GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
Lora: Low-rank adaptation of large language models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2025 3representative citing papers
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
Fine-tuned LLMs with DAR sampling and DPO outperform off-the-shelf versions on algorithm design tasks and generalize to related settings.
citing papers explorer
-
Graph-Based Alternatives to LLMs for Human Simulation
GEMS formulates close-ended human-behavior simulation as link prediction on a heterogeneous graph and matches or exceeds LLM performance with three orders of magnitude fewer parameters across three datasets and three evaluation settings.
-
MoveFM-R: Advancing Mobility Foundation Models via Language-driven Semantic Reasoning
MoveFM-R is a framework that bridges mobility foundation models and LLMs using semantically enhanced location encoding, progressive curriculum alignment, and interactive self-reflection to generate plausible trajectories from language inputs.
-
Fine-tuning Large Language Model for Automated Algorithm Design
Fine-tuned LLMs with DAR sampling and DPO outperform off-the-shelf versions on algorithm design tasks and generalize to related settings.