Tootfinder

CRScore : Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Manav Nitin Kapadnis, Atharva Naik, Carolyn Rose
https://arxiv.org/abs/2506.00296

CRScore++: Reinforcement Learning with Verifiable Tool and AI Feedback for Code Review
Reinforcement learning (RL) to improve code review comment generation requires handling unstructured outputs, making reinforcement learning (RL) feedback challenging. The two main RL approaches, namely RL with Verifiable Feedback (RLVR) and RL with AI Feedback (RLAIF), offer trade-offs: RLVR provides reliable feedback for structured tasks like code generation, while RLAIF works for unstructured outputs but is subjective. We bridge this gap with CRScore++, an RL framework that leverages both LLM…

AI-Assisted analysis of $^{28}$Si$^*$ $\rightarrow$ 7$\alpha$ break-up data
Theodoros Depastas, Aldo Bonasera, Joe Natowitz
https://arxiv.org/abs/2505.23920

AI-Assisted analysis of $^{28}$Si$^*$ $\rightarrow$ 7$α$ break-up data
Mid-weight $α$-conjugate nuclei are predicted to possess exotic toroid-like resonances with high angular momenta. The search for these states in $^{28}$Si$^*$ is the main point of two published experimental investigations of the peripheral $^{28}$Si + $^{12}$C reaction by Cao and collaborators and by Hannaman and collaborators. In this work, we develop a novel Artificial Intelligence (AI)-based machine learning method utilizing the Gaussian Mixture Model (GMM) to analyze available experimental…

Technical Evaluation of a Disruptive Approach in Homomorphic AI
Eric Filiol
https://arxiv.org/abs/2506.11954 https://arxiv.org/pdf/25…

Technical Evaluation of a Disruptive Approach in Homomorphic AI
We present a technical evaluation of a new, disruptive cryptographic approach to data security, known as HbHAI (Hash-based Homomorphic Artificial Intelligence). HbHAI is based on a novel class of key-dependent hash functions that naturally preserve most similarity properties, most AI algorithms rely on. As a main claim, HbHAI makes now possible to analyze and process data in its cryptographically secure form while using existing native AI algorithms without modification, with unprecedented perf…

Towards Structure-aware Model for Multi-modal Knowledge Graph Completion
Linyu Li, Zhi Jin, Yichi Zhang, Dongming Jin, Chengfeng Dou, Yuanpeng He, Xuan Zhang, Haiyan Zhao
https://arxiv.org/abs/2505.21973

Towards Structure-aware Model for Multi-modal Knowledge Graph Completion
Knowledge graphs (KGs) play a key role in promoting various multimedia and AI applications. However, with the explosive growth of multi-modal information, traditional knowledge graph completion (KGC) models cannot be directly applied. This has attracted a large number of researchers to study multi-modal knowledge graph completion (MMKGC). Since MMKG extends KG to the visual and textual domains, MMKGC faces two main challenges: (1) how to deal with the fine-grained modality information interacti…

This https://arxiv.org/abs/2501.14417 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDC_…

DeepServe: Serverless Large Language Model Serving at Scale
In this paper, we propose DEEPSERVE, a scalable and serverless AI platform designed to efficiently serve large language models (LLMs) at scale in cloud environments. DEEPSERVE addresses key challenges such as resource allocation, serving efficiency, and cold start latencies through four main design components. First, DEEPSERVE uses a simple serverless abstraction called the request-job-task model, which helps manage diverse AI workloads across posttraining and model-serving tasks. Second, DEEPS…