Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL CyclesAlphabet, Google DeepMind · neural information processing systems193 citationsJan 1, 2025OpenCUA: Open Foundations for Computer-Use AgentsAlibaba · neural information processing systems187 citationsJan 1, 2025Position: Towards Bidirectional Human-AI AlignmentAlphabet, Google DeepMind, Microsoft · neural information processing systems185 citationsJan 1, 2025Design2Code: Benchmarking Multimodal Code Generation for Automated Front-End EngineeringGoogle DeepMind, Microsoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)185 citationsJan 1, 2025Knowledge Graph-Guided Retrieval Augmented GenerationAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)178 citationsJan 1, 2025Know Your Limits: A Survey of Abstention in Large Language ModelsAllen Institute for AI · Transactions of the Association for Computational Linguistics161 citationsJan 1, 2025Neural Codec Language Models are Zero-Shot Text to Speech SynthesizersMicrosoft · IEEE Transactions on Audio Speech and Language Processing160 citationsJan 1, 2025Generalizing Verifiable Instruction FollowingAllen Institute for AI · neural information processing systems158 citationsJan 1, 2025The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-DeterminismAllen Institute for AI · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)145 citationsJan 1, 2025SWE-bench Goes Live!Microsoft · neural information processing systems144 citationsJan 1, 2025RetrievalAttention: Accelerating Long-Context LLM Inference via Vector RetrievalMicrosoft · neural information processing systems144 citationsJan 1, 2025APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human InterplayOpenAI · neural information processing systems143 citationsJan 1, 2025WASP: Benchmarking Web Agent Security Against Prompt Injection AttacksMeta · neural information processing systems140 citationsJan 1, 2025Astute RAG: Overcoming Imperfect Retrieval Augmentation and Knowledge Conflicts for Large Language ModelsAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting135 citationsJan 1, 2025MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their MixMicrosoft · neural information processing systems133 citationsJan 1, 2025LMFusion: Adapting Pretrained Language Models for Multimodal GenerationOpenAI · neural information processing systems132 citationsJan 1, 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-ImprovementMicrosoft · neural information processing systems132 citationsJan 1, 2025Aria-UI: Visual Grounding for GUI InstructionsAlibaba · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)132 citationsJan 1, 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize BetterAlphabet, Google DeepMind · neural information processing systems130 citationsJan 1, 2025Physics of Language Models: Part 3.3, Knowledge Capacity Scaling LawsMeta · SSRN Electronic Journal129 citationsJan 1, 2025Best-of-N JailbreakingAnthropic · neural information processing systems129 citationsJan 1, 2025mPLUG-DocOwl2: High-resolution Compressing for OCR-free Multi-page Document UnderstandingAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting128 citationsJan 1, 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task AutomationGoogle DeepMind · neural information processing systems121 citationsJan 1, 2025Simplicity Prevails: Rethinking Negative Preference Optimization for LLM UnlearningOpenAI · neural information processing systems116 citationsJan 1, 2025WritingBench: A Comprehensive Benchmark for Generative WritingAlibaba · neural information processing systems114 citationsJan 1, 2025