Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMsLG AI Research · arXiv (Cornell University)Oct 19DeGMatch: Target-Aware Reasoning Data Selection via Deconfounded Gradient MatchingLG AI Research · arXiv (Cornell University)Oct 18CompLit: Scientific Literature Search Benchmarks Must Cover Implicit, Cumulative, and Unmet NeedsLG AI Research · arXiv (Cornell University)Oct 10Continually Post-training Small Models via Synthetic Self-distillationLG AI Research · arXiv (Cornell University)Oct 9Learning Rate Transfer for Hybrid Transformer-SSM ArchitecturesLG AI Research · arXiv (Cornell University)Oct 1HARISSA: Inference-Time Self-Checks for Efficient and Safe Local Language Model DeploymentLG AI Research · arXiv (Cornell University)Sep 29MolDesignBench: Evaluating LLM-based Agent for Scenario-grounded Molecular DesignLG AI Research · arXiv (Cornell University)Sep 23MINT: Molecularly Informed Training with Spatial Transcriptomics Supervision for Pathology Foundation ModelsLG AI Research · Lecture notes in computer scienceSep 21CompCQR: Compositional Query Generation for Training-Free Conversational SearchLG AI Research · arXiv (Cornell University)Sep 13CDTS2: Causal Downstreamer with Causally Disentangled Trend and Seasonality Time-Series RepresentationsLG AI Research · Applied SciencesSep 10EXAONE Tabular 1.0 : Technical ReportLG AI Research · arXiv (Cornell University)Aug 26Scaling Creative Writing Beyond Story-Centric Data with Attribute-Guided Genre ExpansionLG AI Research · arXiv (Cornell University)Aug 14Efficient Piecewise-Linear Embeddings for Deep Tabular Regression by Guided Breakpoint AllocationLG AI Research · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 6MultiTab: A Comprehensive Benchmark Suite for Multi-Dimensional Evaluation in Tabular DomainsLG AI Research · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)Aug 6ReasonCast: Towards Explainable Time Series Forecasting with ReasoningLG AI Research · arXiv (Cornell University)Aug 3Beyond Magnitude and Shape: A Direction-Aware Loss for Time Series ForecastingLG AI Research · arXiv (Cornell University)Aug 3ARHN: Answer-Centric Relabeling of Hard Negatives with Open-Source LLMs for Dense RetrievalLG AI Research · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR)Jul 10When Summaries Distort Decisions: Information Fidelity in LLM-Compressed Financial AnalysisLG AI Research · arXiv (Cornell University)Jun 28A Regret Minimization Framework on Preference Learning in Large Language ModelsLG AI Research · arXiv (Cornell University)Jun 8LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMsLG AI Research · arXiv (Cornell University)May 28From Documents to Segments: A Contextual Reformulation for Topic AssignmentLG AI Research · arXiv (Cornell University)May 18From Documents to Segments: A Contextual Reformulation for Topic AssignmentLG AI Research · arXiv (Cornell University)May 18AdaTKG: Adaptive Memory for Temporal Knowledge Graph ReasoningLG AI Research · arXiv (Cornell University)May 8Channel-Wise Retrieval for Multivariate Time Series ForecastingLG AI Research · IEEE International Conference on Acoustics Speech and Signal ProcessingApr 21Understanding dropout risks in online courses: SHAP-based analysis of lecture interval patterns in LMSLG AI Research · Education and Information TechnologiesApr 18