Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Counterfactual Debiasing for Physical Audiovisual Commonsense ReasoningSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025Image-to-video Adaptation with Outlier Modeling and Robust Self-learningMicrosoft · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025How Do Position Encodings Affect Length Generalization? Case Studies On In-Context Function LearningAlphabet · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025AtomNet: Designing Tiny Models from Operators Under Extreme MCU ConstraintsSenseTime · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025Frozen Language Models Are Gradient Coherence Rectifiers in Vision TransformersAlibaba · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025RFL: Simplifying Chemical Structure Recognition with Ring-Free LanguageiFlytek · Proceedings of the AAAI Conference on Artificial IntelligenceApr 11, 2025Recommendation System in Advertising and Streaming Media: Unsupervised Data Enhancement Sequence SuggestionsMeta · Applied and Computational Engineering43 citationsApr 10, 2025Bridging Algorithmic Information Theory and Machine Learning: Clustering, density estimation, Kolmogorov complexity-based kernels, and kernel learning in unsupervised learningGoogle DeepMind · Physica D Nonlinear Phenomena9 citationsApr 10, 2025STeP: A Framework for Solving Scientific Video Inverse Problems with Spatiotemporal Diffusion PriorsOpenAI · arXiv (Cornell University)8 citationsApr 10, 2025SD$^2$: Self-Distilled Sparse DraftersCerebras Systems · arXiv (Cornell University)4 citationsApr 10, 2025HPCNet: Hybrid Pixel and Contour Network for Audio-Visual Speech Enhancement With Low-Quality VideoiFlytek · IEEE Journal of Selected Topics in Signal Processing1 citationApr 10, 2025Universal photonic artificial intelligence accelerationOpenAI · Nature199 citationsApr 9, 2025Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of PrivacyGoogle DeepMind · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)74 citationsApr 9, 2025Get My Drift? Catching LLM Task Drift with Activation DeltasMicrosoft · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)67 citationsApr 9, 2025Verifiable and Provably Secure Machine UnlearningMicrosoft · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)45 citationsApr 9, 2025A Survey on Personalized and Pluralistic Preference Alignment in Large Language ModelsAllen Institute for AI · arXiv (Cornell University)29 citationsApr 9, 2025Probabilistic Contingent Planning Based on Hierarchical Task Network for High-Quality PlansMicrosoft · Algorithms26 citationsApr 9, 2025UTFix: Change Aware Unit Test Repairing using LLMMeta · Proceedings of the ACM on Programming Languages20 citationsApr 9, 2025OLMoTrace: Tracing Language Model Outputs Back to Trillions of Training TokensAllen Institute for AI · arXiv (Cornell University)16 citationsApr 9, 2025Avoiding Pitfalls for Privacy Accounting of Subsampled Mechanisms Under CompositionGoogle DeepMind · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)14 citationsApr 9, 2025Kaleidoscope: In-language Exams for Massively Multilingual Vision EvaluationCohere · arXiv (Cornell University)13 citationsApr 9, 2025SPLAT: A Framework for Optimised GPU Code-Generation for SParse reguLar ATtentionAlphabet, Microsoft · Proceedings of the ACM on Programming Languages9 citationsApr 9, 2025Revealing Sources of (Memory) Errors via Backward AnalysisMeta · Proceedings of the ACM on Programming Languages7 citationsApr 9, 2025Boosting quantum annealing performance through direct polynomial unconstrained binary optimizationTechnology Innovation Institute · Quantum Science and Technology7 citationsApr 9, 2025Locking Machine Learning Models into HardwareAlphabet, Google DeepMind · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML)5 citationsApr 9, 2025