Domain-adaptative Continual Learning for Low-resource Tasks: Evaluation on Nepaliby Sharad Duwal, Suraj Prasai, Suresh ManandharFirst…
SWAN: SGD with Normalization and Whitening Enables Stateless LLM Trainingby Chao Ma, Wenbo Gong, Meyer…
Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification frameworkby Aman Tiwari, Shiva Krishna Reddy…
RAG Playground: A Framework for Systematic Evaluation of Retrieval Strategies and Prompt Engineering in RAG…
Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformersby Seungwook Han,…
The Open Source Advantage in Large Language Models (LLMs)by Jiya Manchanda, Laura Boettcher, Matheus Westphalen,…
SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separatorby Guoxuan Chen, Han…
EvoLlama: Enhancing LLMs’ Understanding of Proteins via Multimodal Structure and Sequence Representationsby Nuowei Liu, Changzhi…
Sequence-Level Leakage Risk of Training Data in Large Language Modelsby Trishita Tiwari, G. Edward SuhFirst…
Efficient Continual Pre-training of LLMs for Low-resource Languagesby Arijit Nag, Soumen Chakrabarti, Animesh Mukherjee, Niloy…