Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
When Deep Learning Meets Polyhedral Theory: A SurveyAlphabet · INFORMS journal on computing20 citationsMar 12Provable Filter for Real-World Graph ClusteringAlibaba · IEEE Transactions on Cybernetics2 citationsMar 12DOne: Decoupling Structure and Rendering for High-Fidelity Design-to-Code GenerationAlibaba · arXiv (Cornell University)Mar 12MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?Alibaba · arXiv (Cornell University)Mar 12Measurement-Induced State transitions in Inductively-Shunted TransmonsAlphabet · arXiv (Cornell University)Mar 12Tiny Aya: Bridging Scale and Multilingual DepthCohere · arXiv (Cornell University)Mar 12Cross-Domain Policy Optimization via Bellman Consistency and Hybrid CriticsMeta · arXiv (Cornell University)Mar 12Matching Features, Not Tokens: Energy-Based Fine-Tuning of Language ModelsMicrosoft · arXiv (Cornell University)Mar 12Linking Perception, Confidence and Accuracy in MLLMsAlibaba · arXiv (Cornell University)Mar 12Classical neural networks on quantum devices via tensor network disentanglers: A case study in image classificationMultiverse Computing · Physical Review ResearchMar 12Portable multi-GPU urban flood modelling via MPI-OpenACC: evaluating acceleration, scaling, and workload-per-GPUNVIDIA · Environmental Modelling & Software1 citationMar 11High-Fidelity Text-to-Image Generation from Pre-Trained Vision-Language Models via Distribution-Conditioned Diffusion DecodingMicrosoft · arXiv (Cornell University)Mar 11Meta-Reinforcement Learning with Self-Reflection for Agentic SearchAllen Institute for AI · arXiv (Cornell University)Mar 11Uni-ASR: Unified LLM-Based Architecture for Non-Streaming and Streaming Automatic Speech RecognitionAlibaba · arXiv (Cornell University)Mar 11Taking Shortcuts for Categorical VQA Using Super NeuronsAlphabet, Google DeepMind · arXiv (Cornell University)Mar 11Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral ReasoningMicrosoft · arXiv (Cornell University)Mar 11What do near-optimal learning rate schedules look like?Google DeepMind · arXiv (Cornell University)Mar 11Differentiable Geometric Indexing for End-to-End Generative RetrievalAlibaba · arXiv (Cornell University)Mar 11LLM2Vec-Gen: Generative Embeddings from Large Language ModelsCohere · arXiv (Cornell University)Mar 11A Hypergraph-Based Framework for Exploratory Business IntelligenceAlibaba · arXiv (Cornell University)Mar 11Diagnostic accuracy, fairness and clinical implementation of AI for breast cancer screening: results of multicenter retrospective and prospective technical feasibility studiesAlphabet · Nature Cancer18 citationsMar 10StarIR: Convolutional Image Restoration With Spatial-Frequency FusionMicrosoft · IEEE Transactions on Pattern Analysis and Machine Intelligence6 citationsMar 10Impact of using artificial intelligence as a second reader in breast screening including arbitrationAlphabet · Nature Cancer6 citationsMar 10MSCCL++: Rethinking GPU Communication Abstractions for AI InferenceMicrosoft · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)5 citationsMar 10QoServe: Breaking the Silos of LLM Inference ServingMicrosoft · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)4 citationsMar 10