Classical paging serves every miss immediately. We study paging with per-replacement maximum delay, where loading a pending page costs one movement plus the age of its oldest outstanding request and clears that page's entire episode. Equivalently, the holding rate is the number of pending pages. For cache size $k$, thr...
This work proves strong NP-hardness and rule out absolute approximation factors below three halves unless P equals NP, and obtains an exact stochastic benchmark for Poisson arrivals when every item has half the bin capacity.
Online covering in which each instantaneous service pays its purchase cost and one maximum waiting time, with no effect on future requests is studied, finding an offline consecutive-batch normal form that transfers static approximation guarantees to the offline problem.
On-policy distillation (OPD) trains multi-turn language agents with dense teacher supervision on student-generated responses. However, standard think-then-act rollouts require lengthy reasoning before each short action, delaying environment transitions and experience collection. Generating actions directly reduces this...
Zu-Bin Zheng, Jiahao Wu, Shao-Feng Zhang et al.· 1 citation
PaW is a Policy and World modeling co-training framework that adds auxiliary WM supervision to the same policy during RL, without changing the inference paradigm, and shows consistent improvements over strong RL baselines across models and RL algorithms.
Ning Lu, Baijiong Lin, Sheng-Cai Liu et al.· arXiv.org· 12 citations· ⚡2
The deterministic guarantee matches the known fixed-node lower bound, and the matching randomized lower bound are proved, ensuring that both guarantees are optimal on every nondegenerate rooted tree.
Tian-Han Lu, Run-Tian Ren, Sheng-Cai Liu et al.· 3 citations
This work proposes HIVE (History-Informed and online-VErified prompt selection), a dual-stage framework for data-efficient RL that utilizes historical reward trajectories for coarse selection and employs prompt entropy as a real-time proxy to prune instances with stale utility.
Jiahao Wu, Ning Lu, Sheng-Cai Liu et al.· 12 citations
This work uses spatial blindness---announced requests whose locations are revealed only when visited---as a stress test: dyadic exploration preserves a constant ratio on a known finite line, while a single hidden request on a star forces a loss linear in its degree.
Tian-Han Lu, Run-Tian Ren, Sheng-Cai Liu et al.· 0 citations
A cross-fidelity knowledge distillation and adaptive fusion network (CFKD-AFN), which leverages abundant but low-fidelity simulation data to enhance the prediction on scarce but high-fidelity trial data, and is extended to an interpretable variant for exploratory analysis of feature-attribution patterns associated with...
Wen-Jing Chen, Lian-Sheng Zhuang, Zi-Ying Luo et al.· arXiv.org· 0 citations
CoPES is introduced, a cooperative coevolutionary method that decomposes the full parameter space into lower-dimensional subspaces and searches over them cooperatively to improve optimization efficiency and demonstrate an improved trade-off between memory requirements and training time for agentic LLM post-training und...
Zhiyuan Wang, Sheng-Cai Liu, Jiahao Wu et al.· 2 citations
EMO combines graph analysis and pack-level models to formulate energy optimization as a constrained combinatorial problem, efficiently solving for optimal frequency policies under given latency targets.
Jiyu Luo, Shaoyu Chen, Jingwei Sun 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.
