Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RLAlphabet, Google DeepMind, Meta · neural information processing systemsJan 1, 2025Mixture of Languages: Improved Multilingual Encoders Through Language GroupingMeta · Conference on Empirical Methods in Natural Language Processing (EMNLP)Jan 1, 2025A Decoupled Multi-Agent Framework for Complex Text Style TransferMeta · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)Jan 1, 2025What’s in Common? Multimodal Models Hallucinate When Reasoning Across ScenesMeta · neural information processing systemsJan 1, 2025Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion GamesMeta · neural information processing systemsJan 1, 2025From Bytes to Ideas: Language Modeling with Autoregressive U-NetsMeta · neural information processing systemsJan 1, 2025Probabilistic Token Alignment for Large Language Model FusionMeta · neural information processing systemsJan 1, 2025DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision AssignmentMeta · neural information processing systemsJan 1, 2025Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewardsGoogle DeepMind, Meta · neural information processing systemsJan 1, 2025Logic.py: Bridging the Gap between LLMs and Constraint SolversMeta · neural information processing systemsJan 1, 2025The Art of Tool Interface DesignMeta · arXivJan 1, 2025Architecting Analytics-Driven Mobile Ecosystems: Scalable Backend Frameworks for Intelligent Data Flow and Real-Time User InsightsMeta · International Journal of Artificial Intelligence Data Science and Machine LearningJan 1, 2025Personalized Learning Pathways: AI-Adaptive Educational Technology Supporting Diverse Learning NeedsMeta · Technix International Journal for Engineering ResearchJan 1, 2025Demystifying Spam Measurement Systems in AI-Powered Distributed ArchitecturesMeta · Technix International Journal for Engineering ResearchJan 1, 2025Mixed Reality: Revolutionizing Education and Industrial Operations Through Immersive TechnologyMeta · Technix International Journal for Engineering ResearchJan 1, 2025Automatic Optimization Method for Database Indexing By Integrating Monte Carlo Tree Search and Graph Neural NetworkMeta · Procedia Computer ScienceJan 1, 2025Dynamic Fisher-weighted Model Merging via Bayesian OptimizationMeta · Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL)Jan 1, 2025Integrating Artificial Intelligence and Machine Learning Across IT Domains: Advances in Networking, Security, Finance, IoT, and Energy SystemsMeta · Journal of Emerging Technologies and Innovative ResearchJan 1, 2025NaturalReasoning: Reasoning in the Wild with 2.8M Challenging QuestionsMeta · neural information processing systemsJan 1, 2025When Worse is Better: Navigating the Compression Generation Trade-off In Visual TokenizationAllen Institute for AI, Meta · neural information processing systemsJan 1, 2025AdvPrefix: An Objective for Nuanced LLM JailbreaksMeta · neural information processing systemsJan 1, 2025Linguini: A benchmark for language-agnostic linguistic reasoningMeta · neural information processing systemsJan 1, 2025