Výsledky vyhledávání

Report

Detecting and Preventing Hallucinations in Large Vision Language Models

Autor: Gunjal, Anisha, Yin, Jihan, Bas, Erhan

Instruction tuned Large Vision Language Models (LVLMs) have significantly advanced in generalizing across a diverse set of multi-modal tasks, especially for Visual Question Answering (VQA). However, generating detailed responses that are visually gro

Externí odkaz: http://arxiv.org/abs/2308.06394

Zobrazit plný text záznamu

Report

Empirical Analysis of the Strengths and Weaknesses of PEFT Techniques for LLMs

Autor: Pu, George, Jain, Anirudh, Yin, Jihan, Kaplan, Russell

As foundation models continue to exponentially scale in size, efficient methods of adaptation become increasingly critical. Parameter-efficient fine-tuning (PEFT), a recent class of techniques that require only modifying a small percentage of the mod

Externí odkaz: http://arxiv.org/abs/2304.14999

Zobrazit plný text záznamu

Report

NBDT: Neural-Backed Decision Trees

Autor: Wan, Alvin, Dunlap, Lisa, Ho, Daniel, Yin, Jihan, Lee, Scott, Jin, Henry, Petryk, Suzanne, Bargal, Sarah Adel, Gonzalez, Joseph E.

Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models that (1) sacri

Externí odkaz: http://arxiv.org/abs/2004.00221

Zobrazit plný text záznamu