13 papers
PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration
Chen-Yu Lin, Jing-Wen Chen, Hsueh-En Chang +8
We present PhysCaP, a Physics-Informed Code-as-Policy agent system for active perception in robotic manipulation. While vision-language-action policies excel at imitating demonstra…
Robust Deepfake Detection, NTIRE 2026 Challenge: Report
Benedikt Hopf, Radu Timofte, Chenfan Qu +54
Robustness is a long-overlooked problem in deepfake detection. However, detection performance is nearly worthless in the real world if it suffers under exposure to even slight imag…
CANDLE: Illumination-Invariant Semantic Priors for Color Ambient Lighting Normalization
Rong-Lin Jian, Ting-Yao Chen, Yu-Fan Lin +4
Color ambient lighting normalization under multi-colored illumination is challenging due to severe chromatic shifts, highlight saturation, and material-dependent reflectance. Exist…
NTIRE 2026 Challenge on Single Image Reflection Removal in the Wild: Datasets, Results, and Methods
Jie Cai, Kangning Yang, Zhiyuan Li +50
In this paper, we review the NTIRE 2026 challenge on single-image reflection removal (SIRR) in the wild. SIRR is a fundamental task in image restoration. Despite progress in academ…
Frequency Switching Mechanism for Parameter-E!cient Multi-Task Learning
Shih-Wen Liu, Yen-Chang Chen, Wei-Ta Chu +2
Multi-task learning (MTL) aims to enable a single model to solve multiple tasks efficiently; however, current parameter-efficient fine-tuning (PEFT) methods remain largely limited…
VISTA: Validation-Guided Integration of Spatial and Temporal Foundation Models with Anatomical Decoding for Rare-Pathology VCE Event Detection
Bo-Cheng Qiu, Yu-Fan Lin, Yu-Zhe Pien +4
Capsule endoscopy event detection is challenging because diagnostically relevant findings are sparse, visually heterogeneous, and embedded in long, noisy video streams, while evalu…
Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning
Chi-Pin Huang, Yunze Man, Zhiding Yu +4
Vision-Language-Action (VLA) tasks require reasoning over complex visual scenes and executing adaptive actions in dynamic environments. While recent studies on reasoning VLAs show…
TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors
Wei-Yuan Cheng, Kai-Po Chang, Chi-Pin Huang +2
Dense video captioning aims to interpret and describe all temporally localized events throughout an input video. Recent state-of-the-art methods leverage large language models (LLM…
ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
Chi-Pin Huang, Yueh-Hua Wu, Min-Hung Chen +2
Vision-language-action (VLA) reasoning tasks require agents to interpret multimodal instructions, perform long-horizon planning, and act adaptively in dynamic environments. Existin…
Histopathology Image Report Generation by Vision Language Model with Multimodal In-Context Learning
Shih-Wen Liu, Hsuan-Yu Fan, Wei-Ta Chu +2
Automating medical report generation from histopathology images is a critical challenge requiring effective visual representations and domain-specific knowledge. Inspired by the co…
VideoMage: Multi-Subject and Motion Customization of Text-to-Video Diffusion Models
Chi-Pin Huang, Yen-Siang Wu, Hung-Kai Chung +3
Customized text-to-video generation aims to produce high-quality videos that incorporate user-specified subject identities or motion patterns. However, existing methods mainly focu…
MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching
Yen-Siang Wu, Chi-Pin Huang, Fu-En Yang +1
Text-to-video (T2V) diffusion models have shown promising capabilities in synthesizing realistic videos from input text prompts. However, the input text description alone provides…
PromptHSI: Universal Hyperspectral Image Restoration with Vision-Language Modulated Frequency Adaptation
Chia-Ming Lee, Ching-Heng Cheng, Yu-Fan Lin +5
Recent advances in All-in-One (AiO) RGB image restoration have demonstrated the effectiveness of prompt learning in handling multiple degradations within a single model. However, e…