Neural networks are powerful predictors, yet their opacity limits their usefulness in science, where the goal is explanation rather than mere prediction. In neuroscience, for example, deep encoding models accurately predict brain activity in response to natural stimuli, but struggle to reveal which stimulus features dr...
Yash Mehta, C. Singh, Wei-Jia Xu et al.· 1 citation
Masked diffusion language models (dLLMs) generate text by iteratively denoising masked tokens with bidirectional attention. Extending reasoning across generation chunks normally requires keeping earlier generated text in context. We ask whether a dLLM can instead continue reasoning after that text is cleared, using onl...
Albert Ge, C. Singh, Yu-Fan Zhuang et al.· 0 citations
This work proposes a reinforcement learning (RL) fine-tuning framework that treats EHR foundation models as generative policies over patient trajectories, and finds that RL fine-tuning consistently improves over pre-trained backbones and strong baselines.
Yu-Xin Xiao, Sheng Zhang, C. Singh et al.· arXiv.org· 0 citations
Experiments on diverse open-source text classification datasets show that AHR can outperform standard baselines like LoRA when learning from limited samples, despite having 200-1000x fewer trainable parameters, as the authors' AHR only modifies ~0.0001% of the model's parameters.
Tuomas P. Oikarinen, Zixiao Chen, Charlotte Siska et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.