Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Knowledge-based Visual Question Answer with Multimodal Processing, Retrieval and FilteringAlibaba · neural information processing systems15 citationsJan 1, 2025Breaking Latent Prior Bias in Detectors for Generalizable AIGC Image DetectionMicrosoft · neural information processing systems15 citationsJan 1, 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning ChainsAlibaba · neural information processing systems15 citationsJan 1, 2025Multilingual Arbitration: Optimizing Data Pools to Accelerate Multilingual ProgressCohere · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1, 2025Cross-Lingual Auto Evaluation for Assessing Multilingual LLMsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1, 2025Knowing Before Saying: LLM Representations Encode Information About Chain-of-Thought Success Before CompletionNVIDIA · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)15 citationsJan 1, 2025AndroidGen: Building an Android Language Agent under Data ScarcityZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1, 2025A Survey of Post-Training Scaling in Large Language ModelsZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1, 2025DrawEduMath: Evaluating Vision Language Models with Expert-Annotated Students’ Hand-Drawn Math ImagesAllen Institute for AI · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)15 citationsJan 1, 2025Unfolding the Headline: Iterative Self-Questioning for News Retrieval and Timeline SummarizationAlibaba · Findings of the Association for Computational Linguistics: NAACL15 citationsJan 1, 2025Teaching Models to Balance Resisting and Accepting PersuasionAnthropic · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)15 citationsJan 1, 2025Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuningMicrosoft · neural information processing systems15 citationsJan 1, 2025Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMsAlphabet, Google DeepMind · neural information processing systems14 citationsJan 1, 2025VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language ModelsMicrosoft · neural information processing systems14 citationsJan 1, 2025Rectified Point Flow: Generic Point Cloud Pose EstimationNVIDIA · neural information processing systems14 citationsJan 1, 2025RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal OutputsMicrosoft · neural information processing systems14 citationsJan 1, 2025T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic PlanningNVIDIA · neural information processing systems14 citationsJan 1, 2025PanTS: The Pancreatic Tumor Segmentation DatasetMicrosoft, NVIDIA · neural information processing systems14 citationsJan 1, 2025Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical ImagingNVIDIA · neural information processing systems14 citationsJan 1, 2025The State of Multilingual LLM Safety Research: From Measuring The Language Gap To Mitigating ItCohere · Conference on Empirical Methods in Natural Language Processing (EMNLP)14 citationsJan 1, 2025MULTIGUARD: An Efficient Approach for AI Safety Moderation Across Languages and ModalitiesMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)14 citationsJan 1, 2025LogiDynamics: Unraveling the Dynamics of Inductive, Abductive and Deductive Logical Inferences in LLM ReasoningNVIDIA · Conference on Empirical Methods in Natural Language Processing (EMNLP)14 citationsJan 1, 2025Chain of Ideas: Revolutionizing Research Via Novel Idea Development with LLM AgentsAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)14 citationsJan 1, 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of RigorAlphabet, Hugging Face, Microsoft · neural information processing systems14 citationsJan 1, 2025FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language ModelsAlibaba · neural information processing systems14 citationsJan 1, 2025