adapter
PulseAugur coverage of adapter — every cluster mentioning adapter across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
New architecture boosts temporal relation extraction in low-rank models
Researchers have developed a new architecture called Convolutional Bottleneck Interaction (CBI) to improve temporal relation extraction in parameter-efficient fine-tuning scenarios. This method addresses the information…
-
New Framework Generates Natural-Language Explanations for LLM Features
Researchers have developed SAEVerbalizer, a new framework designed to generate natural-language explanations for features extracted by Sparse Autoencoders (SAEs) from large language models (LLMs). Current methods for ex…
-
AdapterMoE architecture improves crop disease recognition efficiency
Researchers have developed AdapterMoE, a novel two-stage hard-routing Mixture-of-Experts architecture designed for multi-crop disease recognition. This system aims to improve efficiency and flexibility by using a Router…
-
PEFT methods boost instance segmentation with minimal parameter tuning
Researchers have investigated parameter-efficient fine-tuning (PEFT) methods, specifically adapters and LoRA, for transformer-based models in instance segmentation tasks. The study found that these techniques can achiev…
-
IO-AI TECH supports ICRA 2026 robotics competition with data and research
IO-AI TECH is participating in ICRA 2026, supporting the second WBCD competition with data and hardware solutions. They are providing their SenseXperience UMI dataset on Hugging Face for the logistics sorting task, emph…