3 papers
cs.DS2026
A Short Note on Algorithms For The Noisy -XOR Problem
Kiril Bangachev
This mostly expository note studies the sample-noise regimes in which the testing problem for noisy -XOR in dimension can be efficiently solved. Concretely, we ask what pair…
cs.LG2026
Discrete Diffusion Models: A Unified Framework from Tokenization to Generation
Ye Yuan, Weien Li, Rui Song +20
Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offering parallel generation and ite…
cs.LG2026
MINER: Mining Multimodal Internal Representation for Efficient Retrieval
Weien Li, Rui Song, Zeyu Li +8
Visual document retrieval has become essential for accessing information in visually rich documents. Existing approaches fall into two camps. Late-interaction retrievers achieve st…