Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MLLM-VADStory: Domain Knowledge-Driven Multimodal LLMs for Video Ad Storyline InsightsMeta · arXiv (Cornell University)Jan 8SPINAL -- Scaling-law and Preference Integration in Neural Alignment LayersAlphabet · arXiv (Cornell University)Jan 8Enhancing Multimodal Retrieval via Complementary Information Extraction and AlignmentAlibaba · arXiv (Cornell University)Jan 8Excess Description Length of Learning Generalizable PredictorsAnthropic · arXiv (Cornell University)Jan 8MineNPC-Task: Task Suite for Memory-Aware Minecraft AgentsMicrosoft · arXiv (Cornell University)Jan 8An Empirical Investigation of Robustness in Large Language Models under Tabular DistortionsMicrosoft · arXiv (Cornell University)Jan 8BackdoorAgent: A Unified Framework for Backdoor Attacks on LLM-based AgentsAlibaba · arXiv (Cornell University)Jan 8Welterweight Go: Boxing, Structural Subtyping, and GenericsAlphabet · Proceedings of the ACM on Programming LanguagesJan 8Bayesian teaching enables probabilistic reasoning in large language modelsAlphabet, Meta · Nature Communications14 citationsJan 7Self-Explaining Hate Speech Detection with Moral RationalesAlphabet · arXiv (Cornell University)2 citationsJan 7Systematic Migration of on-Premise Databases to Azure SQL: Overcoming Challenges and Maximizing Cloud BenefitsMicrosoft · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI)Jan 7Dynamic Resource Optimisation for AI-Powered Data Analytics in Cloud EnvironmentsMicrosoft · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI)Jan 7Artificial Intelligence and Machine Learning New Techniques for Generative AI that Drive Outcomes for Health and TransportationAlphabet · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI)Jan 7LEGATO: Good Identity Unlearning Is ContinuousSenseTime · arXiv (Cornell University)Jan 7Evolving Programmatic Skill NetworksMicrosoft · arXiv (Cornell University)Jan 7FLEx: Language Modeling with Few-shot Language ExplanationsMicrosoft · arXiv (Cornell University)Jan 7Mind the Generative Details: Direct Localized Detail Preference Optimization for Video Diffusion ModelsAlibaba · arXiv (Cornell University)Jan 7Parallel Latent Reasoning for Sequential RecommendationAlibaba · arXiv (Cornell University)9 citationsJan 6S2Vec: Self-Supervised Geospatial Embeddings for the Built EnvironmentAlphabet · ACM Transactions on Spatial Algorithms and Systems4 citationsJan 6VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action ModelsAlibaba · arXiv (Cornell University)2 citationsJan 6COFFEE: COdesign Framework for Feature Enriched Embeddings in Ads-Ranking SystemsMeta · arXiv (Cornell University)2 citationsJan 6PersonaLedger: Generating Realistic Financial Transactions with Persona Conditioned LLMs and Rule Grounded FeedbackAlphabet · arXiv (Cornell University)1 citationJan 6TGIF: Text-Guided Layer Fusion Mitigates Hallucination in Multimodal LLMsNVIDIA · arXiv (Cornell University)1 citationJan 6AI-Powered Intelligent System through context aware log scrutiny for Anomaly detectionMicrosoft · International Conference on Communication Systems & Networks (COMSNETS)Jan 6ECLIPTICA -- A Framework for Switchable LLM Alignment via CITA - Contrastive Instruction-Tuned AlignmentMeta · arXiv (Cornell University)Jan 6