94 citations · 144 across the 21 of their papers we have counts for
23 papers
How Should Diffusion Language Models Edit Code?
Xijia Tao, Ziru Liu, Shansan Gong +7
Code editing requires a model to decide where to make changes, generate the new content, and preserve everything else. We study how masked diffusion language models divide these re…
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…
Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language Models
Jing Xiong, Qi Han, Shansan Gong +6
Diffusion large language models (dLLMs) re-encode the entire prefix at every denoising step, causing recomputation that scales quadratically with context length and becomes prohibi…
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…
OVD: On-policy Verbal Distillation
Jing Xiong, Hui Shen, Shansan Gong +7
Knowledge distillation transfers reasoning capabilities from large teachers to efficient students. However, token-level on-policy distillation (OPD) constrains student exploration…
Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbone
Jiacheng Ye, Shansan Gong, Jiahui Gao +6
While autoregressive Large Vision-Language Models (VLMs) have achieved remarkable success, their sequential generation often limits their efficacy in complex visual planning and dy…
Continuously Augmented Discrete Diffusion model for Categorical Generative Modeling
Huangjie Zheng, Shansan Gong, Ruixiang Zhang +5
Standard discrete diffusion models treat all unobserved states identically by mapping them to an absorbing [MASK] token. This creates an 'information void' where semantic informati…
EconProver: Towards More Economical Test-Time Scaling for Automated Theorem Proving
Mukai Li, Linfeng Song, Zhenwen Liang +5
Large Language Models (LLMs) have recently advanced the field of Automated Theorem Proving (ATP), attaining substantial performance gains through widely adopted test-time scaling s…
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…
DiffuCoder: Understanding and Improving Masked Diffusion Models for Code Generation
Shansan Gong, Ruixiang Zhang, Huangjie Zheng +4
Diffusion large language models (dLLMs) are compelling alternatives to autoregressive (AR) models because their denoising models operate over the entire sequence. The global planni…
GIRAFFE: Design Choices for Extending the Context Length of Visual Language Models
Mukai Li, Lei Li, Shansan Gong +1
Visual Language Models (VLMs) demonstrate impressive capabilities in processing multimodal inputs, yet applications such as visual agents, which require handling multiple images an…
Why Does the Effective Context Length of LLMs Fall Short?
Chenxin An, Jun Zhang, Ming Zhong +5
Advancements in distributed training and efficient attention mechanisms have significantly expanded the context window sizes of large language models (LLMs). However, recent work r…
Scaling Diffusion Language Models via Adaptation from Autoregressive Models
Shansan Gong, Shivam Agarwal, Yizhe Zhang +9
Diffusion Language Models (DLMs) have emerged as a promising new paradigm for text generative modeling, potentially addressing limitations of autoregressive (AR) models. However, c…
Beyond Autoregression: Discrete Diffusion for Complex Reasoning and Planning
Jiacheng Ye, Jiahui Gao, Shansan Gong +4
Autoregressive language models, despite their impressive capabilities, struggle with complex reasoning and long-term planning tasks. We introduce discrete diffusion models as a nov…
BBA: Bi-Modal Behavioral Alignment for Reasoning with Large Vision-Language Models
Xueliang Zhao, Xinting Huang, Tingchen Fu +5
Multimodal reasoning stands as a pivotal capability for large vision-language models (LVLMs). The integration with Domain-Specific Languages (DSL), offering precise visual represen…
Training-Free Long-Context Scaling of Large Language Models
Chenxin An, Fei Huang, Jun Zhang +4
The ability of Large Language Models (LLMs) to process and generate coherent text is markedly weakened when the number of input tokens exceeds their pretraining length. Given the e…
Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models
Jiacheng Ye, Shansan Gong, Liheng Chen +8
Recently, diffusion models have garnered significant interest in the field of text processing due to their many potential advantages compared to conventional autoregressive models.…
DiffuSeq-v2: Bridging Discrete and Continuous Text Spaces for Accelerated Seq2Seq Diffusion Models
Shansan Gong, Mukai Li, Jiangtao Feng +2
Diffusion models have gained prominence in generating high-quality sequences of text. Nevertheless, current approaches predominantly represent discrete text within a continuous dif…
L-Eval: Instituting Standardized Evaluation for Long Context Language Models
Chenxin An, Shansan Gong, Ming Zhong +5
Recently, there has been growing interest in extending the context length of large language models (LLMs), aiming to effectively process long inputs of one turn or conversations wi…
In-Context Learning with Many Demonstration Examples
Mukai Li, Shansan Gong, Jiangtao Feng +4
Large pre-training language models (PLMs) have shown promising in-context learning abilities. However, due to the backbone transformer architecture, existing PLMs are bottlenecked…
DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
Shansan Gong, Mukai Li, Jiangtao Feng +2
Recently, diffusion models have emerged as a new paradigm for generative models. Despite the success in domains using continuous signals such as vision and audio, adapting diffusio…
Few-Shot Natural Language Inference Generation with PDD: Prompt and Dynamic Demonstration
Kaijian Li, Shansan Gong, Kenny Q. Zhu
Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two. This task can be used in data augmentation…
Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
Shansan Gong, Kenny Q. Zhu
News recommendation for anonymous readers is a useful but challenging task for many news portals, where interactions between readers and articles are limited within a temporary log…