Abstract: Discrete rapid-exploring random tree (dRRT) methods have been proposed but remain to be improved, showing great potential for efficiently solving multiagent path finding (MAPF) problems.

Abstract: Sampling random values from a discrete Gaussian distribution with high precision is a major and computationally-intensive operation of emerging and existing cryptographic standards. FALCON ...

Quantized expectation — provides gradient-like guidance for discrete diffusion with a purely discrete embedding space. Anchored remasking — enables adaptive decoding by preserving “anchor tokens” ...

Counterfactual explanations are the backbone of our methodology, and they help us formulate how we approach the generation of counterfactuals alongside the ability to compare similar lines of prior ...

In standard autoregressive generation, an LLM predicts the next-token distribution, samples a discrete token, and then discards the distribution, passing only the sampled token as new input. To ...