58 citations · 153 across the 66 of their papers we have counts for
76 papers
Dynamic self-ensemble on multi-exit residual vision transformer for small-data image classification
Stephen Ekaputra Limantoro, Yan-Kai Wang, Ching-Chun Huang +4
Vision Transformer (ViT) has garnered increased attention for image classification in recent years. However, ViT is notorious for its data-hungry problem as it achieves high-perfor…
Beyond Token Revision: Investigating Mask-and-Replace Diffusion for Zero-Shot Text-to-Speech
Hounsu Kim, Joonyong Park, Yuki Saito +2
Unlike autoregressive models, discrete diffusion-based models for zero-shot text-to-speech generate speech tokens in parallel and can revisit earlier predictions. Mask-and-replace…
Look Before You Judge: Training-Free Region Mining for Grounded and Explainable Deepfake Detection
Chia-Ling Chen, Yu-Ting Ta, Jian-Yu Jiang-Lin +8
Multimodal large language models (MLLMs) can explain deepfake verdicts in natural language, but such explanations are not necessarily visually grounded in the visual evidence under…
HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer Reviews
Tzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao +2
The growing scale of academic peer review has motivated the use of Large Language Models (LLMs) as review assistants, yet LLMs can generate fluent but unsupported claims that under…
RADIANCE: Relative Adaptive Denoising with IP-Adapter for Novel Concept Enhancement
Zi-Xiang Ni, Bo-Lun Huang, Teng-Fang Hsiao +2
Text-to-image (T2I) diffusion models have achieved striking progress but still struggle to synthesize rare concepts involving unusual attribute-object pairings, often resulting in…
IDAG-Edit: Multi-Object Video Editing via Instance-Decoupled Attention and Guidance
Yuan-Zhih Lin, Huu-Thang Nguyen, Huu-Phu Do +2
Diffusion-based video editing has made significant progress; however, achieving precise and temporally consistent object-level control, especially in multi-object scenarios, remain…
HyperPatch: Sequential Knowledge Editing Under n-ary Structural Drift
Yu-Kai Chan, Wen-Sheng Lien, Dong-Ting Yao +4
Large Language Models (LLMs) rely on Knowledge Editing (KE) to maintain temporal validity, yet real-world knowledge is inherently n-ary. We demonstrate that in non-stationary envir…
Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Models
Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +1
World Action Models (WAMs) enable decision-making through imagined rollouts by predicting future observations and actions. However, the reliability of these imagined futures remain…
HyperRAG: Reasoning N-ary Facts over Hypergraphs for Retrieval Augmented Generation
Wen-Sheng Lien, Yu-Kai Chan, Hao-Lung Hsiao +5
Graph-based retrieval-augmented generation (RAG) methods, typically built on knowledge graphs (KGs) with binary relational facts, have shown promise in multi-hop open-domain QA. Ho…
VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
Teng-Fang Hsiao, Bo-Kai Ruan, Yu-Lun Liu +1
3D editing has emerged as a critical research area to provide users with flexible control over 3D assets. While current editing approaches predominantly focus on 3D Gaussian Splatt…
CookAnything: A Framework for Flexible and Consistent Multi-Step Recipe Image Generation
Ruoxuan Zhang, Bin Wen, Hongxia Xie +5
Cooking is a sequential and visually grounded activity, where each step such as chopping, mixing, or frying carries both procedural logic and visual semantics. While recent diffusi…
COACH: Collaborative Agents for Contextual Highlighting -- A Multi-Agent Framework for Sports Video Analysis
Tsz-To Wong, Ching-Chun Huang, Hong-Han Shuai
Intelligent sports video analysis demands a comprehensive understanding of temporal context, from micro-level actions to macro-level game strategies. Existing end-to-end models oft…
TriDF: Evaluating Perception, Detection, and Hallucination for Interpretable DeepFake Detection
Jian-Yu Jiang-Lin, Kang-Yang Huang, Ling Zou +11
Advances in generative modeling have made it increasingly easy to fabricate realistic portrayals of individuals, creating serious risks for security, communication, and public trus…
DNA: Dual-branch Network with Adaptation for Open-Set Online Handwriting Generation
Tsai-Ling Huang, Nhat-Tuong Do-Tran, Ngoc-Hoang-Lam Le +2
Online handwriting generation (OHG) enhances handwriting recognition models by synthesizing diverse, human-like samples. However, existing OHG methods struggle to generate unseen c…
DetailSemNet: Elevating Signature Verification through Detail-Semantic Integration
Meng-Cheng Shih, Tsai-Ling Huang, Yu-Heng Shih +4
Offline signature verification (OSV) is a frequently utilized technology in forensics. This paper proposes a new model, DetailSemNet, for OSV. Unlike previous methods that rely on…
Arbitrary-Resolution and Arbitrary-Scale Face Super-Resolution with Implicit Representation Networks
Yi Ting Tsai, Yu Wei Chen, Hong-Han Shuai +1
Face super-resolution (FSR) is a critical technique for enhancing low-resolution facial images and has significant implications for face-related tasks. However, existing FSR method…
Diversifying Long Prompt Image Generation through Structured Prompt Embedding Space Sampling
Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo +2
Modern text-to-image models produce impressive visual results from richly specified prompts, yet their behavior under long prompts remains insufficiently understood. In this paper,…
Ranking-based Preference Optimization for Diffusion Models from Implicit User Feedback
Yi-Lun Wu, Bo-Kai Ruan, Chiang Tseng +1
Direct preference optimization (DPO) methods have shown strong potential in aligning text-to-image diffusion models with human preferences by training on paired comparisons. These…
Enhancing Robustness in Post-Processing Watermarking: An Ensemble Attack Network Using CNNs and Transformers
Tzuhsuan Huang, Cheng Yu Yeo, Tsai-Ling Huang +3
Recent studies on deep watermarking have predominantly focused on in-processing watermarking, which integrates the watermarking process into image generation. However, post-process…
Color Me Correctly: Bridging Perceptual Color Spaces and Text Embeddings for Improved Diffusion Generation
Sung-Lin Tsai, Bo-Lun Huang, Yu Ting Shen +5
Accurate color alignment in text-to-image (T2I) generation is critical for applications such as fashion, product visualization, and interior design, yet current diffusion models st…
RecipeGen: A Step-Aligned Multimodal Benchmark for Real-World Recipe Generation
Ruoxuan Zhang, Jidong Gao, Bin Wen +4
Creating recipe images is a key challenge in food computing, with applications in culinary education and multimodal recipe assistants. However, existing datasets lack fine-grained…
Breaking the Reviewer: Assessing the Vulnerability of Large Language Models in Automated Peer Review Under Textual Adversarial Attacks
Tzu-Ling Lin, Wei-Chih Chen, Teng-Fang Hsiao +7
Peer review is essential for maintaining academic quality, but the increasing volume of submissions places a significant burden on reviewers. Large language models (LLMs) offer pot…
Score Replacement with Bounded Deviation for Rare Prompt Generation
Bo-Kai Ruan, Zi-Xiang Ni, Bo-Lun Huang +2
Diffusion models achieve impressive performance in high-fidelity image generation but often struggle with rare concepts that appear infrequently in the training distribution. Prior…
Swapped Logit Distillation via Bi-level Teacher Alignment
Stephen Ekaputra Limantoro, Jhe-Hao Lin, Chih-Yu Wang +4
Knowledge distillation (KD) compresses the network capacity by transferring knowledge from a large (teacher) network to a smaller one (student). It has been mainstream that the tea…