
We introduce a challenging training scheme of conditional GANs, called open-set semi-supervised image generation, where the training dataset consists of two parts: (i) labeled data and (ii) unlabeled data with samples belonging to one of the labeled data classes, namely, a closed-set, and samples no…
A release note is a technical document that describes the latest changes to a software product and is crucial in open source software development. However, it still remains challenging to generate release notes automatically. In this paper, we present a new dataset called RNSum, which contains appro…
Existing automatic story evaluation methods place a premium on story lexical level coherence, deviating from human preference.We go beyond this limitation by considering a novel Story Evaluation method that mimics human preference when judging a story, namely StoryER, which consists of three sub-tas…
Mathematical reasoning task is a subset of the natural language question answering task. Existing work suggested solving this task with a two-phase approach, where the model first predicts formulas from questions and then calculates answers from such formulas. This approach achieved desirable perfor…
Visual storytelling is a task of generating relevant and interesting stories for given image sequences. In this work we aim at increasing the diversity of the generated stories while preserving the informative content from the images. We propose to foster the diversity and informativeness of a gener…
Generating texts in scientific papers requires not only capturing the content contained within the given input but also frequently acquiring the external information called context. We push forward the scientific text generation by proposing a new task, namely context-aware text generation in the sc…
Semantic image synthesis is an image-to-image translation problem where the goal is to learn mapping from semantic segmentation masks to corresponding photorealistic images. However, conventional semantic image synthesis methods require numerous pairs of correct semantic masks and real images, and c…
Recent progress in deep learning has enhanced image classification performance. However, classification using deep convolutional neural networks lacks interpretability. To solve this problem, we propose a novel method of explainable classification; this method uses images representing each image cla…
Data augmentation methods are indispensable heuristics to boost the performance of deep neural networks, especially in image recognition tasks. Recently, several studies have shown that augmentation strategies found by search algorithms outperform hand-made strategies. Such methods employ black-box…
This paper proposed a supervised visual attention mechanism for multimodal neural machine translation (MNMT), trained with constraints based on manual alignments between words in a sentence and their corresponding regions of an image. The proposed visual attention mechanism captures the relationship…
Natural language processing (NLP) models often require a massive number of parameters for word embeddings, resulting in a large storage or memory footprint. Deploying neural NLP models to mobile devices requires compressing the word embeddings without any significant sacrifices in performance. For t…