Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal SystemsAlphabet, Google DeepMind · neural information processing systems4 citationsJan 1, 2025Small Changes, Large Consequences: Analyzing the Allocational Fairness of LLMs in Hiring ContextsCohere · International Joint Conference on Natural Language Processing and Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (IJCNLP-AACL)4 citationsJan 1, 2025Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point IterationsGoogle DeepMind · neural information processing systems4 citationsJan 1, 2025Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian SplattingAlphabet · neural information processing systems4 citationsJan 1, 2025Next Semantic Scale Prediction via Hierarchical Diffusion Language ModelsMicrosoft · neural information processing systems4 citationsJan 1, 2025Bigram Subnetworks: Mapping to Next Tokens in Transformer Language ModelsGoogle DeepMind · neural information processing systems4 citationsJan 1, 2025ARGenSeg: Image Segmentation with Autoregressive Image Generation ModelAlibaba · neural information processing systems4 citationsJan 1, 2025Less is More: Unlocking Specialization of Time Series Foundation Models via Structured PruningAlibaba · neural information processing systems4 citationsJan 1, 2025Transition Matching: Scalable and Flexible Generative ModelingMeta · neural information processing systems4 citationsJan 1, 2025Overcoming Long Context Limitations of State Space Models via Context Dependent Sparse AttentionNVIDIA · neural information processing systems4 citationsJan 1, 2025NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data ConstraintsSenseTime · neural information processing systems4 citationsJan 1, 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement LearningAlibaba · neural information processing systems4 citationsJan 1, 2025Convergent Functions, Divergent FormsAllen Institute for AI · neural information processing systems4 citationsJan 1, 2025Empowering Healthcare Practitioners with Language Models: Structuring Speech Transcripts in Two Real-World Clinical ApplicationsMicrosoft · Conference on Empirical Methods in Natural Language Processing (EMNLP)4 citationsJan 1, 2025Enhancing Reasoning Abilities of Small LLMs with Cognitive AlignmentAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)4 citationsJan 1, 2025A Probabilistic Inference Scaling Theory for LLM Self-CorrectionAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)4 citationsJan 1, 2025Language Model Based Text-to-Audio Generation: Anti-Causally Aligned Collaborative Residual TransformersAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)4 citationsJan 1, 2025Chinese Toxic Language Mitigation via Sentiment Polarity Consistent RewritesAlibaba · Conference on Empirical Methods in Natural Language Processing (EMNLP)4 citationsJan 1, 2025Scale Down to Speed Up: Dynamic Data Selection for Reinforcement LearningAlibaba · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)4 citationsJan 1, 2025Can You Trick the Grader? Adversarial Persuasion of LLM JudgesLG AI Research · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)4 citationsJan 1, 2025Teaching Language Models To Gather Information ProactivelyMicrosoft · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)4 citationsJan 1, 2025Elastic ViTs from Pretrained Models without RetrainingNVIDIA · neural information processing systems4 citationsJan 1, 2025Memory Mosaics at scaleMeta · neural information processing systems4 citationsJan 1, 2025NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMsMeta · neural information processing systems4 citationsJan 1, 2025LoRASuite: Efficient LoRA Adaptation Across Large Language Model UpgradesAlibaba · neural information processing systems4 citationsJan 1, 2025