activity
20242026
collaborators

12 papers

cs.CL2026

DreamReasoner-8B: Block-Size Curriculum Learning for Diffusion Reasoning Models

Zirui Wu, Lin Zheng, Jiacheng Ye +5

Block diffusion language models accelerate decoding through parallel block-wise denoising, yet whether they can be reliably scaled for long chain-of-thought (CoT) reasoning remains…

cs.CL2026

Proxy Compression for Language Modeling

Lin Zheng, Xinyu Li, Qian Liu +2

Modern language models are trained almost exclusively on token sequences produced by a fixed tokenizer, an external lossless compressor often over UTF-8 byte sequences, thereby cou…

cs.CL2026

Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models

Lin Zheng, Vasilisa Bashlovkina, Timothy Dozat +3

Tokenizer-free language models eliminate the tokenizer step of the language modeling pipeline by operating directly on bytes; patch-based variants further aggregate contiguous byte…

cs.CL2026

DreamOn: Diffusion Language Models For Code Infilling Beyond Fixed-size Canvas

Zirui Wu, Lin Zheng, Zhihui Xie +8

Diffusion Language Models (DLMs) present a compelling alternative to autoregressive models, offering flexible, any-order infilling without specialized prompting design. However, th…

cs.CL2025

Dream-Coder 7B: An Open Diffusion Language Model for Code

Zhihui Xie, Jiacheng Ye, Lin Zheng +8

We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoreg…

cs.CL2025

Dream 7B: Diffusion Large Language Models

Jiacheng Ye, Zhihui Xie, Lin Zheng +5

We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete…