Dilated Convolution with Learnable Spacings makes visual models more aligned with humans: a Grad-CAM studyby…
KnowPO: Knowledge-aware Preference Optimization for Controllable Knowledge Selection in Retrieval-Augmented Language Modelsby Ruizhe Zhang, Yongxin…
Personalizing Federated Instrument Segmentation with Visual Trait Priors in Robotic Surgeryby Jialang Xu, Jiacheng Wang,…
Unveiling Factual Recall Behaviors of Large Language Models through Knowledge Neuronsby Yifei Wang, Yuheng Chen,…
Training LLMs to Recognize Hedges in Spontaneous Narrativesby Amie J. Paige, Adil Soubki, John Murzaku,…
Reconstruction of the shape of irregular rough particles from their interferometric images using a convolutional…
LLaVA-OneVision: Easy Visual Task Transferby Bo Li, Yuanhan Zhang, Dong Guo, Renrui Zhang, Feng Li,…
Automated Theorem Provers Help Improve Large Language Model Reasoningby Lachlan McGinness, Peter BaumgartnerFirst submitted to…
Optimus: Accelerating Large-Scale Multi-Modal LLM Training by Bubble Exploitationby Weiqi Feng, Yangrui Chen, Shaoyu Wang,…
EXAONE 3.0 7.8B Instruction Tuned Language Modelby LG AI Research, Soyoung An, Kyunghoon Bae, Eunbi…