Yujun Cai

CRAFT-LoRA: Content-Style Personalization via Rank-Constrained Adaptation and Training-Free Fusion CVPR 2026 Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Models ACL 2026 Finding Distributed Object-Centric Properties in Self-Supervised Transformers CVPR 2026 From Scale to Speed: Adaptive Test-Time Scaling for Image Editing CVPR 2026 OmniLottie: Generating Vector Animations via Parameterized Lottie Tokens CVPR 2026 PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs CVPR 2026 SwitchCraft: Training-Free Multi-Event Video Generation with Attention Controls CVPR 2026 VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG ACL 2026 Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding COLING 2025 DiMo-GUI: Advancing Test-time Scaling in GUI Grounding via Modality-Aware Visual Reasoning EMNLP 2025 DRS: Deep Question Reformulation With Structured Output ACL 2025 Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models CVPR 2025 LatentHOI: On the Generalizable Hand Object Motion Generation with Latent Hand Diffusion. CVPR 2025 Learning Few-Step Diffusion Models by Trajectory Distribution Matching ICCV 2025 Making Every Step Effective: Jailbreaking Large Vision-Language Models Through Hierarchical KV Equalization EMNLP 2025 Mapping the Minds of LLMs: A Graph-Based Analysis of Reasoning LLMs EMNLP 2025 MRFD: Multi-Region Fusion Decoding with Self-Consistency for Mitigating Hallucinations in LVLMs EMNLP 2025 SemVink: Advancing VLMs’ Semantic Understanding of Optical Illusions via Visual Global Thinking EMNLP 2025 Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack NAACL 2025 Understanding GUI Agent Localization Biases through Logit Sharpness EMNLP 2025 VistaWise: Building Cost-Effective Agent with Cross-Modal Knowledge Graph for Minecraft EMNLP 2025 Vulnerability of LLMs to Vertically Aligned Text Manipulations ACL 2025 6D-Diff: A Keypoint Diffusion Framework for 6D Object Pose Estimation CVPR 2024 DisC-GS: Discontinuity-aware Gaussian Splatting NeurIPS 2024 emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation NeurIPS 2024 Energy-Clibrated VAE with Test Time Free Lunch ECCV 2024 LLMs are Good Action Recognizers CVPR 2024 A Characteristic Function-Based Method for Bottom-Up Human Pose Estimation CVPR 2023 How Fragile is Relation Extraction under Entity Replacements? CoNLL 2023 LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition NeurIPS 2023 Primacy Effect of ChatGPT EMNLP 2023 Social Diffusion: Long-term Multiple Human Motion Anticipation ICCV 2023 Geometry-Guided Progressive NeRF for Generalizable and Efficient Neural Human Rendering ECCV 2022 GraphCache: Message Passing as Caching for Sentence-Level Relation Extraction NAACL 2022 Heatmap Distribution Matching for Human Pose Estimation NeurIPS 2022 Should We Rely on Entity Mentions for Relation Extraction? Debiasing Relation Extraction with Counterfactual Analysis NAACL 2022 Adaptive Data Augmentation on Temporal Graphs NeurIPS 2021 A Unified 3D Human Motion Synthesis Model via Conditional Variational Auto-Encoder ICCV 2021 Direct Multi-view Multi-person 3D Pose Estimation NeurIPS 2021 DeepEMD: Few-Shot Image Classification With Differentiable Earth Mover's Distance and Structured Classifiers CVPR 2020 Learning Progressive Joint Propagation for Human Motion Prediction ECCV 2020 Exploiting Spatial-Temporal Relationships for 3D Pose Estimation via Graph Convolutional Networks ICCV 2019 Hand PointNet: 3D Hand Pose Estimation Using Point Sets CVPR 2018 Weakly-supervised 3D Hand Pose Estimation from Monocular RGB Images ECCV 2018