Capsule Endoscopy Multi-classification via Gated Attention and Wavelet Transformationsby Lakshmi Srinivas Panchananam, Praveen Kumar Chandaliya,…
BitPipe: Bidirectional Interleaved Pipeline Parallelism for Accelerating Large Models Trainingby Houming Wu, Ling Chen, Wenjie…
Notes on the Mathematical Structure of GPT LLM Architecturesby Spencer Becker-KahnFirst submitted to arxiv on:…
Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistantby Abhirama Subramanyam…
Initialization Matters: On the Benign Overfitting of Two-Layer ReLU CNN with Fully Trainable Layersby Shuning…
Structured Diffusion Models with Mixture of Gaussians as Prior Distributionby Nanshan Jia, Tingyu Zhu, Haoyu…
Learning Coupled Subspaces for Multi-Condition Spike Databy Yididiya Y. Nadew, Xuhui Fan, Christopher J. QuinnFirst…
Adversarial Attacks on Large Language Models Using Regularized Relaxationby Samuel Jacob Chacko, Sajib Biswas, Chashi…
Indication Finding: a novel use case for representation learningby Maren Eckhoff, Valmir Selimi, Alexander Aranovitch,…
Perturbation-based Graph Active Learning for Weakly-Supervised Belief Representation Learningby Dachun Sun, Ruijie Wang, Jinning Li,…