Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
JanusQuant: Accurate and Efficient 2-bit KV Cache Quantization for Long-Context InferenceNVIDIA · ACM SIGPLAN Symposium on Principles and Practice of Parallel ProgrammingJan 28zBuffer: Zero-Copy and Metadata-Free Serialization for Fast RPC with Scatter-Gather ReflectionAlibaba · ACM SIGPLAN Symposium on Principles and Practice of Parallel ProgrammingJan 28Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool)NVIDIA · ACM SIGPLAN International Conference on Compiler Construction (CC)Jan 28Binary Compatible Critical Section DelegationAlibaba · ACM SIGPLAN Symposium on Principles and Practice of Parallel ProgrammingJan 28FlashAttention-T: Towards Fully Tensorized Attention by Exploiting Tensor-Vector ParallelismCambricon Technologies · ACM SIGPLAN Symposium on Principles and Practice of Parallel ProgrammingJan 28RIFS: Run-Time Invariant Function SpecializationAlphabet · ACM SIGPLAN International Conference on Compiler Construction (CC)Jan 28Does AI Now Represent a Paradigm Shift?Alphabet · Communications of the ACMJan 28XiYan-SQL: A Novel Multi-Generator Framework for Text-to-SQLAlibaba · IEEE Transactions on Knowledge and Data Engineering14 citationsJan 27Interdisciplinary expertise to advance human-centered explainable AIAlphabet · Social Science & Medicine10 citationsJan 27DevOps-Gym: Benchmarking AI Agents in Software DevOps CycleAlphabet · arXiv (Cornell University)3 citationsJan 27Taxonomy of the Retrieval System Framework: Pitfalls and ParadigmsAlphabet · arXiv (Cornell University)2 citationsJan 27Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning ModelsAnthropic, Google DeepMind, OpenAI · arXiv (Cornell University)1 citationJan 27Ensemble-Based Quantum Signal Processing for Error MitigationAlphabet · arXiv (Cornell University)Jan 27Entropy-Guided k-Guard Sampling for Long-Horizon Autoregressive Video GenerationHorizon Robotics · arXiv (Cornell University)Jan 27TIGaussian: Disentangle Gaussians for Spatial-Awared Text-Image-3D AlignmentAlibaba · arXiv (Cornell University)Jan 27Regularized $f$-Divergence Kernel TestsAlphabet · arXiv (Cornell University)Jan 27TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous BackendsNVIDIA · arXiv (Cornell University)Jan 27Calibration without Ground TruthMicrosoft · arXiv (Cornell University)Jan 27TokenSeek: Memory Efficient Fine Tuning via Instance-Aware Token DitchingMeta · arXiv (Cornell University)Jan 27Spatial-Temporal Multimodal Large Language Model for Generative Recommendation in AlipayAlibaba · IEEE Transactions on Knowledge and Data EngineeringJan 27See then tell: Enhancing key information extraction with vision groundingiFlytek · NeurocomputingJan 27RKGR: Robust Knowledge Graph-Based Recommendation Method Using Debiased Contrastive LearningiFlytek · IEEE Transactions on Consumer ElectronicsJan 27VIBEVOICE-ASR Technical ReportMicrosoft · arXiv (Cornell University)4 citationsJan 26General Binding Affinity Guidance for Diffusion Models in Structure-Based Drug DesignNVIDIA · Journal of Chemical Information and Modeling4 citationsJan 26OATS: Online Data Augmentation for Time Series Foundation ModelsMicrosoft · arXiv (Cornell University)1 citationJan 26