Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SeaLLMs-Audio: Large Audio-Language Models for Southeast AsiaAlibaba · arXiv (Cornell University)13 citationsNov 3, 2025MicroRemed: Benchmarking LLMs in Microservices RemediationAlibaba · arXiv (Cornell University)13 citationsNov 3, 2025TokenSim: Enabling Hardware and Software Exploration for Large Language Model Inference SystemsAlibaba, SenseTime · Lecture notes in computer science6 citationsNov 3, 2025How to Update Your 5G vRANMicrosoft · ACM Annual International Conference on Mobile Computing and Networking (MobiCom)5 citationsNov 3, 2025Information Extraction From Fiscal Documents Using LLMsAlphabet · arXiv (Cornell University)5 citationsNov 3, 2025Explore More, Learn Better: Parallel MLLM Embeddings under Mutual Information MinimizationAlibaba · arXiv (Cornell University)3 citationsNov 3, 2025Align to Misalign: Automatic LLM Jailbreak with Meta-Optimized LLM JudgesMicrosoft · arXiv (Cornell University)3 citationsNov 3, 2025DPDispatcher: Scalable HPC Task Scheduling for AI-Driven SciencePreferred Networks · Journal of Chemical Information and Modeling3 citationsNov 3, 2025XAIUI: User Belief-Driven Explainable AI for Context-Aware Adaptive InterfacesMeta · ACM Transactions on Interactive Intelligent Systems3 citationsNov 3, 2025TapOut: A Bandit-Based Approach to Dynamic Speculative DecodingCerebras Systems · arXiv (Cornell University)2 citationsNov 3, 2025Flashlight: PyTorch Compiler Extensions to Accelerate Attention VariantsMicrosoft · arXiv (Cornell University)2 citationsNov 3, 2025Multi-Step Adaptive Attack Agent: A Dynamic Approach for Jailbreaking Large Language ModelsAlibaba · IEEE International Conference on Tools with Artificial Intelligence (ICTAI)1 citationNov 3, 2025POSTER: DaPPA: A Data-Parallel Programming Framework for Processing-in-Memory ArchitecturesNVIDIA · International Conference on Parallel Architectures and Compilation Techniques (PACT)Nov 3, 2025POSTER: PIMAP: Characterizing a Real Processing-in-Memory System for Analytical Data ProcessingNVIDIA · International Conference on Parallel Architectures and Compilation Techniques (PACT)Nov 3, 2025Query-Aware Route Enrichment for Handling Complex Direction Queries and Grounding Large Language ModelsMicrosoft · ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (SIGSPATIAL GIS)Nov 3, 2025Experience Paper: Adopting Activity Recognition in On-demand Food Delivery BusinessAlibaba · ACM Annual International Conference on Mobile Computing and Networking (MobiCom)Nov 3, 2025Demo: Towards Seamless 5G vRAN Software UpdatesMicrosoft · ACM Annual International Conference on Mobile Computing and Networking (MobiCom)Nov 3, 2025Wave-Particle (Continuous-Discrete) Dualistic Visual Tokenization for Unified Understanding and GenerationAlibaba · arXiv (Cornell University)Nov 3, 2025Data-Free Cloud-Edge Distillation for Safe and Efficient Intelligent CommunicationsSenseTime · IEEE Journal on Selected Areas in CommunicationsNov 3, 2025FOSS: Learning-Based Multi-Level Design Makes FIFO More Adaptive for CDN CachingAlibaba · IEEE Transactions on Parallel and Distributed SystemsNov 3, 2025Multi-Agent Geophysical AI Workflow for Automated Reservoir CharacterizationDeepSeek · Abu Dhabi International Petroleum Exhibition & Conference (ADIPEC)Nov 3, 2025Portal UX Agent -- A Plug-and-Play Engine for Rendering UIs from Natural Language SpecificationsMicrosoft · arXiv (Cornell University)2 citationsNov 2, 2025From Soup to Bricks: Fast Clustering of Fine-Grained AMR Hierarchies for Rendering on GPUsNVIDIA · IEEE Symposium on Large Data Analysis and VisualizationNov 2, 2025Sherlock: Reliable and Efficient Agentic Workflow ExecutionMicrosoft · arXiv (Cornell University)16 citationsNov 1, 2025Personalized federated learning with exact stochastic gradient descentGoogle DeepMind · Applied Intelligence15 citationsNov 1, 2025