paper-with-me

Papers

Futureproof Static Memory Planning

2025-04-07 · Christos Lamprakos, Panagiotis Xanthopoulos, Manolis Katsaragakis, Sotirios Xydis, Dimitrios Soudris, Francky Catthoor

The NP-complete combinatorial optimization task of assigning offsets to a set of buffers with known sizes and lifetimes so as to minimize total memory usage is called dynamic storage allocation (DSA). Existing DSA implementations bypass the theoretical state-of-the-art algorithms in favor of either fast but wasteful heuristics, or memory-efficient approaches that do not scale beyond one thousand buffers. The "AI memory wall", combined with deep neural networks' static architecture, has reignited interest in DSA. We present idealloc, a low-fragmentation, high-performance DSA implementation designed for million-buffer instances. Evaluated on a novel suite of particularly hard benchmarks from several domains, idealloc ranks first against four production implementations in terms of a joint effectiveness/robustness criterion.

📄 PDF Abstract BibTeX arXiv:2504.04874

Code (1)

cappadokes/idealloc 공식 구현

Tasks

Combinatorial Optimization

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning

2026-02-27 · Zebin Yang, Tong Xie, Baotong Lu, Shaoshan Liu 외 arxiv

Memory-augmented Large Language Models (LLMs) have demonstrated remarkable capability for complex and long-horizon embodied planning. By keeping track of past experiences and environmental states, memory enables LLMs to …

Towards a Privacy-preserving Deep Learning-based Network Intrusion Detection in Data Distribution Services

2021-06-12 · Stanislav Abaimov

Data Distribution Service (DDS) is an innovative approach towards communication in ICS/IoT infrastructure and robotics. Being based on the cross-platform and cross-language API to be applicable in any computerised device…

Deep LearningIntrusion DetectionNetwork Intrusion DetectionPrivacy Preserving+1

Dynamic Tree Databases in Automated Planning

2025-11-16 · Oliver Joergensen, Dominik Drexler, Jendrik Seipp arxiv

A central challenge in scaling up explicit state-space search for large tasks is compactly representing the set of generated states. Tree databases, a data structure from model checking, require constant space per genera…

SoD$^2$: Statically Optimizing Dynamic Deep Neural Network

2024-02-29 · Wei Niu, Gagan Agrawal, Bin Ren

Though many compilation and runtime systems have been developed for DNNs in recent years, the focus has largely been on static DNNs. Dynamic DNNs, where tensor shapes and sizes and even the set of operators used are depe…

Code Generation

LiloDriver: A Lifelong Learning Framework for Closed-loop Motion Planning in Long-tail Autonomous Driving Scenarios

2025-05-22 · Huaiyuan Yao, Pengfei Li, Bu Jin, Yupeng Zheng 외

Recent advances in autonomous driving research towards motion planners that are robust, safe, and adaptive. However, existing rule-based and data-driven planners lack adaptability to long-tail scenarios, while knowledge-…

Autonomous DrivingLifelong learningMotion Planning