Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Cascading Adversarial Bias from Injection to Distillation in Language ModelsAlphabet, Google DeepMind · ACM SIGSAC Conference on Computer and Communications Security (CCS)2 citationsNov 19, 2025Evaluating the Robustness of a Production Malware Detection System to Transferable Adversarial AttacksAlphabet · ACM SIGSAC Conference on Computer and Communications Security (CCS)1 citationNov 19, 2025Byte by Byte: Unmasking Browser Fingerprinting at the Function Level using V8 Bytecode TransformersAlphabet · ACM SIGSAC Conference on Computer and Communications Security (CCS)1 citationNov 19, 2025Snap & Replay: A new way to analyze uarch-scale performance bottlenecks for ML acceleratorsAlphabet · ACM Symposium on Cloud Computing (SoCC)Nov 19, 2025Securing Cryptographic Software via Typed Assembly LanguageAlphabet · ACM SIGSAC Conference on Computer and Communications Security (CCS)Nov 19, 2025Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary DelineationAlphabet · arXiv (Cornell University)Nov 18, 2025Segmentation-Aware Latent Diffusion for Satellite Image Super-Resolution: Enabling Smallholder Farm Boundary DelineationAlphabet · arXiv (Cornell University)Nov 18, 2025Towards Incremental MTU Upgrade for the InternetAlphabet · ACM Workshop on Hot Topics in Networks (HotNets)2 citationsNov 17, 2025Towards Accessible Model-Free VerificationAlphabet · ACM Workshop on Hot Topics in Networks (HotNets)Nov 17, 2025Using Fourier Analysis and Mutant Clustering to Accelerate DNN Mutation TestingAlphabet · IEEE/ACM International Conference on Automated Software Engineering (ASE)1 citationNov 16, 2025A Logspace-Constructive Proof of L=SLAlphabet · arXiv (Cornell University)Nov 15, 2025PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMsGoogle DeepMind · arXiv (Cornell University)1 citationNov 14, 2025Olympiad-level formal mathematical reasoning with reinforcement learningGoogle DeepMind · Nature19 citationsNov 12, 2025Augmenting Question Answering with A Hybrid RAG ApproachAlphabet · IEEE International Conference on Cognitive Machine Intelligence (CogMI)1 citationNov 12, 2025Bi-NAS: Towards Effective and Personalized Explanation for Recommender Systems via Bi-Level Neural Architecture SearchAlphabet · ProceedingsNov 12, 2025The FLuid Allocation of Surface code Qubits (FLASQ) cost model for early fault-tolerant quantum algorithmsAlphabet · arXiv (Cornell University)Nov 11, 2025Nearly-Optimal Private Selection via Gaussian MechanismAlphabet · arXiv (Cornell University)Nov 10, 2025Nearly-Optimal Private Selection via Gaussian MechanismAlphabet · arXiv (Cornell University)Nov 10, 2025Language Generation with Infinite ContaminationAlphabet · arXiv (Cornell University)Nov 10, 2025TNT: Improving Chunkwise Training for Test-Time MemorizationAlphabet · arXiv (Cornell University)Nov 10, 2025Sampling and Loss Weights in Multi-Domain TrainingAlphabet · arXiv (Cornell University)Nov 10, 2025SWE-fficiency: Can Language Models Optimize Real-World Repositories on Real Workloads?Alphabet, Google DeepMind · arXiv (Cornell University)1 citationNov 8, 2025ROI Scan: LLM-powered Object-level Similarity Search for Google Ads Content ModerationAlphabet · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025Google Ads Content Moderation with RAGAlphabet · ACM International Conference on Information and Knowledge Management (CIKM)Nov 8, 2025Mapping the positions of Two-Level-Systems on the surface of a superconducting transmon qubitAlphabet · arXiv (Cornell University)Nov 7, 2025