3 citations · 4 across the 16 of their papers we have counts for
19 papers
Latent World Action Model for GUI Agents
Seungjun Yu, Hojun Choi, Seojeong Park +2
Pixel-space world models have recently emerged as a promising approach for GUI agents, predicting future screens prior to execution and subsequently re-perceiving them for action s…
MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
Hojun Choi, Jaeyo Shin, Suin Lee +1
Agentic systems powered by large language models (LLMs) have opened new opportunities for business ideation. Yet existing approaches remain confined to a text-only paradigm, despit…
Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
Hojun Choi, Seulbin Hwang, Daejung Kim +3
Bird's-eye view (BEV) perception fuses multi-camera images into a unified top-down representation for autonomous driving. Despite recent progress, state-of-the-art methods remain c…
Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views
Jiho Choi, Seonho Lee, Seojeong Park +1
Multi-view 3D Visual Question Answering (MV3D-VQA) requires integrating partial observations into a coherent 3D scene representation and selecting informative viewpoints for multi-…
The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms
Lingdong Kong, Shaoyuan Xie, Zeying Gong +135
Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under…
SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
Wonjeong Ryu, Seungjun Yu, Seokha Moon +4
End-to-End (E2E) planning has become a powerful paradigm for autonomous driving, yet current systems remain fundamentally uncertainty-blind. They assume perception outputs are full…
Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
Inha Kang, Eunki Kim, Wonjeong Ryu +7
Accurate long horizon forecasting of particulate matter (PM) concentration fields is essential for operational public health decisions. However, achieving reliable forecasts remain…
WaymoQA: A Multi-View Visual Question Answering Dataset for Safety-Critical Reasoning in Autonomous Driving
Seungjun Yu, Seonho Lee, Namho Kim +5
Recent advancements in multimodal large language models (MLLMs) have shown strong understanding of driving scenes, drawing interest in their application to autonomous driving. Howe…
Robust Driving QA through Metadata-Grounded Context and Task-Specific Prompts
Seungjun Yu, Junsung Park, Youngsun Lim +1
We present a two-phase vision-language QA system for autonomous driving that answers high-level perception, prediction, and planning questions. In Phase-1, a large multimodal LLM (…
MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
Hojun Choi, Youngsun Lim, Jaeyo Shin +1
Open-vocabulary object detection (OVD) aims to recognize and localize object categories beyond the training set. Recent approaches leverage vision-language models to generate pseud…
What "Not" to Detect: Negation-Aware VLMs via Structured Reasoning and Token Merging
Inha Kang, Youngsun Lim, Seonho Lee +3
State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly seve…
Prompt the Unseen: Evaluating Visual-Language Alignment Beyond Supervision
Raehyuk Jung, Seungjun Yu, Hyunjung Shim
Vision-Language Models (VLMs) combine a vision encoder and a large language model (LLM) through alignment training, showing strong performance on multimodal tasks. A central compon…
No Thing, Nothing: Highlighting Safety-Critical Classes for Robust LiDAR Semantic Segmentation in Adverse Weather
Junsung Park, Hwijeong Lee, Inha Kang +1
Existing domain generalization methods for LiDAR semantic segmentation under adverse weather struggle to accurately predict "things" categories compared to "stuff" categories. In t…
Sampling Bag of Views for Open-Vocabulary Object Detection
Hojun Choi, Junsuk Choe, Hyunjung Shim
Existing open-vocabulary object detection (OVD) develops methods for testing unseen categories by aligning object region embeddings with corresponding VLM features. A recent study…
Label-Augmented Dataset Distillation
Seoungyoon Kang, Youngsun Lim, Hyunjung Shim
Traditional dataset distillation primarily focuses on image representation while often overlooking the important role of labels. In this study, we introduce Label-Augmented Dataset…
Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering
Youngsun Lim, Hojun Choi, Hyunjung Shim
Despite the impressive success of text-to-image (TTI) generation models, existing studies overlook the issue of whether these models accurately convey factual information. In this…
Rethinking Data Augmentation for Robust LiDAR Semantic Segmentation in Adverse Weather
Junsung Park, Kyungmin Kim, Hyunjung Shim
Existing LiDAR semantic segmentation methods often struggle with performance declines in adverse weather conditions. Previous work has addressed this issue by simulating adverse we…
Addressing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval
Youngsun Lim, Hyunjung Shim
Text-to-image generation has shown remarkable progress with the emergence of diffusion models. However, these models often generate factually inconsistent images, failing to accura…
Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation
Junsung Park, Hyunjung Shim
Weakly Supervised Semantic Segmentation (WSSS) employs weak supervision, such as image-level labels, to train the segmentation model. Despite the impressive achievement in recent W…