NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
Loss functions in deep learning: A comprehensive review.CoRR, abs/2504.04242
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
Fine-tuned LLMs on FDM formulation data recommend excipients and predict properties, with Llama2 performing best but exhibiting catastrophic forgetting and limited processability evaluation.
citing papers explorer
-
Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
NExt accelerates RLVR training for LLMs by nonlinearly extrapolating low-rank parameter trajectories extracted from LoRA runs.
-
Fed-Listing: Federated Label Distribution Inference in Graph Neural Networks
Fed-Listing infers client label proportions in FedGNNs from final-layer gradients, outperforming baselines on four datasets and three architectures even in non-i.i.d. settings.
-
FormuLLA: A Large Language Model Approach to Generating Novel 3D Printable Formulations
Fine-tuned LLMs on FDM formulation data recommend excipients and predict properties, with Llama2 performing best but exhibiting catastrophic forgetting and limited processability evaluation.