Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Informal Learning Emerges in Everyday Human-LLM InteractionMicrosoft · arXiv (Cornell University)Jul 20LLM-as-a-Coach: Experiential Learning for Non-Verifiable TasksMicrosoft · arXiv (Cornell University)Jul 20TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory MinimizationAlphabet · arXiv (Cornell University)Jul 20X-Translator: A Real-Time Multilingual Speaker-Aware Speech-to-Speech Translation SystemMicrosoft · arXiv (Cornell University)Jul 20RTC Relay Server Infrastructure StudyMeta · Applied Networking Research Workshop (ANRW)Jul 20Query Optimization in the Wild: Realities and TrendsMicrosoft · ACM SIGMOD RecordJul 20How To Build End-To-End Physical AI Systems for RobotsNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Introduction to Slang: The Next-Generation Shading LanguageNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19An Introduction to Neural ShadingNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Advanced Real-Time Volume GraphicsNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Accelerate Robot Learning With NVIDIA Isaac Lab and NewtonNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Dreaming in 4 dimensions: generating media with Gemini, Genie, and VeoAlphabet · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19GPU Ray Tracing using NVIDIA OptiX and OWLNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Building with Meta Wearable Device Access ToolkitMeta · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19A Step-by-Step Introduction to the ANARI Rendering APINVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Hands-On Machine Learning with Slang: Building High-Performance GPU Inference PipelinesNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19Simulating a Dextrous Hand For Robotics With OpenUSDNVIDIA · ACM SIGGRAPH Conference Papers (SIGGRAPH)Jul 19TurboVec: A Case Study in Cost-Efficient Private Retrieval for Enterprise RAG via Codebook-Oblivious QuantizationAlphabet · arXiv (Cornell University)Jul 18SpecLA: Efficient Speculative Decoding for Linear-Attention ModelsAlibaba · arXiv (Cornell University)Jul 18Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided RefinementAlibaba · arXiv (Cornell University)Jul 18Wait-Free Locks Should Not Fear Later ArrivalsNVIDIA · arXiv (Cornell University)Jul 18Adaptive Incident Prioritization for Security Operations at ScaleMicrosoft · arXiv (Cornell University)Jul 18Grad-ECLIP: Gradient-Based Visual and Textual Explanations for CLIPSenseTime · IEEE Transactions on Pattern Analysis and Machine Intelligence2 citationsJul 17Evaluating AI models’ capability to automate voice phishing attacksMeta · Expert Systems with Applications1 citationJul 17Lost in Perception: Isolating Perceptual and Reasoning Failures in Multimodal Physics and Geometry ReasoningMicrosoft · arXiv (Cornell University)Jul 17