Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MEETING DELEGATE: Benchmarking LLMs on Attending Meetings on Our BehalfMicrosoft · Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)5 citationsJan 1, 2025FaStFact: Faster, Stronger Long-Form Factuality Evaluations in LLMsNVIDIA · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)5 citationsJan 1, 2025Consensus or Conflict? Fine-Grained Evaluation of Conflicting Answers in Question-AnsweringAlphabet · Workshop on Uncertainty-Aware NLP (UncertaiNLP)5 citationsJan 1, 2025GeoCAD: Local Geometry-Controllable CAD Generation with Large Language ModelsAlibaba · neural information processing systems5 citationsJan 1, 2025Leveraging Quantum Machine Learning Generalization to Significantly Speed up Quantum CompilationMicrosoft · IEEE Transactions on Quantum Engineering5 citationsJan 1, 2025IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video GenerationAlphabet, Google DeepMind · neural information processing systems5 citationsJan 1, 2025A Controllable Examination for Long-Context Language ModelsAlibaba · neural information processing systems5 citationsJan 1, 2025Struct-Bench: A Benchmark for Differentially Private Structured Text GenerationGoogle DeepMind, Microsoft · neural information processing systems5 citationsJan 1, 2025Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-GeneratorAlibaba · neural information processing systems5 citationsJan 1, 2025TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender SystemsAlibaba · neural information processing systems5 citationsJan 1, 2025Reading Recognition in the WildMeta · neural information processing systems5 citationsJan 1, 2025CAGE: Continuity-Aware edGE Network Unlocks Robust Floorplan ReconstructionAlibaba · neural information processing systems5 citationsJan 1, 2025Understanding Outer Optimizers in Local SGD: Learning Rates, Momentum, and AccelerationAlphabet · neural information processing systems5 citationsJan 1, 2025Guard Me If You Know Me: Protecting Specific Face-Identity from DeepfakesMicrosoft · neural information processing systems5 citationsJan 1, 2025Towards Efficient SDRTV-to-HDRTV by Learning From Image FormationSenseTime · IEEE Transactions on Multimedia5 citationsJan 1, 2025A Novel Approach to Mimic Linguistic Features of Transcripts of Atypical SpeechMicrosoft · IEEE Transactions on Audio Speech and Language Processing5 citationsJan 1, 2025P2 Law: Scaling Law for Post-Training After Model PruningZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting5 citationsJan 1, 2025M2PA: A Multi-Memory Planning Agent for Open Worlds Inspired by Cognitive TheoryAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)5 citationsJan 1, 2025Better Aligned with Survey Respondents or Training Data? Unveiling Political Leanings of LLMs on U.S. Supreme Court CasesAllen Institute for AI · arXiv5 citationsJan 1, 2025Teaching an Old LLM Secure Coding: Localized Preference Optimization on Distilled PreferencesMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting5 citationsJan 1, 2025Awes, Laws, and Flaws From Today’s LLM ResearchMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)5 citationsJan 1, 2025LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language FeedbackAlibaba, Microsoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)5 citationsJan 1, 2025BSM-iMagLS: ILD Informed Binaural Signal Matching for Reproduction With Head-Mounted Microphone ArraysMeta · IEEE Transactions on Audio Speech and Language Processing5 citationsJan 1, 2025GeoCoder: Solving Geometry Problems by Generating Modular Code through Vision-Language ModelsGoogle DeepMind · Findings of the Association for Computational Linguistics: NAACL5 citationsJan 1, 2025Towards Inducing Long-Context Abilities in Multilingual Neural Machine Translation ModelsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)5 citationsJan 1, 2025