Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
YOLOv5-FRNet: A Real-time Drowning Detection Method with Multi-Model CascadeiFlytek · Journal of big data and computing.1 citationJun 1, 2025LT-YOLO: An Improved Lightweight Detection Algorithm Based on YOLOv11iFlytek · Journal of big data and computing.1 citationJun 1, 2025Autonomous Mario Kart in the Wild: Lessons Learned From the Earth Rover Challenge at IROS 2024 [Competitions]Alphabet, Meta · IEEE Robotics & Automation Magazine1 citationJun 1, 2025Improved Pedestrian Attribute Recognition Algorithm Based on Image Style TransferiFlytek · Journal of big data and computing.Jun 1, 2025Scams at Scale: Unmasking Crypto Fraud and Social Engineering on the Modern WebMeta · XRDS Crossroads The ACM Magazine for StudentsJun 1, 2025MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical ReasoningMicrosoft · arXiv (Cornell University)47 citationsMay 31, 2025SenseFlow: Scaling Distribution Matching for Flow-based Text-to-Image DistillationSenseTime · arXiv (Cornell University)27 citationsMay 31, 2025Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI AgentsMicrosoft · arXiv (Cornell University)15 citationsMay 31, 2025Creating Effective Alerts for Monitoring Distributed SystemsMicrosoft · International Journal of Computer Trends and Technology5 citationsMay 31, 2025Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMsAlibaba · arXiv (Cornell University)3 citationsMay 31, 2025Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled PreferencesMicrosoft · arXiv (Cornell University)3 citationsMay 31, 2025Democratizing AI Across your Organization Using Cloud - AWS, Azure, and GCPMicrosoft · International Journal of Computer Trends and Technology2 citationsMay 31, 2025Constrained Stein Variational Gradient Descent for Robot Perception, Planning, and IdentificationNVIDIA · arXiv (Cornell University)1 citationMay 31, 2025Zero Trust for AI: Enabling Secure Workload Execution and Data ProtectionMicrosoft · Computer Fraud & SecurityMay 31, 2025Visual Embodied Brain: Let Multimodal Large Language Models See, Think, and Control in SpacesSenseTime · arXiv (Cornell University)42 citationsMay 30, 2025ReasonGen-R1: CoT for Autoregressive Image generation models through SFT and RLMicrosoft · arXiv (Cornell University)32 citationsMay 30, 2025MoDoMoDo: Multi-Domain Data Mixtures for Multimodal LLM Reinforcement LearningNVIDIA · arXiv (Cornell University)29 citationsMay 30, 2025EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingAlibaba · arXiv (Cornell University)19 citationsMay 30, 2025HD-NDEs: Neural Differential Equations for Hallucination Detection in LLMsAlibaba · arXiv (Cornell University)5 citationsMay 30, 2025Productionizing Quantum Mass ProductionAlphabet · arXiv (Cornell University)3 citationsMay 30, 2025Exploiting lightweight neural post-filtering for directional speech enhancementHorizon Robotics · Applied Acoustics3 citationsMay 30, 2025TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social IntelligenceAlibaba · arXiv (Cornell University)2 citationsMay 30, 2025Minifinetuning: Low-Data Generation Domain Adaptation through Corrective Self-DistillationNVIDIA · arXiv (Cornell University)1 citationMay 30, 2025Randomized Dimensionality Reduction for Euclidean Maximization and Diversity MeasuresAlphabet · arXiv (Cornell University)1 citationMay 30, 2025Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden StatesMicrosoft · arXiv (Cornell University)1 citationMay 30, 2025