1 citations · 1 across the 16 of their papers we have counts for
17 papers
Fine-Grained Multi Image Object Hallucination Benchmark
Joonki Min, Chaeyun Kim, Hyungwook Choi +4
Multimodal Large Language Models (MLLMs) are increasingly deployed in multi-image scenarios requiring complex reasoning across visual contexts. However, current MLLMs remain fundam…
Domain Generalization via Text-Anchored Information Bottleneck
Eunyi Lyou, Yunjeong Choi, Junho Lee +1
Visual recognition models often fail when deployed in new environments. Domain Generalization (DG) addresses this by learning representations that remain invariant to environment-s…
Generative Modeling of Quantum Distribution with Functional Flow Matching
Jaehoon Hahm, Tak Hur, Joonseok Lee +1
The emergence of powerful deep generative models based on diffusion and flow matching has enabled the learning and modeling of complex distributions. Learning quantum distributions…
Equivariant Latent Alignment via Flow Matching under Group Symmetries
Sunghyun Kim, Jaehoon Hahm, Jeongwoo Shin +1
Geometry-aware generative models and novel view synthesis approaches have shown strong potential in visual fidelity and consistency. In parallel, equivariant representation learnin…
EVIDENT: Routing MLLM Adaptation through Entity-Grounded Visual Evidence for Cross-Domain Video Temporal Grounding
Geo Ahn, Jiwook Han, Youngrae Kim +2
Fine-tuning MLLMs for Video Temporal Grounding (VTG) often improves in-domain performance but degrades sharply under domain shift. In this work, we find that this failure is primar…
Geometry-Aware Image Flow Matching
Junho Lee, Kwanseok Kim, Joonseok Lee
Recent advances in generative models highlight the power of geometry-aware modeling in manifold-constrained settings. Yet, for natural images, the field remains confined to Euclide…
ArtSplat: Feed-Forward Articulated 3D Gaussian Splatting from Sparse Multi-State Uncalibrated Views
Inseo Lee, Yoonji Kim, Eugene Sohn +4
Articulated object reconstruction from sparse-view images is an ill-posed problem that requires simultaneous inference of geometry and underlying articulation structure. Existing m…
A More Word-like Image Tokenization for MLLMs
Hyun Lee, Hyemin Jeong, Yejin Kim +4
Modern multimodal large language models (MLLMs) typically keep the language model fixed and train a visual projector that maps the pixels into a sequence of tokens in its embedding…
Efficient Adjoint Matching for Fine-tuning Diffusion Models
Jeongwoo Shin, Dongsoo Shin, Yuchen Zhu +5
Reward fine-tuning has become a common approach for aligning pretrained diffusion and flow models with human preferences in text-to-image generation. Among reward-gradient-based me…
Towards Motion-aware Referring Image Segmentation
Chaeyun Kim, Seunghoon Yi, Yejin Kim +2
Referring Image Segmentation (RIS) requires identifying objects from images based on textual descriptions. We observe that existing methods significantly underperform on motion-rel…
Is There a Better Source Distribution than Gaussian? Exploring Source Distributions for Image Flow Matching
Junho Lee, Kwanseok Kim, Joonseok Lee
Flow matching has emerged as a powerful generative modeling approach with flexible choices of source distribution. While Gaussian distributions are commonly used, the potential for…
Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs
Hyungjin Chung, Hyelin Nam, Jiyeon Kim +6
Video Large Language Models (VideoLLMs) face a critical bottleneck: increasing the number of input frames to capture fine-grained temporal detail leads to prohibitive computational…
Self-Guided Masked Autoencoder
Jeongwoo Shin, Inseo Lee, Junho Lee +1
Masked Autoencoder (MAE) is a self-supervised approach for representation learning, widely applicable to a variety of downstream tasks in computer vision. In spite of its success,…
Latent Diffusion Models with Masked AutoEncoders
Junho Lee, Jeongwoo Shin, Hyungwook Choi +1
In spite of the remarkable potential of Latent Diffusion Models (LDMs) in image generation, the desired properties and optimal design of the autoencoders have been underexplored. I…
Finding NeMo: Negative-mined Mosaic Augmentation for Referring Image Segmentation
Seongsu Ha, Chaeyun Kim, Donghwa Kim +3
Referring Image Segmentation is a comprehensive task to segment an object referred by a textual query from an image. In nature, the level of difficulty in this task is affected by…
Scalable Frame Sampling for Video Classification: A Semi-Optimal Policy Approach with Reduced Search Space
Junho Lee, Jeongwoo Shin, Seung Woo Ko +2
Given a video with frames, frame sampling is a task to select frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but…
Isometric Representation Learning for Disentangled Latent Space of Diffusion Models
Jaehoon Hahm, Junho Lee, Sunghyun Kim +1
The latent space of diffusion model mostly still remains unexplored, despite its great success and potential in the field of generative modeling. In fact, the latent space of exist…