Research

A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.

Field
Lab

13,724 papers in Computer Science, newest first. Some proceedings carry OpenAlex's date of January 1.

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging QuestionsMeta · neural information processing systems86 citationsJan 1, 2025CodexGraph: Bridging Large Language Models and Code Repositories via Code Graph DatabasesAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)85 citationsJan 1, 2025Breaking Agents: Compromising Autonomous LLM Agents Through Malfunction AmplificationMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)83 citationsJan 1, 2025Scaling RL to Long VideosAlphabet, NVIDIA · neural information processing systems83 citationsJan 1, 2025Wait, We Don’t Need to “Wait”! Removing Thinking Tokens Improves Reasoning EfficiencyAllen Institute for AI · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)81 citationsJan 1, 2025The BiGGen Bench: A Principled Benchmark for Fine-grained Evaluation of Language Models with Language ModelsLG AI Research · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)81 citationsJan 1, 2025Chain-of-Retrieval Augmented GenerationMicrosoft · neural information processing systems78 citationsJan 1, 2025HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and LanguagesNVIDIA · neural information processing systems77 citationsJan 1, 2025IrokoBench: A New Benchmark for African Languages in the Age of Large Language ModelsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)77 citationsJan 1, 2025Unlocking Multimodal Mathematical Reasoning via Process Reward ModelAlibaba · neural information processing systems76 citationsJan 1, 2025Network Digital Twin for 6G and Beyond: An End-to-End View Across Multi-Domain Network EcosystemsNVIDIA · IEEE Open Journal of the Communications Society75 citationsJan 1, 2025The Matrix: Infinite-Horizon World Generation with Real-Time Moving ControlAlibaba · neural information processing systems74 citationsJan 1, 2025VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation ModelsMicrosoft · neural information processing systems73 citationsJan 1, 2025VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement LearningAlibaba · neural information processing systems73 citationsJan 1, 2025OLMES: A Standard for Language Model EvaluationsAllen Institute for AI · Findings of the Association for Computational Linguistics: NAACL71 citationsJan 1, 2025Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous ThoughtMeta, NVIDIA · neural information processing systems70 citationsJan 1, 2025Autoregressive Speech Synthesis without Vector QuantizationMicrosoft · Proceedings of the conference - Association for Computational Linguistics. Meeting70 citationsJan 1, 2025Physics of Language Models: Part 2.1, Grade-School Math and the Hidden Reasoning ProcessAlphabet, Meta · SSRN Electronic Journal70 citationsJan 1, 2025Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language ModelsAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting69 citationsJan 1, 2025Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and ResearchAlphabet, Google DeepMind, Microsoft · neural information processing systems69 citationsJan 1, 2025BumbleBee: Secure Two-party Inference Framework for Large TransformersAlibaba · Network and Distributed System Security Symposium69 citationsJan 1, 2025Gymnasium: A Standard Interface for Reinforcement Learning EnvironmentsMeta · neural information processing systems68 citationsJan 1, 2025RewardBench: Evaluating Reward Models for Language ModelingAllen Institute for AI · Findings of the Association for Computational Linguistics: NAACL68 citationsJan 1, 2025Deep Video Discovery: Agentic Search with Tool Use for Long-form Video UnderstandingMicrosoft · neural information processing systems67 citationsJan 1, 2025Autoregressive Adversarial Post-Training for Real-Time Interactive Video GenerationAlibaba · neural information processing systems67 citationsJan 1, 2025