Wonsuk Yang

Hugo Berg, Siobhan Mackenzie Hall, Yash Bhalgat et al. · oxford

Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we investigate bias measures and apply ranking metrics for image-text representations. We then investigate debiasing methods and show that prepending learned embeddings to text queries that are jointly trained with adversarial debiasing and a contrastive loss reduces various bias measures with minimal degradation to the image-text representation.

Sungjun Han, Juyoung Suk, Suyeong An et al.

We introduce Trillion-7B, the most token-efficient Korean-centric multilingual LLM available. Our novel Cross-lingual Document Attention (XLDA) mechanism enables highly efficient and effective knowledge transfer from English to target languages like Korean and Japanese. Combined with optimized data mixtures, language-specific filtering, and tailored tokenizer construction, Trillion-7B achieves competitive performance while dedicating only 10\% of its 2T training tokens to multilingual data and requiring just 59.4K H100 GPU hours (\$148K) for full training. Comprehensive evaluations across 27 benchmarks in four languages demonstrate Trillion-7B's robust multilingual performance and exceptional cross-lingual consistency.

Chaerin Kong, Seungyong Lee, Soohyeok Im et al.

Image editing has been a long-standing challenge in the research community with its far-reaching impact on numerous applications. Recently, text-driven methods started to deliver promising results in domains like human faces, but their applications to more complex domains have been relatively limited. In this work, we explore the task of fashion style editing, where we aim to manipulate the fashion style of human imagery using text descriptions. Specifically, we leverage a generative human prior and achieve fashion style editing by navigating its learned latent space. We first verify that the existing text-driven editing methods fall short for our problem due to their overly simplified guidance signal, and propose two directions to reinforce the guidance: textual augmentation and visual referencing. Combined with our empirical findings on the latent space structure, our Fashion Style Editing framework (FaSE) successfully projects abstract fashion concepts onto human images and introduces exciting new applications to the field.

Heeseung Yun, Youngjae Yu, Wonsuk Yang et al.

360$^\circ$ videos convey holistic views for the surroundings of a scene. It provides audio-visual cues beyond pre-determined normal field of views and displays distinctive spatial relations on a sphere. However, previous benchmark tasks for panoramic videos are still limited to evaluate the semantic understanding of audio-visual relationships or spherical spatial property in surroundings. We propose a novel benchmark named Pano-AVQA as a large-scale grounded audio-visual question answering dataset on panoramic videos. Using 5.4K 360$^\circ$ video clips harvested online, we collect two types of novel question-answer pairs with bounding-box grounding: spherical spatial relation QAs and audio-visual relation QAs. We train several transformer-based models from Pano-AVQA, where the results suggest that our proposed spherical spatial embeddings and multimodal training objectives fairly contribute to a better semantic understanding of the panoramic surroundings on the dataset.