Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
Enhancing Mixture-of-Experts Specialization via Cluster-Aware UpcyclingLG AI Research · arXiv (Cornell University)Apr 15ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense RetrievalLG AI Research · arXiv (Cornell University)Apr 13DuET: Dual Execution for Test Output Prediction with Generated Code and PseudocodeLG AI Research · arXiv (Cornell University)Apr 13DuET: Dual Execution for Test Output Prediction with Generated Code and PseudocodeLG AI Research · arXiv (Cornell University)Apr 13ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense RetrievalLG AI Research · arXiv (Cornell University)Apr 13Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language ModelsLG AI Research · arXiv (Cornell University)Apr 12Multi-Drafter Speculative Decoding with Alignment FeedbackLG AI Research · arXiv (Cornell University)Apr 7Multi-Drafter Speculative Decoding with Alignment FeedbackLG AI Research · arXiv (Cornell University)Apr 7Rank-Aware Conditional Synthesis: Feasible Quantum Generative Modeling on Matrix Product State ManifoldsLG AI Research · SymmetryApr 2Rethinking Multimodal Fusion for Time Series: Text Modalities Need Constrained FusionLG AI Research · arXiv (Cornell University)Mar 23OrcheCause Agent: From Textual Knowledge to End-to-End Causal InferenceLG AI Research · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14AEGIS: Toward Expert-in-the-loop Industrial Anomaly DetectionLG AI Research · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14RL-Studio: A System for Multi-Phase Reinforcement Learning ExperimentationLG AI Research · Proceedings of the AAAI Conference on Artificial IntelligenceMar 14RetroReasoner: A Reasoning LLM for Strategic Retrosynthesis PredictionLG AI Research · arXiv (Cornell University)1 citationMar 13MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion ModelsLG AI Research · arXiv (Cornell University)Feb 19MERIT Feedback Elicits Better Bargaining in LLM NegotiatorsLG AI Research · arXiv (Cornell University)Feb 11MERIT Feedback Elicits Better Bargaining in LLM NegotiatorsLG AI Research · arXiv (Cornell University)Feb 11CADO: From Imitation to Cost Minimization for Heatmap-based Solvers in Combinatorial OptimizationLG AI Research · arXiv (Cornell University)Feb 9When Is Enough Not Enough? Illusory Completion in Search AgentsLG AI Research · arXiv (Cornell University)Feb 7Lost in the Noise: How Reasoning Models Fail with Contextual DistractorsLG AI Research · arXiv (Cornell University)1 citationJan 12Judging Against the Reference: Uncovering Knowledge-Driven Failures in LLM-Judges on QA EvaluationLG AI Research · arXiv (Cornell University)Jan 12Adaptive Retrieval for Reasoning-Intensive RetrievalLG AI Research · arXiv (Cornell University)Jan 8Don’t Judge Code by Its Cover: Exploring Biases in LLM Judges for Code EvaluationLG AI Research · Findings of the Association for Computational Linguistics: EACL3 citationsJan 1From Documents to Segments: A Contextual Reformulation for Topic AssignmentLG AI Research · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)Jan 1Adaptive Retrieval for ReasoningLG AI Research · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1