4 papers
Noise Your Prompt: Noising Conditioning Tokens in Continuous Diffusion Language Models
Justin Jung
We revisit a standard accepted practice in the continuous diffusion language model literature of fixing conditioning prompt tokens clean during training. We make a very simple modi…
Guided Discrete Diffusion for Constraint Satisfaction Problems
Justin Jung
We propose discrete diffusion guidance for constraint satisfaction problems (CSPs) and demonstrate its ability to solve Sudoku puzzles without supervision.
Scaffold Diffusion: Sparse Multi-Category Voxel Structure Generation with Discrete Diffusion
Justin Jung
Generating realistic sparse multi-category 3D voxel structures is difficult due to the cubic memory scaling of voxel structures and moreover the significant class imbalance caused…
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
David Yunis, Justin Jung, Falcon Dai +1
Exploration in sparse-reward reinforcement learning is difficult due to the requirement of long, coordinated sequences of actions in order to achieve any reward. Moreover, in conti…