4 papers
Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss
Thomas T. Zhang, Alok Shah, Yifei Zhang +3
Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., regression, cross-entropy), but deploy the network by rollin…
ConSurv: Multimodal Continual Learning for Survival Analysis
Dianzhi Yu, Conghao Xiong, Yankai Chen +6
Survival prediction of cancers is crucial for clinical practice, as it informs mortality risks and influences treatment plans. However, a static model trained on a single dataset f…
From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation
Zhihan Guo, Jiele Wu, Wenqian Cui +4
Current research on long-form context in Large Language Models (LLMs) primarily focuses on the understanding of long-contexts, the Open-ended Long Text Generation (Open-LTG) remain…
NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction
Qichao Wang, Ziqiao Meng, Wenqian Cui +6
Inspired by the impressive capabilities of GPT-4o, there is growing interest in enabling speech language models (SLMs) to engage in natural, fluid spoken interactions with humans.…