排序
标签

15M web servers on one VM – smoltcp, DPDK, AF_XDP

Response-Relevant Information Is Not Sufficient for Neural Training-State Equivalence
Response-relevant information is not sufficient evidence that two neural networks are in the same training state. We define training-state equivalence operationally: two checkpoints are equivalent, re...

Goemans's Unsplittable-Flow Conjecture: The Anatomy of AI-Assisted Counterexample Discovery
Goemans conjectured that any fractional single-source flow could be converted into an unsplittable flow without increasing total cost and while increasing any arc load by at most the largest demand. R...

Biologically-Inspired Spike Encoding and Optimization for Spiking Neural Networks
Spiking Neural Networks (SNNs) offer theoretical energy-efficiency advantages over conventional deep networks, but realizing these advantages on vision tasks requires sparse spike representations that...

GridForge: An Open Physics-Informed Digital Twin and Benchmark Suite for UK 11 kV Underground Distribution Cables
The UK distribution-cable monitoring sector is data-rich but framework-poor: each Distribution Network Operator (DNO) collects megabytes of telemetry per asset per day, but there is no public benchmar...

Neural Network-Based Modeling of Hysteretic Systems: From Prandtl and Preisach Neural Networks to Neuro-Madelung and Neuroplastic Continuous Models
Hysteresis is a complex nonlinear phenomenon characterized by memory dependence, path dependence, and, in many physical systems, degradation, non-congruency, asymmetry, and rate dependence. This revie...

CounselTraj: Synthesizing Process-Aware Psychological Counseling Dialogues via Dialogue-Act Trajectory Planning
The growing demand for psychological counseling has motivated the development of LLM-based systems that support human counselors, but training such systems requires large-scale, high-quality dialogue ...

Once Upon a Bias: Gender Stereotyping in LLM-Generated Children's Stories
Large language models are increasingly used to create stories for children. Since bedtime stories can shape children's perceptions of social roles, this raises concerns about whether LLMs adapt narrat...

MIRAGE: A Framework for Multi-hop Reasoning under Dynamic Knowledge Injection
Multi-hop Question Answering (MQA) requires large language models (LLMs) to retrieve and synthesize multiple pieces of evidence into a coherent reasoning path, which is essential for complex tasks. Ho...

Grading Executable Legal Rules Against Independent Records: Transitional Provisions and Korean SME Status
Laws are increasingly turned into programs that decide cases, such as whether a firm was a small or medium enterprise (SME) on a given date, and large language models (LLMs) now write them. The progra...

A Hybrid RAG Framework for Deceptive Review Detection: Integrating RoBERTa-LoRA, FAISS-Based Retrieval, and LLM Reasoning
The growth of deceptive online opinions poses a critical risk of misinformation and fraud. This paper proposes a Retrieval-Augmented Generation (RAG) system to automatically distinguish spam reviews. ...

Compression Effects on Low-Resource Multilingual Translation
We present a pilot study characterising the effect of post-training quantisation on multilingual machine translation quality and inference cost for three African languages - Hausa, Swahili, and Yoruba...
加载中...
已经到底啦