Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Efficiently Editing Mixture-of-Experts Models with Compressed ExpertsMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)7 citationsJan 1, 2025MASSV: Multimodal Adaptation and Self-Data Distillation for Speculative Decoding of Vision-Language ModelsCerebras Systems · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)7 citationsJan 1, 2025Chain of Strategy Optimization Makes Large Language Models Better Emotional SupporteriFlytek · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)7 citationsJan 1, 2025AMANDA: Agentic Medical Knowledge Augmentation for Data-Efficient Medical Visual Question AnsweringMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)7 citationsJan 1, 2025A2AS: Agentic AI Runtime Security and Self-DefenseAlphabet · SSRN Electronic Journal7 citationsJan 1, 2025Dynamic Risk Assessments for Offensive Cybersecurity AgentsMicrosoft · neural information processing systems7 citationsJan 1, 2025DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition Under Realistic Single-Channel ConditionsiFlytek · IEEE Transactions on Audio Speech and Language Processing7 citationsJan 1, 2025Exploring the Coordination of Frequency and Attention in Masked Image ModelingAlibaba · IEEE Transactions on Image Processing7 citationsJan 1, 2025RPO: Retrieval Preference Optimization for Robust Retrieval-Augmented GenerationiFlytek · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Chinese SafetyQA: A Safety Short-form Factuality Benchmark for Large Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025DEEPER Insight into Your User: Directed Persona Refinement for Dynamic Persona ModelingAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Interactive and Expressive Code-Augmented Planning with Large Language ModelsLG AI Research · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Aligned but Blind: Alignment Increases Implicit Bias by Reducing Awareness of RaceAllen Institute for AI · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert ModelsAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Mitigate Position Bias in LLMs via Scaling a Single Hidden States ChannelMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)7 citationsJan 1, 2025HellaSwag-Pro: A Large-Scale Bilingual Benchmark for Evaluating the Robustness of LLMs in Commonsense ReasoningAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)7 citationsJan 1, 2025PGPO: Enhancing Agent Reasoning via Pseudocode-style Planning Guided Preference OptimizationAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)7 citationsJan 1, 2025Value Compass Benchmarks: A Comprehensive, Generative and Self-Evolving Platform for LLMs’ Value EvaluationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting7 citationsJan 1, 2025Little Giants: Synthesizing High-Quality Embedding Data at ScaleMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)7 citationsJan 1, 2025Generative Prompt InternalizationMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)7 citationsJan 1, 2025An Efficient Rehearsal Scheme for Catastrophic Forgetting Mitigation during Multi-stage Fine-tuningAlphabet · Findings of the Association for Computational Linguistics: NAACL7 citationsJan 1, 2025Concise and Organized Perception Facilitates Reasoning in Large Language ModelsAlibaba · Findings of the Association for Computational Linguistics: NAACL7 citationsJan 1, 2025Improving Hyperparameter Optimization with Checkpointed Model WeightsNVIDIA · Lecture notes in computer science7 citationsJan 1, 2025Embedding Geometries of Contrastive Language-Image Pre-trainingCohere · Lecture notes in computer science7 citationsJan 1, 2025Voice Attribute Editing With Text PromptiFlytek · IEEE Transactions on Audio Speech and Language Processing7 citationsJan 1, 2025