Skip to content

Author

Lin-Feng Zhang

We have 5 of 16 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 Nov 2026

Beyond Passive Imitation: On-Policy Mid-Training Distillation for Language Models

Continual pre-training (CPT) adapts large language models (LLMs) to specialized domains, yet its standard next-token prediction (NTP) objective treats every corpus token as a fixed target, regardless of its utility to the current model. In a controlled study on the same 1B-token mathematical corpus, we observe sharply...

Rui-Ze Zheng, Xu-Yang Liu, Siyu Ren et al. · 0 citations
Preprint Aug 2026

AViTS: Adaptive Spatiotemporal Token Selection for Efficient Dynamic-Resolution Generation

AViTS models spatial importance via latent-text attention and temporal importance via token-level feature variation across diffusion timesteps, and fuses them to enable spatiotemporal importance-aware selective upsampling: it prioritizes resolution refinement for critical tokens while deferring less important ones, the...

Hao-Ran Qin, Zhen Yan, Shikang Zheng et al. · 0 citations
#machine learning Preprint Sep 2026

Accelerating Diffusion Transformers with Gaussian Process Rectified Feature Cache

A statistical observation that the residuals between the features of full computation steps using caching methods and reference full-compute trajectory locally exhibit a zero-mean Gaussian distribution is presented, and a plug-and-play GP-Refiner correction framework is proposed.

Zhi-Rong Shen, Rui-Xin Huang, Chang Zou et al. · 0 citations
#artificial intelligence Preprint Sep 2026

MemForest: Efficient Agent Memory Management via EventTree Partitioning and Progressive Merging

This work proposes a general memory compression framework adaptable to various agent memory systems, MemForest, and introduces an anchor-guided propagation retrieval mechanism that retrieves relevant memory nodes from the temporal neighborhoods of key nodes, improving retrieval accuracy.

Junxi Wang, Te Sun, Jiayi Zhu et al. · 0 citations
Preprint Aug 2026

LinCa: Accelerating Diffusion Models via Learnable Decomposed Feature Caching

LinCa decomposes cached features into sub-components with distinct continuity properties via a lightweight invertible network and applies differentiated prediction orders matched to each component, forming a unified Decompose-Predict-Reconstruct pipeline.

Jin-Shan Liu, Hao-Ran Qin, Xiao-Bing Tu 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.