Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1PRiSM: Benchmarking Phone Realization in Speech ModelsNVIDIA · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1AgentOCR: Reimagining Agent History via Optical Self-CompressionAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Modeling LLM Unlearning as an Asymmetric Two-Task Learning ProblemAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1ART: Attention Replacement Technique to Improve Factuality in LLMsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Scale Can’t Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language ReasoningAllen Institute for AI, Mistral AI · Transactions of the Association for Computational Linguistics2 citationsJan 1WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid InterfacesMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1The Geometry of LLM-as-Judge: Why Inter-LLM Consensus Is Not Human AlignmentMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World SessionsAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1Hybrid Adversarial Retraining Approach for a Proactive Network Intrusion Detection SystemTechnology Innovation Institute · IEEE Open Journal of the Communications Society2 citationsJan 1LVMark: Robust Watermark for Latent Video Diffusion ModelsAlphabet · IEEE Transactions on Information Forensics and Security2 citationsJan 1MolmoWeb: Open Visual Web Agent and Open Data for the Open WebAllen Institute for AI · Lecture notes in computer science2 citationsJan 1CarbonWise CX: An Agentic AI Framework for Carbon-Aware Customer Support Analytics Using RAG and LLM-Based Code GenerationMicrosoft · IEEE Access2 citationsJan 1Adaptive Data Flywheel: Applying MAPE Control Loops to AI Agent ImprovementNVIDIA · Conference of the European Chapter of the Association for Computational Linguistics2 citationsJan 1RotBench: Evaluating Multi-modal Large Language Models on Identifying Image RotationAllen Institute for AI · Conference of the European Chapter of the Association for Computational Linguistics2 citationsJan 1FaithLM: Towards Faithful Explanations for Large Language ModelsAlphabet, Meta · Conference of the European Chapter of the Association for Computational Linguistics2 citationsJan 1Reasoning Beyond Labels: Measuring LLM Sentiment in Low-Resource, Culturally Nuanced ContextsMicrosoft · Workshop on African Natural Language Processing (AfricaNLP)2 citationsJan 1Incentivizing Strong Reasoning from Weak SupervisionAlibaba, Allen Institute for AI · Conference of the European Chapter of the Association for Computational Linguistics2 citationsJan 1A Novel Framework for HealthGoverned Application Reliability in Cloud PlatformsMicrosoft · JOURNAL OF EMERGING TRENDS AND NOVEL RESEARCH2 citationsJan 1LoGeR: Long-Context Geometric Reconstruction with Hybrid MemoryAlphabet · Lecture notes in computer science2 citationsJan 1Standardizing Generative Face Video Compression Using Supplemental Enhancement InformationAlibaba · IEEE Transactions on Multimedia2 citationsJan 1Adaptively Clustering Neighbor Elements for Image-Text GenerationAlibaba · IEEE Transactions on Multimedia2 citationsJan 1A Resource-Rational Account of Human Eye Movements During Immersive Visual SearchOpenAI · Open Mind2 citationsJan 1AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial MemoriesAllen Institute for AI · Lecture notes in computer science2 citationsJan 1HALT: Hallucination Assessment via Log-probs as Time seriesMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)2 citationsJan 1