Notes

Oct 22, 2026Ideas

Survive-Driven Intelligence

We believe that existence is the sole reason intelligence came into being. What can endure will remain; what cannot will pass away.

Selected research

All research

CRP: a history-free base prediction plus a history-conditioned residual, using one network in two passes.

Core idea ↗

arXiv 2026Video generation · CRP

Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher

Bowen Zheng, Zhiguang Liu, Jiarong Ou, Rui Chen, Tianyang Hu

Reducing reliance on generated history through conditional residual prediction, enabling autoregressive video diffusion without a bidirectional teacher.

Read on arXiv

Prologue: separate prologue and visual tokens during training and autoregressive inference.

Core idea ↗

arXiv 2026Visual generation · Prologue

Autoregressive Visual Generation Needs a Prologue

Bowen Zheng, Weijian Luo, Guang Yang, Colin Zhang, Tianyang Hu

Learning a separate sequence of prologue tokens for autoregressive generation while keeping visual tokens dedicated to reconstruction.

Read on arXiv Code ↗

D2O: generative pre-training followed by GAN fine-tuning for one-step image generation.

Core idea ↗

ICML 2025One-step generation

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

Bowen Zheng, Tianming Yang

Viewing diffusion training as generative pre-training, with lightweight GAN fine-tuning to unlock one-step generation.

Read on arXiv

SimLens: intermediate-layer predictions and an entropy threshold for early exit.

Core idea ↗

EMNLP 2026Efficient inference

SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token

Ming Ma*, Bowen Zheng*, Zhongqiao Lin, Tianming Yang

* Co-first authors

Decoding intermediate-layer predictions with a short continuation to support efficient early-exit inference.

Read on arXiv

Label Words: demonstrations of knowledge and categorization tasks in in-context learning.

Core idea ↗

Findings of ACL 2026In-context learning

Label Words as Local Task Vectors in In-Context Learning

Bowen Zheng*, Ming Ma*, Zhongqiao Lin, Tianming Yang

* Co-first authors

Studying how individual demonstrations form local task vectors and how language models aggregate their information.

Read on arXiv

Notes

Survive-Driven Intelligence

Selected research

Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher ↗

Autoregressive Visual Generation Needs a Prologue ↗

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation ↗

SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token ↗

Label Words as Local Task Vectors in In-Context Learning ↗

Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional Teacher

Autoregressive Visual Generation Needs a Prologue

Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation

SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token

Label Words as Local Task Vectors in In-Context Learning