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 systems18 citationsJan 1, 2025In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue AgentsAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting18 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)17 citationsJan 1, 2025Are LLMs Better than Reported? Detecting Label Errors and Mitigating Their Effect on Model PerformanceAlphabet · Conference on Empirical Methods in Natural Language Processing (EMNLP)16 citationsJan 1, 2025Absolute Zero: Reinforced Self-play Reasoning with Zero DataAlibaba, Google DeepMind · neural information processing systems15 citationsJan 1, 2025BIG-Bench Extra HardAlphabet · Proceedings of the conference - Association for Computational Linguistics. Meeting15 citationsJan 1, 2025Nested Learning: The Illusion of Deep Learning ArchitecturesAlphabet · neural information processing systems12 citationsJan 1, 2025Carbon-Aware Computing for Data Centers with Probabilistic Performance GuaranteesAlphabet · IEEE Transactions on Power Systems12 citationsJan 1, 2025Confidence Improves Self-Consistency in LLMsAlphabet · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)12 citationsJan 1, 2025Measuring what Matters: Construct Validity in Large Language Model BenchmarksAllen Institute for AI, Google DeepMind · neural information processing systems10 citationsJan 1, 2025Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion TransformersGoogle DeepMind · neural information processing systems9 citationsJan 1, 2025Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control SignalsAlphabet · neural information processing systems9 citationsJan 1, 2025A deep learning and digital archaeology approach for mosquito repellent discoveryAlphabet · Chemical Senses9 citationsJan 1, 2025Grounded Reinforcement Learning for Visual ReasoningAlphabet · neural information processing systems8 citationsJan 1, 2025PerceptionLM: Open-Access Data and Models for Detailed Visual UnderstandingAlphabet, Meta · neural information processing systems8 citationsJan 1, 2025MiniMax-Remover: Taming Bad Noise Helps Video Object RemovalGoogle DeepMind · neural information processing systems8 citationsJan 1, 2025AIM 2024 Sparse Neural Rendering Challenge: Methods and ResultsAlphabet · Lecture notes in computer science8 citationsJan 1, 2025WorldModelBench: Judging Video Generation Models As World ModelsAlphabet, NVIDIA · neural information processing systems7 citationsJan 1, 2025SensorLM: Learning the Language of Wearable SensorsAlphabet, Google DeepMind · neural information processing systems7 citationsJan 1, 2025Meta CLIP 2: A Worldwide Scaling RecipeGoogle DeepMind, Meta, OpenAI · neural information processing systems7 citationsJan 1, 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing ModelsAlphabet, Google DeepMind, Microsoft · neural information processing systems7 citationsJan 1, 2025Temporal Chain of Thought: Long-Video Understanding by Thinking in FramesAlphabet, Google DeepMind · neural information processing systems6 citationsJan 1, 2025Meta-World+: An Improved, Standardized, RL BenchmarkAlphabet · neural information processing systems6 citationsJan 1, 2025Video World Models with Long-term Spatial MemoryGoogle DeepMind · neural information processing systems6 citationsJan 1, 2025MindJourney: Test-Time Scaling with World Models for Spatial ReasoningGoogle DeepMind, Microsoft · neural information processing systems6 citationsJan 1, 2025