Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-ConsistencySenseTime · Lecture notes in computer science35 citationsJan 1Conditional Memory via Scalable Lookup: A New Axis of Sparsity for Large Language ModelsDeepSeek · Proceedings of the conference - Association for Computational Linguistics. Meeting34 citationsJan 1Integrating Large Language Models Into Recommendation via Mutual Augmentation and Adaptive AggregationSenseTime · IEEE Journal of Selected Topics in Signal Processing34 citationsJan 1DeformGS: Scene Flow in Highly Deformable Scenes for Deformable Object ManipulationNVIDIA · Springer proceedings in advanced robotics31 citationsJan 1Memp: Exploring Agent Procedural MemoryAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)23 citationsJan 1LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation ModelsMeta · Conference on Empirical Methods in Natural Language Processing (EMNLP)18 citationsJan 1Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language ModelsAnthropic · Conference of the European Chapter of the Association for Computational Linguistics16 citationsJan 1View-Centric Multiobject Tracking With Homographic Matching in Moving UAVAlibaba · IEEE Transactions on Geoscience and Remote Sensing16 citationsJan 1Person identity shift for privacy-preserving person re-identificationMicrosoft · Science China Information Sciences16 citationsJan 1DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model With Self-Generated Cross-Modal AlignmentNVIDIA · IEEE Transactions on Audio Speech and Language Processing15 citationsJan 1Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive TasksAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1AutoML-Pipeline: A RAG-Enhanced Code Generation Framework With Pre-Validation for Cloud-Native Machine Learning WorkflowsMicrosoft · IEEE Access14 citationsJan 1CAGR: A Cross-Accelerator Graph Optimization Framework for Efficient Recommender System InferenceMicrosoft · IEEE Access13 citationsJan 1SACTOR: LLM-Driven Correct and Idiomatic C to Rust Translation with Static Analysis and FFI-Based VerificationAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting11 citationsJan 1Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent SkillsAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)11 citationsJan 1Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model AgentsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting10 citationsJan 1Down with the Hierarchy: The ‘H’ in HNSW Stands for “Hubs”Alphabet · Lecture notes in computer science10 citationsJan 1From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level AlignmentAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting10 citationsJan 1Quantifying and Improving the Robustness of Retrieval-Augmented Language Models Against Spurious Features in Grounding DataMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1TAMAS: Benchmarking Adversarial Risks in Multi-Agent LLM SystemsMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1DRL-Adapt: Deep Reinforcement Learning for Adaptive Routing Convergence Optimization in Large-Scale NetworksMicrosoft · IEEE Open Journal of the Computer Society9 citationsJan 1Multi-Granularity Prediction with Learnable Fusion for Scene Text RecognitionAlibaba · International Journal of Computer Vision9 citationsJan 1Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent EvolutionAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)9 citationsJan 1Glyph: Scaling Context Windows via Visual-Text CompressionZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting9 citationsJan 1Towards General Agentic Intelligence via Environment ScalingAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)9 citationsJan 1