Technology
Convergence-Rate-Matching Discretization of Accelerated Optimization Flows Through Opportunistic State-Triggered Control
Neural Information Processing Systems http://nips.cc/
Multi Time Scale World Models
Inference in the introduced linear Gaussian SSM is straightforward and can be performed using Kalman prediction and observation updates.
Mapping State Space using Landmarks for Universal Goal Reaching
Zhiao Huang, Fangchen Liu, Hao Su
Neural Information Processing Systems http://nips.cc/
Black-BoxGeneralization: StabilityofZeroth-OrderLearning
Forboundednonconvex losses and a batch sizem = 1, we additionally show that both generalization error and learning rate are independent ofd and K, and remain essentially the same asfortheSGD, evenfortwofunction evaluations.
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
This work was accomplished when Liyi Chen was an intern at Alibaba Cloud Computing.