Author

Junming Liu

h-index 6 View on Semantic Scholar

We have 2 of 22 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.

#artificial intelligence Preprint Sep 2026

ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation

ForkLeft, a distillation framework that resolves a fundamental mismatch between autoregressive teacher predicts from a left prefix and NTP teacher under the same context, is introduced, showing that DLMs can learn NTP-style reasoning without sacrificing native parallel generation.

Jun-Ming Liu, Ji-Cheng Wang, Yifeng He et al. · 0 citations

Jul 2026

TransMem: Transforming Hidden States into Memory for Large Language Models

TransMem is proposed, a lightweight inference-time parametric memory module that transforms sparse historical hidden states from a frozen LLM backbone into reusable memory representations and introduces evidence-conditioned self-distillation to learn transferable memory utilization rather than task-specific knowledge.

Haodong Lei, Junming Liu, Yirong Chen et al. · arXiv.org · 0 citations