Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
ThinkSound: Chain-of-Thought Reasoning in Multimodal Large Language Models for Audio Generation and EditingAlibaba · arXiv (Cornell University)27 citationsJun 26, 2025Spec2RTL-Agent: Automated Hardware Code Generation from Complex Specifications Using LLM Agent SystemsNVIDIA · IEEE International Conference on LLM-Aided Design (ICLAD)26 citationsJun 26, 2025AssertionForge: Enhancing Formal Verification Assertion Generation with Structured Representation of Specifications and RTLNVIDIA · IEEE International Conference on LLM-Aided Design (ICLAD)21 citationsJun 26, 2025Performance Prediction for Large Systems via Text-to-Text RegressionAlphabet · arXiv (Cornell University)17 citationsJun 26, 2025ECAMP: Entity-centered Context-aware Medical Vision Language Pre-trainingiFlytek · Medical Image Analysis17 citationsJun 26, 2025AI Driven Self-Healing Cybersecurity Systems with Agentic AI for Adaptive Threat Response and ResilienceMicrosoft · IEEE Cloud Summit15 citationsJun 26, 2025Data Efficacy for Language Model TrainingMicrosoft · arXiv (Cornell University)12 citationsJun 26, 2025DFVEdit: Conditional Delta Flow Vector for Zero-shot Video EditingAlibaba · arXiv (Cornell University)5 citationsJun 26, 2025Double-Checker: Enhancing Reasoning of Slow-Thinking LLMs via Self-Critical Fine-TuningNVIDIA · arXiv (Cornell University)4 citationsJun 26, 2025Enhancing User Engagement in Socially-Driven Dialogue through Interactive LLM AlignmentsMicrosoft · arXiv (Cornell University)3 citationsJun 26, 2025ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in IndustryAlibaba · arXiv (Cornell University)2 citationsJun 26, 2025DynamicBench: Evaluating Real-Time Report Generation in Large Language ModelsAlibaba · arXiv (Cornell University)Jun 26, 2025AFPD: System for Prediction, Mitigation and Remediation of Node Interruptions in Cloud InfrastructureMicrosoft · IEEE Cloud SummitJun 26, 2025Computer-vision research powers surveillance technologyAllen Institute for AI · Nature43 citationsJun 25, 2025Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI ApplicationsMicrosoft · arXiv (Cornell University)10 citationsJun 25, 2025Cognitive models can reveal interpretable value trade-offs in language modelsGoogle DeepMind · arXiv (Cornell University)8 citationsJun 25, 2025Neural Recommendation Reasoning with Logic RulesMicrosoft · ACM Transactions on Information Systems3 citationsJun 25, 2025AgentStory: A Multi-Agent System for Story Visualization with Multi-Subject Consistent Text-to-Image GenerationAlibaba · International Conference on Multimedia Retrieval2 citationsJun 25, 2025Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to DeferAlphabet · arXiv (Cornell University)1 citationJun 25, 2025Towards Efficient Exemplar Based Image Editing with Multimodal VLMsMicrosoft · arXiv (Cornell University)Jun 25, 2025CEFSW'25: The 2nd Collaboration and Evolution of Foundation and Specialized Models WorkshopMeta · International Conference on Multimedia RetrievalJun 25, 2025Reproducibility Companion Paper: u-LLaVA: Unifying Multi-Modal Tasks via Large Language ModelAlibaba · International Conference on Multimedia RetrievalJun 25, 2025AI-based large-scale screening of gastric cancer from noncontrast CT imagingAlibaba · Nature Medicine50 citationsJun 24, 2025MSR-Align: Policy-Grounded Multimodal Alignment for Safety-Aware Reasoning in Vision-Language ModelsAlibaba · arXiv (Cornell University)9 citationsJun 24, 2025Hierarchical Control of Emotion Rendering in Speech SynthesisAlibaba · IEEE Transactions on Affective Computing7 citationsJun 24, 2025