Summary of Unified Lexical Representation For Interpretable Visual-language Alignment, by Yifan Li et al.
Unified Lexical Representation for Interpretable Visual-Language Alignmentby Yifan Li, Yikai Wang, Yanwei Fu, Dongyu Ru,…
Summary of Accurate and Efficient Fine-tuning Of Quantized Large Language Models Through Optimal Balance, by Ao Shen et al.
Accurate and Efficient Fine-Tuning of Quantized Large Language Models Through Optimal Balanceby Ao Shen, Qiang…
Summary of Lawma: the Power Of Specialization For Legal Tasks, by Ricardo Dominguez-olmedo et al.
Lawma: The Power of Specialization for Legal Tasksby Ricardo Dominguez-Olmedo, Vedant Nanda, Rediet Abebe, Stefan…
Summary of A Deeper Look at Depth Pruning Of Llms, by Shoaib Ahmed Siddiqui et al.
A deeper look at depth pruning of LLMsby Shoaib Ahmed Siddiqui, Xin Dong, Greg Heinrich,…
Summary of Attention Is All You Need but You Don’t Need All Of It For Inference Of Large Language Models, by Georgy Tyukin et al.
Attention Is All You Need But You Don’t Need All Of It For Inference of…
Summary of Chatqa 2: Bridging the Gap to Proprietary Llms in Long Context and Rag Capabilities, by Peng Xu et al.
ChatQA 2: Bridging the Gap to Proprietary LLMs in Long Context and RAG Capabilitiesby Peng…
Summary of Lazyllm: Dynamic Token Pruning For Efficient Long Context Llm Inference, by Qichen Fu et al.
LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inferenceby Qichen Fu, Minsik Cho, Thomas…
Summary of Metallm: a High-performant and Cost-efficient Dynamic Framework For Wrapping Llms, by Quang H. Nguyen et al.
MetaLLM: A High-performant and Cost-efficient Dynamic Framework for Wrapping LLMsby Quang H. Nguyen, Duy C.…
Summary of Fine-tuning and Prompt Optimization: Two Great Steps That Work Better Together, by Dilara Soylu et al.
Fine-Tuning and Prompt Optimization: Two Great Steps that Work Better Togetherby Dilara Soylu, Christopher Potts,…
Summary of Flash Normalization: Fast Rmsnorm For Llms, by Nils Graef et al.
Flash normalization: fast RMSNorm for LLMsby Nils Graef, Matthew Clapp, Andrew WasielewskiFirst submitted to arxiv…