Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Designing Secure and Scalable API Management Frameworks for Cloud EnvironmentsMicrosoft · International Conference on Intelligent Computing and Control Systems (ICICCS)Mar 16Distributional Open-Ended Evaluation of LLM Cultural Value Alignment Based on Value CodebookMicrosoft · arXiv (Cornell University)Mar 16Aligning Paralinguistic Understanding and Generation in Speech LLMs via Multi-Task Reinforcement LearningMeta · arXiv (Cornell University)Mar 16AsgardBench -- Evaluating Visually Grounded Interactive Planning Under Minimal FeedbackMicrosoft · arXiv (Cornell University)Mar 16Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement LearningMicrosoft, NVIDIA · arXiv (Cornell University)Mar 16Simple is Better: Multiplication May Be All You Need for LLM Request SchedulingAlibaba · arXiv (Cornell University)Mar 16Understanding Reasoning in LLMs through Strategic Information Allocation under UncertaintyMicrosoft · arXiv (Cornell University)Mar 16Generative Video Compression with One-Dimensional Latent RepresentationMicrosoft · arXiv (Cornell University)Mar 16POLCA: Stochastic Generative Optimization with LLMAlphabet · arXiv (Cornell University)Mar 16Integrating Weather Foundation Model and Satellite to Enable Fine-Grained Solar Irradiance ForecastingAlibaba · arXiv (Cornell University)Mar 16The Hrunting of AI: Where and How to Improve English Dialectal FairnessMicrosoft · arXiv (Cornell University)Mar 16Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow PoliciesMicrosoft · arXiv (Cornell University)Mar 16HST-MoE: Hierarchical Soft-Training for Multiexpert Federated LearningMicrosoft · IEEE Transactions on Computer-Aided Design of Integrated Circuits and SystemsMar 16MITTA: A Multi-Task Transformer Accelerator With Mixed Precision Structured Sparsity and Hierarchical Task-Adaptive Power ManagementNVIDIA · IEEE Journal of Solid-State CircuitsMar 16Breaking and Fixing MacaKeyTechnology Innovation Institute · IACR Transactions on Symmetric CryptologyMar 16Optimizing Sparse SYKAlphabet · QuantumMar 16Invited: Polymath: Self-Improving Hierarchical Workflow for Multi-Domain Problem SolvingNVIDIA · International Symposium on Physical DesignMar 15Membership Inference for Contrastive Pre-training Models with Text-only PII QueriesAlibaba · arXiv (Cornell University)Mar 15Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMsAlibaba · arXiv (Cornell University)Mar 15AtlasRAN: Timing-Aware Evaluation of Open-source 5G Platforms for Integrated Wireless TestbedsNVIDIA · arXiv (Cornell University)Mar 15DesInsert: Strategic descriptive term insertion fools text-to-image generationMicrosoft · Neural NetworksMar 15MAISI-v2: Accelerated 3D High-Resolution Medical Image Synthesis with Rectified Flow and Region-specific Contrastive LossNVIDIA · Proceedings of the AAAI Conference on Artificial Intelligence9 citationsMar 14StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and CompressionAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence7 citationsMar 14Assessing the Quality of AI-Generated Exams: A Large-Scale Field StudyMicrosoft · Proceedings of the AAAI Conference on Artificial Intelligence6 citationsMar 14EasyText: Controllable Diffusion Transformer for Multilingual Text RenderingAlibaba · Proceedings of the AAAI Conference on Artificial Intelligence6 citationsMar 14