5 papers
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
Nan Chen, Zhouhao Yang, Soufiane Hayou
Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefined classes. For instance, given a user prompt, the system must determine wheth…
Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
Nan Chen, Soledad Villar, Soufiane Hayou
Low-Rank Adaptation (LoRA) is a standard tool for parameter-efficient finetuning of large models. While it induces a small memory footprint, its training dynamics can be surprising…
pscaling small models: Principled warm starts and hyperparameter transfer
Yuxin Ma, Nan Chen, Mateo Díaz +3
Modern large-scale neural networks are often trained and released in multiple sizes to accommodate diverse inference budgets. To improve efficiency, recent work has explored model…
SynerGen: Contextualized Generative Recommender for Unified Search and Recommendation
Vianne R. Gao, Chen Xue, Marc Versage +11
The dominant retrieve-then-rank pipeline in large-scale recommender systems suffers from mis-calibration and engineering overhead due to its architectural split and differing optim…
Exploring Pseudo-Token Approaches in Transformer Neural Processes
Jose Lara-Rangel, Nanze Chen, Fengzhe Zhang
Neural Processes (NPs) have gained attention in meta-learning for their ability to quantify uncertainty, together with their rapid prediction and adaptability. However, traditional…