Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Machine Learning and the Future of AI: Revolutionizing Industries with Data-Driven InnovationsAlphabet · International Conference on Emerging Trends in Engineering and Medical Sciences (ICETEMS)Mar 6FVRuleLearner: Operator-Level Reasoning Tree (Op-Tree)-Based Rules Learning for Formal VerificationNVIDIA · arXiv (Cornell University)Mar 6Do 3D Large Language Models Really Understand 3D Spatial Relationships?Google DeepMind · arXiv (Cornell University)Mar 6TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor AnalysisAlibaba · arXiv (Cornell University)Mar 6Reference-guided Policy Optimization for Molecular Optimization via LLM ReasoningAlibaba · arXiv (Cornell University)Mar 6StreamWise: Serving Multi-Modal Generation in Real-Time at ScaleMicrosoft · arXiv (Cornell University)Mar 6Efficient K-generalizable Learned SearchAlibaba · arXiv (Cornell University)Mar 6Preventing Learning Stagnation in PPO by Scaling to 1 Million Parallel EnvironmentsGoogle DeepMind · arXiv (Cornell University)Mar 6Making Training-Free Diffusion Segmentors Scale with the Generative PowerAlibaba · arXiv (Cornell University)Mar 6Test-Time Adaptation via Many-Shot Prompting: Benefits, Limits, and PitfallsMicrosoft, xAI · arXiv (Cornell University)Mar 6LUMINA: LLM-Guided GPU Architecture Exploration via Bottleneck AnalysisMicrosoft · arXiv (Cornell University)Mar 6Latent Transfer Attack: Adversarial Examples via Generative Latent SpacesNVIDIA · arXiv (Cornell University)Mar 6Lost in Stories: Consistency Bugs in Long Story Generation by LLMsMicrosoft · arXiv (Cornell University)Mar 6EgoReasoner: Learning Egocentric 4D Reasoning via Task-Adaptive Structured ThinkingAlphabet, Google DeepMind · arXiv (Cornell University)Mar 6Efficient, Property-Aligned Fan-Out Retrieval via RL-Compiled DiffusionAlphabet · arXiv (Cornell University)Mar 6Polymorph: Energy-Efficient Multi-Label Classification for Video Streams on Embedded DevicesMicrosoft · IEEE Winter Conference on Applications of Computer VisionMar 6Zero-Shot Audio-Visual Editing via Cross-Modal Delta DenoisingMicrosoft · IEEE Winter Conference on Applications of Computer VisionMar 6MageBench: Bridging Large Multimodal Models to AgentsMicrosoft · IEEE Winter Conference on Applications of Computer VisionMar 6Optimizing Inclusion and Accessibility in Digital Education with Adaptive LearningAlphabet · Jurnal Mentari Manajemen Pendidikan dan Teknologi Informasi1 citationMar 5Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large ToolspacesMicrosoft · arXiv (Cornell University)Mar 5CodeScout: Contextual Problem Statement Enhancement for Software AgentsDatabricks · arXiv (Cornell University)Mar 5On the Necessity of Learnable Sheaf LaplaciansMicrosoft · arXiv (Cornell University)Mar 5Observing and Controlling Features in Vision-Language-Action ModelsNVIDIA · arXiv (Cornell University)Mar 5On Solving String Equations via Powers and Parikh ImagesMicrosoft · arXiv (Cornell University)Mar 5AI+HW 2035: Shaping the Next DecadeNVIDIA · arXiv (Cornell University)Mar 5