Reducing False Discoveries in Statistically-Significant Regional-Colocation Mining: A Summary of Resultsby Subhankar Ghosh, Jayant Gupta,…
MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attentionby Huiqiang Jiang, Yucheng Li,…
Data-driven Power Flow Linearization: Theoryby Mengshuo Jia, Gabriela Hug, Ning Zhang, Zhaojian Wang, Yi Wang,…
Analytical Solution of a Three-layer Network with a Matrix Exponential Activation Functionby Kuo Gai, Shihua…
RLHF Can Speak Many Languages: Unlocking Multilingual Preference Optimization for LLMsby John Dang, Arash Ahmadian,…
Towards the Next Frontier in Speech Representation Learning Using Disentanglementby Varun Krishna, Sriram GanapathyFirst submitted…
Domain Generalizable Knowledge Tracing via Concept Aggregation and Relation-Based Attentionby Yuquan Xie, Wanqi Yang, Jinyu…
Meta 3D Genby Raphael Bensadoun, Tom Monnier, Yanir Kleiman, Filippos Kokkinos, Yawar Siddiqui, Mahendra Kariya,…
D-Rax: Domain-specific Radiologic assistant leveraging multi-modal data and eXpert model predictionsby Hareem Nisar, Syed Muhammad…
Linear Submodular Maximization with Bandit Feedbackby Wenjing Chen, Victoria G. CrawfordFirst submitted to arxiv on:…