papers

Publications (11)

cs.LG2026

State commitment learning: training language models to distinguish computation from memory

Fei Ding, Yongkang Zhang, Runhao Liu +3

Reasoning language models do not distinguish tokens used for computation from tokens that constitute persistent state: once generated, all hidden thoughts remain in context and inf…

cs.CE2025

Probabilistic Method for Optimizing Submarine Search and Rescue Strategy Under Environmental Uncertainty

Runhao Liu, Ziming Chen, Peng Zhang

When coping with the urgent challenge of locating and rescuing a deep-sea submersible in the event of communication or power failure, environmental uncertainty in the ocean can not…

cs.CL2026

Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs

Fei Ding, Yongkang Zhang, Runhao Liu +3

Post-training of large language models optimizes only parameters, while inference-time procedural scaffolds are typically designed independently of parameter training. This disconn…

cs.NI2026

LATTICE: Constraint-Directed Scheduling, Memory Planning, and Pipeline Refinement for NPUs

Runhao Liu, Minman Pei, Peng Zheng +7

General-purpose NPUs execute fine-grained command DAGs across heterogeneous compute and memory-transfer engines backed by finite, explicitly managed on-chip memories. This executio…

cs.CV2026

Exploring the Challenge and Value of Deep Learning in Automated Skin Disease Diagnosis

Runhao Liu, Ziming Chen, Guangzhen Yao +1

Skin cancer is one of the most prevalent and deadly forms of cancer worldwide, highlighting the critical importance of early detection and diagnosis in improving patient outcomes.…

cs.LG2026

Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning

Fei Ding, Yongkang Zhang, Runhao Liu +4

The central challenge of reinforcement learning for reasoning lies not only in the sparsity of outcome-level supervision, but more fundamentally in how to transform feedback provid…