Skip to content

Author

Ruixuan Deng

We have 5 of 8 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.

Review Sep 2026

Long-horizon autoformalization of a core theorem underlying MIP* = RE

This work completed a machine-checked Lean 4 proof of the quantum soundness of the classical low individual-degree test, a core theorem underlying MIP* = RE, and provides a verified foundation for quantum complexity.

Si-Rui Lu, Rui-Xuan Deng, David Zhu et al. · 1 citation
#artificial intelligence Preprint Sep 2026

Transformers Stop Thinking Too Early, and a Tiny LoRA Fixes It

Pretrained transformers use little of their depth to follow references in context. Thirteen base models reliably follow only 1.4-3.6 lines, and extra pretrained loops add little. A task-trained rank-8 LoRA at one early layer extends this computation with all model weights frozen. Qwen3-8B improves from 15.5% to 99% exa...

Ze-Hao Jin, Rui-Xuan Deng, Jun-Ran Wang · 0 citations
#artificial intelligence Review Sep 2026

Long-horizon autoformalization of a core theorem underlying MIP* = RE

Landmark mathematical formalizations have taken specialist teams years to complete. We present FormalFlow, a system that coordinates AI proving agents under human supervision to address statement drift and proof composition in long-horizon formalization. Drawing on software engineering principles and practices, it uses...

Si-Rui Lu, Ruixuan Deng, Yan-Qiao Zhu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

AcFlow: Controlling Text-to-Image Diffusion Transformers via Learned Conditional Activation Flow

AcFlow is introduced, an inference-time controller that transports intermediate layer image-token activations through a learned concept-conditioned velocity field while keeping the base DiT frozen, and supports the learned velocity field as an adaptive control mechanism.

Jun-Ran Wang, Ze-Hao Jin, Tian-Yu Luan et al. · 0 citations
Jul 2026

How Benchmarks Mis-Score Computer-Use Agents

A three-tier diagnostic taxonomy shows that verification/feedback and planning failures dominate execution/grounding errors, while a single scalar success rate can not explain, and connects these findings to newer long-horizon CUA benchmarks and derive stage-specific design rules for CUA evaluation.

Zi-Han Dong, Zhiyuan Ma, Zekun Wang et al. · 2 citations

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