· ai
[Paper] How to Correctly Report LLM-as-a-Judge Evaluations
Large language models (LLMs) are increasingly used as evaluators in lieu of humans. While scalable, their judgments are noisy due to imperfect specificity and s...
-
- · ai
[Paper] MortgageLLM: Domain-Adaptive Pretraining with Residual Instruction Transfer, Alignment Tuning, and Task-Specific Routing
Large Language Models (LLMs) demonstrate exceptional capabilities across general domains, yet their application to specialized sectors such as mortgage finance ...
- · ai
[Paper] Semantic Anchors in In-Context Learning: Why Small LLMs Cannot Flip Their Labels
Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating...
- · ai
[Paper] RosettaSpeech: Zero-Shot Speech-to-Speech Translation from Monolingual Data
The scarcity of parallel speech corpora critically hampers speech-to-speech translation (S2ST), often forcing reliance on complex, multi-stage pipelines. This p...
- · ai
[Paper] Towards Audio Token Compression in Large Audio Language Models
Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks, ranging from speech recognition to general audio understanding. How...
- · ai
[Paper] SpaceX: Exploring metrics with the SPACE model for developer productivity
This empirical investigation elucidates the limitations of deterministic, unidimensional productivity heuristics by operationalizing the SPACE framework through...
- · ai
[Paper] Readout-Side Bypass for Residual Hybrid Quantum-Classical Models
Quantum machine learning (QML) promises compact and expressive representations, but suffers from the measurement bottleneck - a narrow quantum-to-classical read...
- · ai
[Paper] Application of machine learning for infrastructure reconstruction programs management
The purpose of this article is to describe an adaptive decision-making support model aimed at improving the efficiency of engineering infrastructure reconstruct...
- · ai
[Paper] Pre-train to Gain: Robust Learning Without Clean Labels
Training deep networks with noisy labels leads to poor generalization and degraded accuracy due to overfitting to label noise. Existing approaches for learning ...
- · ai
[Paper] Ranking-Enhanced Anomaly Detection Using Active Learning-Assisted Attention Adversarial Dual AutoEncoders
Advanced Persistent Threats (APTs) pose a significant challenge in cybersecurity due to their stealthy and long-term nature. Modern supervised learning methods ...
- · ai
[Paper] LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework
Unit testing is an essential but resource-intensive step in software development, ensuring individual code units function correctly. This paper introduces Agone...
- · ai
[Paper] NNGPT: Rethinking AutoML with Large Language Models
Building self-improving AI systems remains a fundamental challenge in the AI domain. We present NNGPT, an open-source framework that turns a large language mode...