Skip to content

Author

Yunjie Tian

We have 6 of 9 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

Back2Struct: Making Structured Images Editable Again

Structured images, such as diagrams, charts, and flowcharts, are inherently symbolic and can be compactly represented in an editable format, yet in practice, they are often rendered as images, and therefore not graphically editable. This mismatch presents a significant challenge for researchers, engineers, and designer...

Peng-Yu Yan, Yi-Xin Wu, Yun-Jie Tian et al. · 0 citations
#natural language process... Preprint Oct 2026

Scaling and Distilling Text Embeddings for Better Diffusibility

Diffusion language models (DLMs) offer a promising alternative to autoregressive (AR) language generation. Recent advances in continuous DLMs, which apply latent diffusion to continuous text embeddings, raise a practical question: which embedding makes the best latent space, i.e., the most diffusible? To answer this, w...

Ze-Kai Zhang, Yun-Jie Tian, Yan-Jin He et al. · 0 citations
Jul 2026

Visual Contrastive Self-Distillation

This work proposes Visual Contrastive Self-Distillation, namely VCSD, which converts image-content removal into an on-policy self-distillation signal, and consistently outperforms matched OPSD across Qwen3-VL and Qwen3.5 models.

Yijun Liang, Yunjie Tian, Yijiang Li et al. · 5 citations
Preprint Aug 2026

Self-Supervised Visual On-Policy Distillation

Self-Supervised Visual On-Policy Distillation (S$^2$VOPD), a simple yet effective method that constructs on-policy learning signals from asymmetric augmented views, systematically explores a broad design space of visual augmentations and uncover that asymmetry matters.

Yijiang Li, Yijun Liang, Yunjie Tian et al. · 0 citations
Preprint Aug 2026

On-Policy Self-Distillation without Any Supervision

U-OPSD first samples multiple rollouts and constructs a pseudo solution by majority vote under a self-consistency threshold, and conditions the model's distribution on the pseudo-solution and distills itself on the disagreeing completions, allowing the model to correct itself precisely where it is confidently wrong.

Yijiang Li, Bingyang Wang, Yijun Liang et al. · 10 citations · ⚡1
#artificial intelligence Preprint Aug 2026

Co-RL: Unsupervised Reasoning Emerges from Diverse Cohort in Multi-agent RL

This work introduces Co-RL, a framework in which multiple decoupled models, sharing no parameters, are simultaneously optimized through RL using rewards derived from their peers, and shows that unsupervised reasoning can emerge through cooperative multi-agent training.

Yunhao Yang, Yuexin Bian, Yun-Jie Tian et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.