Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
MMTU: A Massive Multi-Task Table Understanding and Reasoning BenchmarkMicrosoft · neural information processing systems12 citationsJan 1, 2025MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts SystemsMicrosoft · neural information processing systems12 citationsJan 1, 2025Training Language Models to Generate Quality Code with Program Analysis FeedbackAnthropic, Google DeepMind, Microsoft · neural information processing systems12 citationsJan 1, 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward ModelsAlphabet, Microsoft · neural information processing systems12 citationsJan 1, 2025POSITION BIAS MITIGATES POSITION BIAS: Mitigate Position Bias Through Inter-Position Knowledge DistillationAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025On Relation-Specific Neurons in Large Language ModelsGoogle DeepMind · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025SSA-COMET: Do LLMs Outperform Learned Metrics in Evaluating MT for Under-Resourced African Languages?Alphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language ModelsMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025Do RAG Systems Really Suffer From Positional Bias?Technology Innovation Institute · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025Revealing and Mitigating the Challenge of Detecting Character Knowledge Errors in LLM Role-PlayingAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)12 citationsJan 1, 2025GeoPQA: Bridging the Visual Perception Gap in MLLMs for Geometric ReasoningAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)12 citationsJan 1, 2025TwT: Thinking without Tokens by Habitual Reasoning Distillation with Multi-Teachers’ GuidanceMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)12 citationsJan 1, 2025Dyn-O: Building Structured World Models with Object-Centric RepresentationsMicrosoft · neural information processing systems12 citationsJan 1, 2025Language Modeling by Language ModelsAllen Institute for AI · neural information processing systems12 citationsJan 1, 2025Broken Tokens? Your Language Model can Secretly Handle Non-Canonical TokenizationsAllen Institute for AI · neural information processing systems12 citationsJan 1, 2025LLM-Mixer: Multiscale Mixing in LLMs for Time Series ForecastingMicrosoft · Table Representation Learning Workshop (TRL)12 citationsJan 1, 2025SLAM-Omni: Timbre-Controllable Voice Interaction System with Single-Stage TrainingMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)12 citationsJan 1, 2025Markov Chain of Thought for Efficient Mathematical ReasoningAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)12 citationsJan 1, 2025ReIFE: Re-evaluating Instruction-Following EvaluationAllen Institute for AI · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)12 citationsJan 1, 2025CLaMP 2: Multimodal Music Information Retrieval Across 101 Languages Using Large Language ModelsMicrosoft · Findings of the Association for Computational Linguistics: NAACL12 citationsJan 1, 2025Survey on Backdoor Attacks on Deep Learning: Current Trends, Categorization, Applications, Research Challenges, and Future ProspectsTechnology Innovation Institute · IEEE Access12 citationsJan 1, 2025Nutrition Estimation for Dietary Management: A Transformer Approach With Depth SensingNVIDIA · IEEE Transactions on Multimedia12 citationsJan 1, 2025Diverse AI Feedback For Large Language Model AlignmentAlibaba · Transactions of the Association for Computational Linguistics12 citationsJan 1, 2025Transformers as TransducersAllen Institute for AI · Transactions of the Association for Computational Linguistics12 citationsJan 1, 2025AdaMesh: Personalized Facial Expressions and Head Poses for Adaptive Speech-Driven 3D Facial AnimationSenseTime · IEEE Transactions on Multimedia12 citationsJan 1, 2025