Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
An Empirically-grounded tool for Automatic Prompt Linting and Repair: A Case Study on Bias, Vulnerability, and Optimization in Developer PromptsMicrosoft · arXiv (Cornell University)1 citationJan 21, 2025Quantum-Inspired Solver for Simulating Material DeformationsMultiverse Computing · arXiv (Cornell University)1 citationJan 21, 2025Sparse Blossom: correcting a million errors per core second with minimum-weight matchingAlphabet · Quantum305 citationsJan 20, 2025HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-Body Mesh RecoveryNVIDIA · IEEE Transactions on Pattern Analysis and Machine Intelligence60 citationsJan 20, 2025PIKE-RAG: sPecIalized KnowledgE and Rationale Augmented GenerationMicrosoft · arXiv (Cornell University)21 citationsJan 20, 2025It Is Time to Standardize Principles and Practices for Software Memory SafetyAlphabet, Microsoft · Communications of the ACM11 citationsJan 20, 2025H4H: Hybrid Convolution-Transformer Architecture Search for NPU-CIM Heterogeneous Systems for AR/VR ApplicationsMeta · Asia and South Pacific Design Automation Conference (ASP-DAC)7 citationsJan 20, 2025DEMOTIC: A Differentiable Sampler for Multi-Level Digital CircuitsNVIDIA · Asia and South Pacific Design Automation Conference (ASP-DAC)3 citationsJan 20, 2025Glinthawk: A Two-Tiered Architecture for Offline LLM InferenceMicrosoft · arXiv (Cornell University)1 citationJan 20, 20252025 ACM SIGMOBILE Test of Time AwardMicrosoft · GetMobile Mobile Computing and CommunicationsJan 20, 2025ACM fellow: Ramón CáceresMicrosoft · GetMobile Mobile Computing and CommunicationsJan 20, 2025Leveraging Generative AI for Database Migration: A Comprehensive Approach for Heterogeneous MigrationsAlphabet · Indian Engineering Journal1 citationJan 19, 2025Analysis of Transformer Decoder Architecture and KV Cache Behavior During LLM InferenceNVIDIA · International Conference on Electronics, Information, and Communication (ICEIC)1 citationJan 19, 2025Banknote Fitness Judgment System Using MemSeg Based on K-Means Memory UpdateLG AI Research · International Conference on Electronics, Information, and Communication (ICEIC)Jan 19, 2025EMO2: End-Effector Guided Audio-Driven Avatar Video GenerationAlibaba · arXiv (Cornell University)37 citationsJan 18, 2025Can Multimodal LLMs do Visual Temporal Understanding and Reasoning? The answer is No!Alibaba · arXiv (Cornell University)23 citationsJan 18, 2025Detecting Cloud Misconfigurations with RAG and Intelligent Agents: A Natural Language Understanding ApproachAlphabet · Journal of Electrical Systems8 citationsJan 18, 2025Topology-joint Curvilinear Segmentation Network using Confidence-based Bezier Topological RepresentationAlibaba · Engineering Applications of Artificial Intelligence5 citationsJan 18, 2025DiffuEraser: A Diffusion Model for Video InpaintingAlibaba · arXiv (Cornell University)75 citationsJan 17, 2025Modeling Fine-Grained Relations in Dynamic Space-Time Graphs for Video-Based Facial Expression RecognitioniFlytek · IEEE Transactions on Affective Computing21 citationsJan 17, 2025Privacy-preserving coordinated operation of cross-enterprise data centersAlibaba · Applied Energy18 citationsJan 17, 2025MSTS: A Multimodal Safety Test Suite for Vision-Language ModelsGoogle DeepMind · arXiv (Cornell University)17 citationsJan 17, 2025GaussMark: A Practical Approach for Structural Watermarking of Language ModelsMicrosoft · arXiv (Cornell University)13 citationsJan 17, 2025RelationLMM: Large Multimodal Model as Open and Versatile Visual Relationship GeneralistSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence13 citationsJan 17, 2025SLIM: Sim-to-Real Legged Instructive Manipulation via Long-Horizon Visuomotor LearningHorizon Robotics · arXiv (Cornell University)7 citationsJan 17, 2025