19 papers
When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object Segmentation
Jihwan Hong, Woohyeon Park, Jaeik Kim +1
Video Object Segmentation (VOS) in complex and long videos is increasingly important for real-world applications, where target objects often appear only intermittently within long…
What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation
Sieun Hyeon, Yejoon Lee, Mintaek Lim +3
Omnimodal evaluation should go beyond independent text, image, and speech production: individually plausible outputs may not express a coherent shared event. We introduce Omni-Stor…
Dynin-Robotics: Omnimodal Unified Diffusion Vision-Language-Action Model
Hoeun Lee, Jaeik Kim, Jusang Oh +4
Visual goal and dynamics prediction can provide language-conditioned robot policies with both a target outcome and a representation of action-dependent scene changes. We bring thes…
Unified Static-Dynamic Pruning for Efficient LLM Inference
Jinhyeok Kim, Yejoon Lee, Jaeyoung Do
The increasing deployment of large language models (LLMs) has magnified the computational and memory bottlenecks of autoregressive decoding, where low compute intensity and bandwid…
SUM: Unified Geometric Surgery on Spatio-Temporal Adaptation Vectors for Federated Class Incremental Learning
Jaeik Kim, Jaeyoung Do
Real-world intelligent systems often require both distributed collaboration across data-isolated clients and continual adaptation to evolving tasks. This setting naturally gives ri…
MI-CXR: A Benchmark for Longitudinal Reasoning over Multi-Interval Chest X-rays
Sunghwan Steve Cho, Yunseok Han, Jaeyoung Do
Longitudinal chest X-ray (CXR) interpretation requires reasoning over disease evolution across multiple patient visits, yet most existing medical VQA benchmarks focus on single ima…
Report of the 5th PVUW Challenge: Towards More Diverse Modalities in Pixel-Level Understanding
Chang Liu, Henghui Ding, Nikhila Ravi +40
This report summarizes the objectives, datasets, and top-performing methodologies of the 2026 Pixel-level Video Understanding in the Wild (PVUW) Challenge, hosted at CVPR 2026, whi…
VIRST: Video-Instructed Reasoning Assistant for SpatioTemporal Segmentation
Jihwan Hong, Jaeyoung Do
Referring Video Object Segmentation (RVOS) aims to segment target objects in videos based on natural language descriptions. However, fixed keyframe-based approaches that couple a v…
3rd Place of MeViS-Audio Track of the 5th PVUW: VIRST-Audio
Jihwan Hong, Jaeyoung Do
Audio-based Referring Video Object Segmentation (ARVOS) requires grounding audio queries into pixel-level object masks over time, posing challenges in bridging acoustic signals wit…
Dynin-Omni: Omnimodal Unified Large Diffusion Language Model
Jaeik Kim, Woojin Kim, Jihwan Hong +8
We present Dynin-Omni, the first masked-diffusion-based omnimodal foundation model that unifies text, image, and speech understanding and generation, together with video understand…
MEDIC-AD: Towards Medical Vision-Language Model's Clinical Intelligence
Woohyeon Park, Jaeik Kim, Sunghwan Steve Cho +7
Lesion detection, symptom tracking, and visual explainability are central to real-world medical image analysis, yet current medical Vision-Language Models (VLMs) still lack mechani…
RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
Yunseok Han, Yejoon Lee, Jaeyoung Do
Large Reasoning Models (LRMs) exhibit strong performance, yet often produce rationales that sound plausible but fail to reflect their true decision process, undermining reliability…
MATA: Multi-Agent Framework for Reliable and Flexible Table Question Answering
Sieun Hyeon, Jusang Oh, Sunghwan Steve Cho +1
Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring…
VALUEFLOW: Toward Pluralistic and Steerable Value-based Alignment in Large Language Models
Woojin Kim, Sieun Hyeon, Jusang Oh +1
Aligning Large Language Models (LLMs) with the diverse spectrum of human values remains a central challenge: preference-based methods often fail to capture deeper motivational prin…
Don't Let It Fade: Preserving Edits in Diffusion Language Models via Token Timestep Allocation
Woojin Kim, Jaeyoung Do
While diffusion language models (DLMs) enable fine-grained refinement, their practical controllability remains fragile. We identify and formally characterize a central failure mode…
Exploring and Leveraging Class Vectors for Classifier Editing
Jaeik Kim, Jaeyoung Do
Image classifiers play a critical role in detecting diseases in medical imaging and identifying anomalies in manufacturing processes. However, their predefined behaviors after exte…
MMPB: It's Time for Multi-Modal Personalization
Jaeik Kim, Woojin Kim, Woohyeon Park +1
Visual personalization is essential in user-facing AI systems such as smart homes and healthcare, where aligning model behavior with user-centric concepts is critical. However, rec…
SECOND: Mitigating Perceptual Hallucination in Vision-Language Models via Selective and Contrastive Decoding
Woohyeon Park, Woojin Kim, Jaeik Kim +1
Despite significant advancements in Vision-Language Models (VLMs), the performance of existing VLMs remains hindered by object hallucination, a critical challenge to achieving accu…
Aligning Large Language Models via Fine-grained Supervision
Dehong Xu, Liang Qiu, Minseok Kim +2
Pre-trained large-scale language models (LLMs) excel at producing coherent articles, yet their outputs may be untruthful, toxic, or fail to align with user expectations. Current ap…