Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Inverse Scaling in Test-Time ComputeAnthropic · arXiv (Cornell University)50 citationsJul 19, 2025Enhancing LLMs for Power System Simulations: A Feedback-Driven Multi-Agent FrameworkAlibaba · IEEE Transactions on Smart Grid56 citationsJul 18, 2025A Large-Scale Study of Relevance Assessments with Large Language Models Using UMBRELAMicrosoft · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)20 citationsJul 18, 2025W-RAG: Weakly Supervised Dense Retrieval in RAG for Open-domain Question AnsweringMeta · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)17 citationsJul 18, 2025Demographically-Inspired Query Variants Using an LLMMicrosoft · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)9 citationsJul 18, 2025Towards Two-Stage Counterfactual Learning to RankMeta · ACM SIGIR International Conference on Theory of Information Retrieval (ICTIR)5 citationsJul 18, 2025In-Depth and In-Breadth: Pre-training Multimodal Language Models Customized for Comprehensive Chart UnderstandingMicrosoft · arXiv (Cornell University)4 citationsJul 18, 2025Inner-character and Inner-word Features Based Representation Learning for Chinese Word EmbeddingMininglamp Technology · ACM Transactions on Asian and Low-Resource Language Information Processing1 citationJul 18, 2025AutoPartGen: Autogressive 3D Part Generation and DiscoveryMeta · arXiv (Cornell University)32 citationsJul 17, 2025VideoITG: Multimodal Video Understanding with Instructed Temporal GroundingNVIDIA · arXiv (Cornell University)30 citationsJul 17, 2025Global earthquake detection and warning using Android phonesAlphabet · Science23 citationsJul 17, 2025FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion TransformersAlibaba · arXiv (Cornell University)15 citationsJul 17, 2025Intent-Based Network for RAN Management with Large Language ModelsNVIDIA · arXiv (Cornell University)12 citationsJul 17, 2025Learning to summarize user information for personalized reinforcement learning from human feedbackMicrosoft · arXiv (Cornell University)10 citationsJul 17, 2025Growing Sparse Quantum Codes from a SeedMicrosoft · arXiv (Cornell University)4 citationsJul 17, 2025Bridging Gaps Between Student and Expert Evaluations of AI-Generated Programming HintsMicrosoft · ACM Conference on Learning @ Scale (L@S)4 citationsJul 17, 2025Insights into a radiology-specialised multimodal large language model with sparse autoencodersMicrosoft · arXiv (Cornell University)3 citationsJul 17, 2025Spectral Bellman Method: Unifying Representation and Exploration in RLAlphabet, NVIDIA · arXiv (Cornell University)2 citationsJul 17, 2025TransEvalnia: Reasoning-based Evaluation and Ranking of TranslationsSakana AI · arXiv (Cornell University)2 citationsJul 17, 2025Change of Thought: Adaptive Test-Time ComputationAlphabet · arXiv (Cornell University)Jul 17, 2025Optimizers Qualitatively Alter Solutions And We Should Leverage ThisGoogle DeepMind · arXiv (Cornell University)21 citationsJul 16, 2025Re-Boosting Self-Collaboration Parallel Prompt GAN for Unsupervised Image RestorationAlphabet, Google DeepMind · IEEE Transactions on Pattern Analysis and Machine Intelligence20 citationsJul 16, 2025Thought Purity: A Defense Framework For Chain-of-Thought AttackAlibaba · arXiv (Cornell University)6 citationsJul 16, 2025Representation-driven sampling and adaptive policy resetting for improving multi-Agent reinforcement learningiFlytek · Neural Networks5 citationsJul 16, 2025Dual form Complementary Masking for Domain-Adaptive Image SegmentationiFlytek · arXiv (Cornell University)2 citationsJul 16, 2025