SCA
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution
arXiv:2605.19228v2 Announce Type: replace Abstract: Large Language Models have achieved strong performance on reasoning tasks with objective answers by generating step-by-step solutions, but diagnosing where a multi-step reasoning trace might fail remains difficult. Confidence estimation offers a diagnostic signal, yet existing methods are restricted to final answers or require internal model access. In this paper, we introduce Stepwise Confidence Attribution (SCA), a framework for...
Evaluating and Calibrating LLM Confidence on Questions with Multiple Correct Answers
Announce Type: replace Abstract: Confidence calibration is essential for making large language models (LLMs) reliable, yet existing training-free methods have been primarily studied under single-answer question answering. In this paper, we show that these methods break down in the presence of multiple valid answers, where disagreement among equally correct responses leads to systematic underestimation of confidence.
AI Model Extraction Attacks: Bypassing Single-Client Assumptions in Defenses
Announce Type: new Abstract: Ensuring the protection of Artificial Intelligence (AI) models deployed in military Command and Control (C2) systems and critical infrastructure is essential for maintaining information superiority. Model Extraction Attacks (MEAs) pose a significant threat, as they enable adversaries to replicate proprietary models, compromise protected information, and prepare offline adversarial attacks. However, current defense strategies predominantly rely on the Single...
Book Dedications
To my sister, Dr. Soma Mohammed Mohammed Baroud. I write your name in full, because that is how it appeared on the white body bag that held your remains soon after the bomb was dropped. Dedications A random assortment of book dedications.
Rotatable Antenna-Enhanced Cell-Free Communication
arXiv:2512.04742v4 Announce Type: replace Abstract: Rotatable antenna (RA) is a promising technology that can exploit new spatial degrees-of-freedom (DoFs) by flexibly adjusting the three-dimensional (3D) boresight direction of antennas. In this letter, we investigate an RA-enhanced cell-free system for downlink transmission, where multiple RA-equipped access points (APs) cooperatively serve multiple single-antenna users over the same time-frequency resource. Specifically, we aim to maximize...
Rotatable Antenna-Enabled Mobile Edge Computing
Announce Type: replace Abstract: In the evolving landscape of mobile edge computing (MEC), enhancing communication reliability and computation efficiency to support increasingly stringent low-latency services remains a fundamental challenge. Rotatable antenna (RA) is a promising technology that introduces new spatial degrees of freedom (DoFs) to tackle this challenge. In this letter, we investigate an RA-enabled MEC system where antenna boresight directions can be independently adjusted to...
Show HN: DepsGuard – one command to harden NPM/pnpm/yarn/bun/uv configs
I kept seeing every npm/pnpm/yarn/bun/uv supply chain post end with the same advice (set a minimum release age, turn off install scripts), and while I know cooldowns are "controversial", they do work. But even if you convince people that they should set cooldowns, it seems many don't end up following through, not sure why, maybe because it means hand-editing five config files in five formats with five different time units, or perhaps the "it won't happen to me" syndrome (or "I'll do it...
Rotatable Antenna-Enhanced Cell-Free Communication
arXiv:2512.04742v3 Announce Type: replace Abstract: Rotatable antenna (RA) is a promising technology that can exploit new spatial degrees-of-freedom (DoFs) by flexibly adjusting the three-dimensional (3D) boresight direction of antennas. In this letter, we investigate an RA-enhanced cell-free system for downlink transmission, where multiple RA-equipped access points (APs) cooperatively serve multiple single-antenna users over the same time-frequency resource. Specifically, we aim to maximize...
Reasoning-Aware Multimodal Fusion for Hateful Video Detection
arXiv:2512.02743v2 Announce Type: replace Abstract: Hate speech in online videos is posing an increasingly serious threat to digital platforms, especially as video content becomes increasingly multimodal and context-dependent. Existing methods often struggle to effectively fuse the complex semantic relationships between modalities and lack the ability to understand nuanced hateful content. To address these issues, we propose an innovative Reasoning-Aware Multimodal Fusion (RAMF) framework.