Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
EpiQAL: Benchmarking Large Language Models in Epidemiological Question Answering and ReasoningMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)3 citationsJan 1Retrieval–Reasoning Processes for Multi-hop Question Answering: A Four-Axis Design Framework and Empirical TrendsAlphabet · arXiv3 citationsJan 1Does Understanding Inform Generation in Unified Multimodal Models? From Analysis to Path ForwardAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)3 citationsJan 1Towards Scalable Pre-training of Visual Tokenizers for GenerationMiniMax · Lecture notes in computer science3 citationsJan 1LPO: Towards Accurate GUI Agent Interaction via Location Preference OptimizationAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)3 citationsJan 1Automated Profile Inference with Language Model AgentsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)3 citationsJan 1Shorten After You’re Right: Lazy Length Penalties for Reasoning RLMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)3 citationsJan 1GL-DT: Multi-UAV Detection and Tracking With Global–Local IntegrationTechnology Innovation Institute · IEEE Transactions on Geoscience and Remote Sensing3 citationsJan 1Towards Uni fied W orld M odels for Visual Navigation via Memory-Augmented Planning and ForesightMicrosoft · Lecture notes in computer science3 citationsJan 1Writing-RL: Advancing Long-form Writing via Adaptive Curriculum Reinforcement LearningAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting3 citationsJan 1Beyond Turn Limits: Training Deep Search Agents with Dynamic Context WindowAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)3 citationsJan 1VeriStruct: AI-assisted Automated Verification of Data-Structure Modules in VerusMicrosoft · Lecture notes in computer science3 citationsJan 1Can Large Language Models Adequately Perform Symbolic Reasoning Over Time Series?Microsoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)3 citationsJan 1A Survey of Adversarial Defenses in Vision-Based Systems: Categorization, Methods, and ChallengesTechnology Innovation Institute · IEEE Access3 citationsJan 1Evaluating Style-Personalized Text Generation: Challenges and DirectionsMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)3 citationsJan 1Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective AmbiguityAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting3 citationsJan 1Advancing geometry with AI: Multi-agent generation of polytopesGoogle DeepMind · Advances in Theoretical and Mathematical Physics3 citationsJan 1How Good is Your Wikipedia? Auditing Data Quality for Low-resource and Multilingual NLPAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting3 citationsJan 1Hierarchical Action Recognition: A Contrastive Video-Language Approach with Hierarchical InteractionsAlibaba · Lecture notes in computer science3 citationsJan 1Adapting Network Information Into Semantics for Generalizable and Plug-and-Play Multi-Scenario Network DiagnosisAlibaba · IEEE Transactions on Communications2 citationsJan 1A Unified Evaluation of Learning-Based Similarity Techniques for Malware DetectionAlphabet, Databricks · International Conference on Security and Cryptography2 citationsJan 1No More Stale Feedback: Co-Evolving Critics for Open-World Agent LearningAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1Training LLMs for Divide-and-Conquer Reasoning Elevates Test-Time ScalabilityMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1RLSeek: Evidence-Grounded Reasoning for RAG Hallucination DetectionMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1CHIMERA: A Knowledge Base of Scientific Idea Recombinations for Research Analysis and IdeationAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1