Country
4a1590df1d5968d41b855005bb8b67bf-Paper.pdf
For regression, we obtain a running time of O(nd+(nL/µ) p snL/µ) where µ > 0 is the smallest eigenvalue ofA>A. This running time improves upon the previous best unaccelerated running time of O(nd + nLd/µ). This result expands the regimes where regression can be solved in nearly linear time from whenL/µ= O(1)towhenL/µ= O(d2/3/(sn)1/3).
Chasing Ghosts: Instruction Following as Bayesian State Tracking
Peter Anderson, Ayush Shrivastava, Devi Parikh, Dhruv Batra, Stefan Lee
Neural Information Processing Systems http://nips.cc/
Hierarchical Reinforcement Learning with Advantage-Based Auxiliary Rewards
Siyuan Li, Rui Wang, Minxue Tang, Chongjie Zhang
N experiences h and l forT low-le low-lerlt defined thehigh-lei-thiteration. themodifiedi-thiteration.
Moonshine: Distilling with Cheap Convolutions
Elliot J. Crowley, Gavin Gray, Amos J. Storkey
Using attention transfer, we provide Pareto curves/tables for distillation of residual networks with four benchmark datasets, indicating the memory versus accuracy payoff.
Weakly Supervised Dense Event Captioning in Videos
Xuguang Duan, Wenbing Huang, Chuang Gan, Jingdong Wang, Wenwu Zhu, Junzhou Huang
Among the wide variety of applications on video understanding, the video captioning task is attracting more and more interests in recent years [4, 5, 6, 7, 8, 9, 10, 11].
A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design Fang Wu
Therapeutic antibodies are an essential and rapidly expanding drug modality.