Dynamic Backtracking in GFlowNets: Enhancing Decision Steps with Reward-Dependent Adjustment Mechanismsby Shuai Guo, Jielei Chu,…
Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Modelsby Bowen Pan, Yikang Shen, Haokun…
DRoP: Distributionally Robust Data Pruningby Artem Vysogorets, Kartik Ahuja, Julia KempeFirst submitted to arxiv on:…
Test-Time Training for Depression Detectionby Sri Harsha Dumpala, Chandramouli Shama Sastry, Rudolf Uher, Sageev OoreFirst…
A Structure-Guided Gauss-Newton Method for Shallow ReLU Neural Networkby Zhiqiang Cai, Tong Ding, Min Liu,…
DREAM: Improving Video-Text Retrieval Through Relevance-Based Augmentation Using Large Foundation Modelsby Yimu Wang, Shuai Yuan,…
A Note on LoRAby Vlad Fomenko, Han Yu, Jongho Lee, Stanley Hsieh, Weizhu ChenFirst submitted…
SEER-MoE: Sparse Expert Efficiency through Regularization for Mixture-of-Expertsby Alexandre Muzio, Alex Sun, Churan HeFirst submitted…
Active Test-Time Adaptation: Theoretical Analyses and An Algorithmby Shurui Gui, Xiner Li, Shuiwang JiFirst submitted…
Importance of realism in procedurally-generated synthetic images for deep learning: case studies in maize and…