5 papers
Unifying Masked Diffusion Models with Various Generation Orders and Beyond
Chunsan Hong, Sanghyun Lee, Jong Chul Ye
Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality depends critically on the generation orde…
Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval
Hangeol Chang, Changsun Lee, Seungjoon Rho +2
Retrieval-Augmented Generation (RAG) improves Large Language Models (LLMs) by grounding generation in external, non-parametric knowledge. However, when a task requires choosing amo…
FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction
Seonghyun Jin, Jong Chul Ye
Streaming 3D reconstruction maintains a persistent latent state that is updated online from incoming frames, enabling constant-memory inference. A key failure mode is the state upd…
Reviving ConvNeXt for Efficient Convolutional Diffusion Models
Taesung Kwon, Lorenzo Bianchi, Lennart Wittke +5
Recent diffusion models increasingly favor Transformer backbones, motivated by the remarkable scalability of fully attentional architectures. Yet the locality bias, parameter effic…
Improving Discrete Diffusion Unmasking Policies Beyond Explicit Reference Policies
Chunsan Hong, Seonho An, Min-Soo Kim +1
Masked diffusion models (MDMs) have recently emerged as a novel framework for language modeling. MDMs generate sentences by iteratively denoising masked sequences, filling in [MASK…