Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
RMTBench: Benchmarking LLMs Through Multi-Turn User-Centric Role-PlayingAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025ISACL: Internal State Analyzer for Copyrighted Training Data LeakageMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025EfficientXLang: Towards Improving Token Efficiency Through Cross-Lingual ReasoningMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025OVFact: Measuring and Improving Open-Vocabulary Factuality for Long Caption ModelsGoogle DeepMind · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)2 citationsJan 1, 2025Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete ModalitiesAlphabet · neural information processing systems2 citationsJan 1, 2025Towards Automated PetrographyMicrosoft · neural information processing systems2 citationsJan 1, 2025Tail recursion modulo context: An equational approach (extended version)Microsoft · Journal of Functional Programming2 citationsJan 1, 2025Self-Boost via Optimal Retraining: An Analysis via Approximate Message PassingAlphabet · neural information processing systems2 citationsJan 1, 2025Probabilistic Token Alignment for Large Language Model FusionMeta · neural information processing systems2 citationsJan 1, 2025Policy Optimized Text-to-Image Pipeline DesignNVIDIA · neural information processing systems2 citationsJan 1, 20253D Visual Illusion Depth EstimationNVIDIA · neural information processing systems2 citationsJan 1, 2025SegMASt3R: Geometry Grounded Segment MatchingGoogle DeepMind · neural information processing systems2 citationsJan 1, 2025On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel OptimizationAlphabet · neural information processing systems2 citationsJan 1, 2025A Simple Linear Patch Revives Layer-Pruned Large Language ModelsAlibaba · neural information processing systems2 citationsJan 1, 2025AmorLIP: Efficient Language-Image Pretraining via AmortizationAlphabet, Google DeepMind · neural information processing systems2 citationsJan 1, 2025Volume Fusion-Based Self-Supervised Pretraining for 3D Medical Image SegmentationSenseTime · IEEE Transactions on Image Processing2 citationsJan 1, 2025The Cost of Compression: Tight Quadratic Black-Box Attacks on Sketches for $\ell_2$ Norm EstimationAlphabet · neural information processing systems2 citationsJan 1, 2025FineReason: Evaluating and Improving LLMs’ Deliberate Reasoning through Reflective Puzzle SolvingAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1, 2025ARise: Towards Knowledge-Augmented Reasoning via Risk-Adaptive SearchSenseTime · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1, 2025Synergistic Weak-Strong Collaboration by Aligning PreferencesMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1, 2025From English to Second Language Mastery: Enhancing LLMs with Cross-Lingual Continued Instruction TuningAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1, 2025Pruning General Large Language Models into Customized Expert ModelsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)2 citationsJan 1, 2025iTBLS: A Dataset of Interactive Conversations Over Tabular InformationAlphabet · Table Representation Learning Workshop (TRL)2 citationsJan 1, 2025The Art of Tool Interface DesignMeta · Workshop for Research on Agent Language Models (REALM)2 citationsJan 1, 2025DISC: Plug-and-Play Decoding Intervention with Similarity of Characters for Chinese Spelling CheckAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting2 citationsJan 1, 2025