Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Spectrum Tuning: Post-Training for Distributional Coverage and In-Context SteerabilityMicrosoft · arXiv (Cornell University)10 citationsOct 7, 2025The code distance of Floquet codesAlphabet · arXiv (Cornell University)10 citationsOct 7, 2025MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded EvaluationAlibaba, Microsoft · arXiv (Cornell University)9 citationsOct 7, 2025Mixture of Neuron ExpertsMicrosoft · arXiv (Cornell University)9 citationsOct 7, 2025EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-ForgetMicrosoft · arXiv (Cornell University)8 citationsOct 7, 2025Wonder3D++: Cross-Domain Diffusion for High-Fidelity 3D Generation From a Single ImageHorizon Robotics · IEEE Transactions on Pattern Analysis and Machine Intelligence5 citationsOct 7, 2025(Token-Level) InfoRMIA: Stronger Membership Inference and Memorization Assessment for LLMsAlphabet · arXiv (Cornell University)5 citationsOct 7, 2025EgoTrigger: Toward Audio-Driven Image Capture for Human Memory Enhancement in All-Day Energy-Efficient Smart GlassesAlphabet · IEEE Transactions on Visualization and Computer Graphics5 citationsOct 7, 2025MDSF-YOLO: Advancing Object Detection With a Multiscale Dilated Sequence Fusion NetworkAlibaba · IEEE Transactions on Neural Networks and Learning Systems4 citationsOct 7, 2025GUIDE: Guided Initialization and Distillation of EmbeddingsAlphabet · arXiv (Cornell University)1 citationOct 7, 2025Truthful Calibration Errors for Multi-Class PredictionMicrosoft · arXiv (Cornell University)1 citationOct 7, 2025A sign language to SQL query translation system for enhancing database accessibilityMicrosoft · Automated Software EngineeringOct 7, 2025Inoculation Prompting: Instructing LLMs to misbehave at train-time improves test-time alignmentAnthropic · arXiv (Cornell University)41 citationsOct 6, 2025ParallelBench: Understanding the Trade-offs of Parallel Decoding in Diffusion LLMsMicrosoft · arXiv (Cornell University)38 citationsOct 6, 2025Reinforce-Ada: An Adaptive Sampling Framework under Non-linear RL ObjectivesMicrosoft · arXiv (Cornell University)27 citationsOct 6, 2025Factuality Matters: When Image Generation and Editing Meet Structured VisualsHugging Face · arXiv (Cornell University)17 citationsOct 6, 2025Let it Calm: Exploratory Annealed Decoding for Verifiable Reinforcement LearningMeta · arXiv (Cornell University)13 citationsOct 6, 2025MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement LearningAlibaba · arXiv (Cornell University)9 citationsOct 6, 2025FrodoKEM: A CCA-Secure Learning With Errors Key Encapsulation MechanismMicrosoft · IACR Communications in Cryptology9 citationsOct 6, 2025Model-Free Test Time Adaptation for Out-of-Distribution DetectionAlibaba, Meta · IEEE Transactions on Pattern Analysis and Machine Intelligence9 citationsOct 6, 2025Closed-Form Last Layer OptimizationGoogle DeepMind · arXiv (Cornell University)7 citationsOct 6, 2025CMT-Benchmark: A Benchmark for Condensed Matter Theory Built by Expert ResearchersAlphabet · arXiv (Cornell University)6 citationsOct 6, 2025One step forward, two steps back: ML-based malware detection under concept driftMeta · Computing5 citationsOct 6, 2025LightCache: Memory-Efficient, Training-Free Acceleration for Video GenerationMicrosoft · arXiv (Cornell University)3 citationsOct 6, 2025Expand Neurons, Not ParametersOpenAI · arXiv (Cornell University)2 citationsOct 6, 2025