Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse AttentionDeepSeek · Proceedings of the conference - Association for Computational Linguistics. Meeting415 citationsJan 1, 2025Titans: Learning to Memorize at Test TimeAlphabet · neural information processing systems342 citationsJan 1, 2025Absolute Zero: Reinforced Self-play Reasoning with Zero DataAlibaba, Google DeepMind · neural information processing systems336 citationsJan 1, 2025LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context MultitasksZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting327 citationsJan 1, 2025Generative AI in cybersecurity: A comprehensive review of LLM applications and vulnerabilitiesTechnology Innovation Institute · Internet of Things and Cyber-Physical Systems324 citationsJan 1, 2025TheAgentCompany: Benchmarking LLM Agents on Consequential Real World TasksAlibaba, Meta, Microsoft · neural information processing systems323 citationsJan 1, 2025ReSearch: Learning to Reason with Search for LLMs via Reinforcement LearningMicrosoft · neural information processing systems314 citationsJan 1, 2025SWE-smith: Scaling Data for Software Engineering AgentsAlibaba · neural information processing systems300 citationsJan 1, 2025Reinforcement Learning for Reasoning in Large Language Models with One Training ExampleMicrosoft · neural information processing systems296 citationsJan 1, 2025GPT4RoI: Instruction Tuning Large Language Model on Region-of-InterestAlibaba · Lecture notes in computer science294 citationsJan 1, 2025ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language ModelsMicrosoft · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)287 citationsJan 1, 2025Perception Encoder: The best visual embeddings are not at the output of the networkMeta, xAI · neural information processing systems278 citationsJan 1, 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software EvolutionDatabricks, Meta · neural information processing systems265 citationsJan 1, 2025ProcessBench: Identifying Process Errors in Mathematical ReasoningAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting265 citationsJan 1, 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time TestMicrosoft · neural information processing systems256 citationsJan 1, 2025Improving Video Generation with Human FeedbackAlibaba · neural information processing systems237 citationsJan 1, 2025ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language ModelsNVIDIA · neural information processing systems230 citationsJan 1, 2025WebDancer: Towards Autonomous Information Seeking AgencyAlibaba · neural information processing systems227 citationsJan 1, 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-FreeAlibaba · neural information processing systems223 citationsJan 1, 2025Global MMLU: Understanding and Addressing Cultural and Linguistic Biases in Multilingual EvaluationCohere, Hugging Face · Proceedings of the conference - Association for Computational Linguistics. Meeting222 citationsJan 1, 2025AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language ReasoningAlibaba · neural information processing systems219 citationsJan 1, 2025Physics of Language Models: Part 3.1, Knowledge Storage and ExtractionMeta · SSRN Electronic Journal213 citationsJan 1, 2025Multi-SWE-bench: A Multilingual Benchmark for Issue ResolvingAlibaba · neural information processing systems208 citationsJan 1, 2025VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech InteractionAlibaba · neural information processing systems202 citationsJan 1, 2025WebWalker: Benchmarking LLMs in Web TraversalAlibaba · Proceedings of the conference - Association for Computational Linguistics. Meeting201 citationsJan 1, 2025