5 accepted papers
The probabilistic diffusion model (DM), generating content by inferencing through a recursive chain structure, has emerged as a powerful framework for visual generation. After pre-training on enormous data, the model needs to be properly aligned to meet requirements for downstream applications. How…
Reinforcement learning with verifiable reward has recently emerged as a central paradigm for post-training large language models (LLMs); however, prevailing mean-based methods, such as Group Relative Policy Optimization (GRPO), suffer from entropy collapse and limited reasoning gains. We argue that…
In this work, we consider the problem of Bayesian Optimization (BO) under reward model uncertainty—that is, when the underlying distribution type of the reward is unknown and potentially intractable to specify. This challenge is particularly evident in many modern applications, where the reward dis…
Given the limitations of backpropagation, perturbation-based gradient computation methods have recently gained focus for learning with only forward passes, also referred to as queries. Conventional forward learning consumes enormous queries on each data point for accurate gradient estimation through…
Phased array radar (PAR) is shown to provide an enhanced performance for target tracking due to its beam agility and ability for time resource allocation. Existing algorithms for PAR resource allocation often consider standard and simplified dynamic models for target motion, which are not suitable f…