Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel DecodingNVIDIA · arXiv (Cornell University)325 citationsMay 28, 2025A survey of geometric graph neural networks: data structures, models and applicationsAlibaba · Frontiers of Computer Science102 citationsMay 28, 2025ASVspoof 5: Design, collection and validation of resources for spoofing, deepfake, and adversarial attack detection using crowdsourced speechMicrosoft · Computer Speech & Language40 citationsMay 28, 2025EvolveSearch: An Iterative Self-Evolving Search AgentAlibaba · arXiv (Cornell University)32 citationsMay 28, 2025EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video GuidanceAllen Institute for AI · arXiv (Cornell University)21 citationsMay 28, 2025Text2Grad: Reinforcement Learning from Natural Language FeedbackMicrosoft · arXiv (Cornell University)15 citationsMay 28, 2025BOFormer: Learning to Solve Multi-Objective Bayesian Optimization via Non-Markovian RLNVIDIA · arXiv (Cornell University)6 citationsMay 28, 2025Latent Reasoning via Sentence Embedding PredictionLG AI Research · arXiv (Cornell University)4 citationsMay 28, 2025ProCrop: Learning Aesthetic Image Cropping from Professional CompositionsMicrosoft · arXiv (Cornell University)4 citationsMay 28, 2025Efficient Leave-one-out Approximation in LLM Multi-agent Debate Based on IntrospectionAlibaba · arXiv (Cornell University)4 citationsMay 28, 2025Game of Thoughts: Iterative Reasoning in Game-Theoretic Domains with Large Language ModelsGoogle DeepMind · Adaptive Agents and Multi-Agents Systems2 citationsMay 28, 2025Enabling Flexible Multi-LLM Integration for Scalable Knowledge AggregationAlphabet · arXiv (Cornell University)2 citationsMay 28, 2025Calibrated Value-Aware Model Learning with Probabilistic Environment ModelsCohere · arXiv (Cornell University)1 citationMay 28, 2025IRS: Incremental Relationship-guided Segmentation for Digital PathologyNVIDIA · arXiv (Cornell University)1 citationMay 28, 2025Beyond path selection: Better LLMs for Scientific Information Extraction with MimicSFT and Relevance and Rule-induced(R$^2$)GRPOZhipu AI · arXiv (Cornell University)1 citationMay 28, 2025The connected Grundy coloring problem: Formulations and a local-search enhanced biased random-key genetic algorithmMicrosoft · Computers & Operations Research1 citationMay 28, 2025Fairness and Optimality in RoutingAlphabet · Adaptive Agents and Multi-Agents SystemsMay 28, 2025DyESP: Accelerating Hyperparameter-Architecture Search via Dynamic Exploration and Space PruningGoogle DeepMind · Proceedings of the AAAI Symposium SeriesMay 28, 2025FaceChain-MMID: Generating highly identity-consistent realistic portraits via dividing & merging multi-modal representationsAlibaba · Pattern RecognitionMay 28, 2025The Multilingual Divide and Its Impact on Global AI SafetyCohere · arXiv (Cornell University)13 citationsMay 27, 2025Watermarking Without Standards Is Not AI GovernanceMeta · arXiv (Cornell University)12 citationsMay 27, 2025Lunguage: A Benchmark for Structured and Sequential Chest X-ray InterpretationMicrosoft · arXiv (Cornell University)9 citationsMay 27, 2025A Course Correction in Steerability Evaluation: Revealing Miscalibration and Side Effects in LLMsMicrosoft · arXiv (Cornell University)6 citationsMay 27, 2025Improving Code Reviewer Recommendation: Accuracy, Latency, Workload, and BystandersMeta · ACM Transactions on Software Engineering and Methodology6 citationsMay 27, 2025VeriTrail: Closed-Domain Hallucination Detection with TraceabilityMicrosoft · arXiv (Cornell University)5 citationsMay 27, 2025