Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
SongBloom: Coherent Song Generation via Interleaved Autoregressive Sketching and Diffusion RefinementMicrosoft · neural information processing systems17 citationsJan 1, 2025Robust LLM Alignment via Distributionally Robust Direct Preference OptimizationAlphabet · neural information processing systems17 citationsJan 1, 2025Co-Reinforcement Learning for Unified Multimodal Understanding and GenerationMicrosoft · neural information processing systems17 citationsJan 1, 2025DataRater: Meta-Learned Dataset CurationAlphabet, Google DeepMind · neural information processing systems17 citationsJan 1, 2025Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented AugmentationNVIDIA · neural information processing systems17 citationsJan 1, 2025MIRA: Medical Time Series Foundation Model for Real-World Health DataMicrosoft · neural information processing systems17 citationsJan 1, 2025ExeCoder: Empowering Large Language Models with Executability Representation for Code TranslationMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)17 citationsJan 1, 2025Examining False Positives under Inference Scaling for Mathematical ReasoningMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)17 citationsJan 1, 2025From Bytes to Ideas: Language Modeling with Autoregressive U-NetsMeta · neural information processing systems17 citationsJan 1, 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language ModelsAlibaba · neural information processing systems17 citationsJan 1, 2025X-Scene: Large-Scale Driving Scene Generation with High Fidelity and Flexible ControllabilityOpenAI · neural information processing systems17 citationsJan 1, 2025Critical Batch Size Revisited: A Simple Empirical Approach to Large-Batch Language Model TrainingAllen Institute for AI · neural information processing systems17 citationsJan 1, 2025Ontology-Guided Reverse Thinking Makes Large Language Models Stronger on Knowledge Graph Question AnsweringiFlytek · Proceedings of the conference - Association for Computational Linguistics. Meeting17 citationsJan 1, 2025Task Facet Learning: A Structured Approach To Prompt OptimizationMicrosoft · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)17 citationsJan 1, 2025Pre-training Distillation for Large Language Models: A Design Space ExplorationZhipu AI · Proceedings of the conference - Association for Computational Linguistics. Meeting17 citationsJan 1, 2025Generative quantum combinatorial optimization by means of a novel conditional generative quantum eigensolverNVIDIA · Digital Discovery17 citationsJan 1, 2025SeaLLMs 3: Open Foundation and Chat Multilingual Large Language Models for Southeast Asian LanguagesAlibaba · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)17 citationsJan 1, 2025Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language ModelsAllen Institute for AI · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT)17 citationsJan 1, 2025Verifiable Format Control for Large Language Model GenerationsMicrosoft · Findings of the Association for Computational Linguistics: NAACL17 citationsJan 1, 2025Improving Visual Object Tracking Through Visual PromptingMicrosoft · IEEE Transactions on Multimedia17 citationsJan 1, 2025Nested Learning: The Illusion of Deep Learning ArchitecturesAlphabet · neural information processing systems16 citationsJan 1, 2025OmniTalker: One-shot Real-time Text-Driven Talking Audio-Video Generation With Multimodal Style MimickingAlibaba · neural information processing systems16 citationsJan 1, 2025Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware PermutationNVIDIA · neural information processing systems16 citationsJan 1, 2025FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video DiffusionAlibaba · neural information processing systems16 citationsJan 1, 2025Scaling Offline RL via Efficient and Expressive Shortcut ModelsDatabricks · neural information processing systems16 citationsJan 1, 2025