Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Tuning Medical Foundation Models for Inner Ear Temporal CT Analysis with Plug-and-play Domain Knowledge AggregatorMicrosoft · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14SimDiff: Simpler Yet Better Diffusion Model for Time Series Point ForecastingAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14OmniEvent: Unified Event Representation LearningMeta · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Zero-to-Hero: Empowering Video Appearance Transfer with Zero-Shot Initialization and Holistic RestorationAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14M-Loss: Quantifying Model Merging Compatibility with Limited Unlabeled DataAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Multi-Objective Bilevel LearningMeta · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Facial Dynamics in Video: Instruction Tuning for Improved Facial Expression Perception and Contextual AwarenessAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14From Diagnosis to Generalization: A Cognitive Approach to Data Selection for Educational LLMsiFlytek · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Adaptive Hallucination Alleviation in Multimodal Large Language Models: From Strategic Data Selection to Severity-Guided TrainingAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14DeepPhy: Benchmarking Agentic VLMs on Physical ReasoningAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Enhancing Conversational Recommender Systems with Tree-Structured Knowledge and Pretrained Language ModelsiFlytek · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Efficient Diffusion Planning with Temporal DiffusionCambricon Technologies · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text RerankingAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14GigaMoE: Sparsity-Guided Mixture of Experts for Efficient Gigapixel Object DetectionAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Think-J: Learning to Think for Generative LLM-as-a-JudgeAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Faster Game Solving via Hyperparameter SchedulesAnthropic · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference AlignmentDatabricks · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14URPO: A Unified Reward & Policy Optimization Framework for Large Language ModelsMoore Threads · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Injection Without Distortion: Geometrically Constrained Knowledge Enhancement for Vision-Language ModelsSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14READ: Real-time and Efficient Asynchronous Diffusion for Audio-driven Talking Head GenerationiFlytek · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Missing Mass for Differentially Private Domain DiscoveryAlphabet · arXiv (Cornell University)Mar 14RAA: Achieving Interactive Remove/Add Anything via Fully Synthetic DataSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Disentangling for Transfer: Boosting Limited Modalities via Information-Theoretic Regularization and Cross-Modal ReconstructionAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Contribution-aware Token Compression for Efficient Video Understanding via Reinforcement LearningAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14Learning Systems Expansion with Efficient Heterogeneity-aware Knowledge TransferMicrosoft · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14