Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Personalized Safety in LLMs: A Benchmark and A Planning-Based Agent ApproachMicrosoft · neural information processing systems14 citationsJan 1, 2025A Unified Agentic Framework for Evaluating Conditional Image GenerationAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025FlashAudio: Rectified Flow for Fast and High-Fidelity Text-to-Audio GenerationAlibaba, Meta · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and CompetitionAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025ToolCoder: A Systematic Code-Empowered Tool Learning Framework for Large Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025AIR-Bench: Automated Heterogeneous Information Retrieval BenchmarkJina AI · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025MedCite: Can Language Models Generate Verifiable Text for Medicine?Microsoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)14 citationsJan 1, 2025BELLE: A Bi-Level Multi-Agent Reasoning Framework for Multi-Hop Question AnsweringAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting14 citationsJan 1, 2025Iterative Self-Tuning LLMs for Enhanced Jailbreaking CapabilitiesMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)14 citationsJan 1, 2025ComPO: Community Preferences for Language Model PersonalizationAllen Institute for AI · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)14 citationsJan 1, 2025Graph Neural Network Enhanced Retrieval for Question Answering of Large Language ModelsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)14 citationsJan 1, 2025CausalGraph2LLM: Evaluating LLMs for Causal QueriesAlphabet · Findings of the Association for Computational Linguistics: NAACL14 citationsJan 1, 2025A Tight VC-Dimension Analysis of Clustering Coresets with ApplicationsAlphabet · Society for Industrial and Applied Mathematics eBooks14 citationsJan 1, 2025Almost Tight Bounds for Differentially Private Densest SubgraphAlphabet · Society for Industrial and Applied Mathematics eBooks14 citationsJan 1, 2025GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New InsightsGoogle DeepMind · neural information processing systems13 citationsJan 1, 2025Fundamental Limitations in Pointwise Defences of LLM Finetuning APIsOpenAI · neural information processing systems13 citationsJan 1, 2025Simulating Society Requires Simulating ThoughtAlphabet · neural information processing systems13 citationsJan 1, 2025UniEdit: A Unified Knowledge Editing Benchmark for Large Language ModelsAlibaba · neural information processing systems13 citationsJan 1, 2025PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and EnhancementMicrosoft · neural information processing systems13 citationsJan 1, 2025DREAM: Drafting with Refined Target Features and Entropy-Adaptive Cross-Attention Fusion for Multimodal Speculative DecodingCerebras Systems · neural information processing systems13 citationsJan 1, 2025Inference-Time Hyper-Scaling with KV Cache CompressionNVIDIA · neural information processing systems13 citationsJan 1, 2025UNComp: Can Matrix Entropy Uncover Sparsity? — A Compressor Design from an Uncertainty-Aware PerspectiveMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)13 citationsJan 1, 2025ReliableEval: A Recipe for Stochastic LLM Evaluation via Method of MomentsAlphabet · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)13 citationsJan 1, 2025Findings of the WMT25 General Machine Translation Shared Task: Time to Stop Evaluating on Easy Test SetsAlphabet, Microsoft · Conference on Machine Translation (WMT)13 citationsJan 1, 2025Controlling Thinking Speed in Reasoning ModelsAlibaba · neural information processing systems13 citationsJan 1, 2025