Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Reasoning with Latent Thoughts: On the Power of Looped TransformersAlphabet · arXiv (Cornell University)130 citationsFeb 24, 2025The Geometry of Refusal in Large Language Models: Concept Cones and Representational IndependenceAlphabet · arXiv (Cornell University)73 citationsFeb 24, 2025AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language ModelsAlibaba · arXiv (Cornell University)29 citationsFeb 24, 2025Synthetic Text Generation for Training Large Language Models via Gradient MatchingAlphabet · arXiv (Cornell University)9 citationsFeb 24, 2025ATEB: Evaluating and Improving Advanced NLP Tasks for Text Embedding ModelsAlphabet, Google DeepMind · arXiv (Cornell University)6 citationsFeb 24, 2025FilterLLM: Text-To-Distribution LLM for Billion-Scale Cold-Start RecommendationAlibaba · arXiv (Cornell University)6 citationsFeb 24, 2025IGDA: Interactive Graph Discovery through Large Language Model AgentsMicrosoft · arXiv (Cornell University)5 citationsFeb 24, 2025LLM Inference Acceleration via Efficient Operation Fusiond-Matrix · arXiv (Cornell University)4 citationsFeb 24, 2025Leveraging Procedural Knowledge and Task Hierarchies for Efficient Instructional Video Pre-trainingGoogle DeepMind · arXiv (Cornell University)3 citationsFeb 24, 2025Can Explanations Improve Recommendations? Evidence from Prediction-Informed ExplanationsAlphabet · arXiv (Cornell University)3 citationsFeb 24, 2025Pleno-Generation: A Scalable Generative Face Video Compression Framework with Bandwidth IntelligenceAlibaba · arXiv (Cornell University)2 citationsFeb 24, 2025Predictive Response Optimization: Using Reinforcement Learning to Fight Online Social Network AbuseMeta · arXiv (Cornell University)Feb 24, 2025Unified Semantic and ID Representation Learning for Deep RecommendersMeta · arXiv (Cornell University)22 citationsFeb 23, 2025WildLong: Synthesizing Realistic Long-Context Instruction Data at ScaleMicrosoft · arXiv (Cornell University)10 citationsFeb 23, 2025StoCFL: A stochastically clustered federated learning framework for Non-IID data with dynamic client participationMeta · Neural Networks47 citationsFeb 22, 2025LLM-Vectorizer: LLM-Based Verified Loop VectorizerMicrosoft · Proceedings of the CGO/Proceedings of the ... CGO38 citationsFeb 22, 2025A Constant Rate Quantum Computer on a LineAlphabet · arXiv (Cornell University)9 citationsFeb 22, 2025Implicit Bias of Gradient Descent for Non-Homogeneous Deep NetworksGoogle DeepMind · arXiv (Cornell University)9 citationsFeb 22, 2025Cross-lingual entity alignment based on complex relationships and fine-grained attributesAlibaba · Applied Soft Computing4 citationsFeb 22, 2025PreFix: Optimizing the Performance of Heap-Intensive ApplicationsAlphabet · Proceedings of the CGO/Proceedings of the ... CGO1 citationFeb 22, 2025Pattern Matching in AI Compilers and Its FormalizationNVIDIA · Proceedings of the CGO/Proceedings of the ... CGOFeb 22, 2025PolarDETR: Polar Parametrization for vision-based surround-view 3D detectionHorizon Robotics · Image and Vision Computing73 citationsFeb 21, 2025S2-Transformer for Mask-Aware Hyperspectral Image ReconstructionMeta · IEEE Transactions on Pattern Analysis and Machine Intelligence31 citationsFeb 21, 2025Addressing biomedical data challenges and opportunities to inform a large-scale data lifecycle for enhanced data sharing, interoperability, analysis, and collaboration across stakeholdersMicrosoft · Scientific Reports27 citationsFeb 21, 2025HydraServe: Minimizing Cold Start Latency for Serverless LLM Serving in Public CloudsAlibaba · arXiv (Cornell University)20 citationsFeb 21, 2025