Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
CorrFill: Enhancing Faithfulness in Reference-Based Inpainting with Correspondence Guidance in Diffusion ModelsNVIDIA · IEEE Winter Conference on Applications of Computer Vision10 citationsFeb 26, 2025Elucidating Optimal Reward-Diversity Tradeoffs in Text-to-Image Diffusion ModelsNVIDIA · IEEE Winter Conference on Applications of Computer Vision10 citationsFeb 26, 2025EgoCast: Forecasting Egocentric Human Pose in the WildGoogle DeepMind · IEEE Winter Conference on Applications of Computer Vision9 citationsFeb 26, 2025LoSA: Long-Short-Range Adapter for Scaling End-to-End Temporal Action LocalizationMicrosoft · IEEE Winter Conference on Applications of Computer Vision9 citationsFeb 26, 2025ORFormer: Occlusion-Robust Transformer for Accurate Facial Landmark DetectionNVIDIA · IEEE Winter Conference on Applications of Computer Vision9 citationsFeb 26, 2025AUCPro: AUC-Oriented Provable Robustness LearningAlibaba · IEEE Transactions on Pattern Analysis and Machine Intelligence8 citationsFeb 26, 2025Nexus: An Omni-Perceptive And -Interactive Model for Language, Audio, And VisionMeta · arXiv (Cornell University)6 citationsFeb 26, 2025ALSTER: A Local Spatio-Temporal Expert for Online 3D Semantic ReconstructionMicrosoft · IEEE Winter Conference on Applications of Computer Vision6 citationsFeb 26, 2025SensorFlow: Sensor and Image Fused Video StabilizationAlphabet · IEEE Winter Conference on Applications of Computer Vision6 citationsFeb 26, 2025Towards Real-Time Open-Vocabulary Video Instance SegmentationAlphabet · IEEE Winter Conference on Applications of Computer Vision6 citationsFeb 26, 2025UCDR-Adapter: Exploring Adaptation of Pre-Trained Vision-Language Models for Universal Cross-Domain RetrievalAlibaba, Microsoft · IEEE Winter Conference on Applications of Computer Vision5 citationsFeb 26, 2025Contrastive Sequential-Diffusion Learning: Non-Linear and Multi-Scene Instructional Video SynthesisAlphabet · IEEE Winter Conference on Applications of Computer Vision5 citationsFeb 26, 2025Adaptive multi-model fusion learning for sparse-reward reinforcement learningLG AI Research · Neurocomputing5 citationsFeb 26, 2025MoKGNN: Boosting Graph Neural Networks via Mixture of Generic and Task-Specific Language ModelsMicrosoft · ACM International Conference on Web Search and Data Mining (WSDM)5 citationsFeb 26, 2025Distilling Reinforcement Learning Algorithms for In-Context Model-Based PlanningLG AI Research · arXiv (Cornell University)4 citationsFeb 26, 2025ReBotNet: Fast Real-Time Video EnhancementAlphabet · IEEE Winter Conference on Applications of Computer Vision4 citationsFeb 26, 2025REEDIT: Multimodal Exemplar-Based Image EditingMicrosoft · IEEE Winter Conference on Applications of Computer Vision3 citationsFeb 26, 2025Spatio-Temporal Context Prompting for Zero-Shot Action DetectionNVIDIA · IEEE Winter Conference on Applications of Computer Vision3 citationsFeb 26, 2025STLight: A Fully Convolutional Approach for Efficient Predictive Learning by Spatio-Temporal Joint ProcessingAlphabet · IEEE Winter Conference on Applications of Computer Vision3 citationsFeb 26, 2025LLM4Eval@WSDM 2025: Large Language Model for Evaluation in Information RetrievalMicrosoft · ACM International Conference on Web Search and Data Mining (WSDM)3 citationsFeb 26, 2025Gradient Deconfliction via Orthogonal Projections onto Subspaces For Multi-task LearningAlibaba · ACM International Conference on Web Search and Data Mining (WSDM)3 citationsFeb 26, 2025DivAvatar: Diverse 3D Avatar Generation with a Single PromptAlibaba · IEEE Winter Conference on Applications of Computer Vision2 citationsFeb 26, 2025SAND: Enhancing Open-Set Neuron Descriptions through Spatial AwarenessAlphabet · IEEE Winter Conference on Applications of Computer Vision2 citationsFeb 26, 2025Zero-Shot Image Moderation in Google Ads with LLM-Assisted Textual Descriptions and Cross-modal Co-embeddingsAlphabet · ACM International Conference on Web Search and Data Mining (WSDM)2 citationsFeb 26, 2025Advancing Weight and Channel Sparsification with Enhanced SaliencyNVIDIA · IEEE Winter Conference on Applications of Computer Vision1 citationFeb 26, 2025