Scalable and Secure AI Inference in Healthcare: A Comparative Benchmarking of FastAPI and Triton Inference Server on Kubernetes
arXiv:2602.00053v1 Announce Type: new Abstract: Efficient and scalable deployment of machine learning (ML) models is a prerequisite for modern production…
TEON: Tensorized Orthonormalization Beyond Layer-Wise Muon for Large Language Model Pre-Training
arXiv:2601.23261v2 Announce Type: replace-cross Abstract: The Muon optimizer has demonstrated strong empirical performance in pre-training large language models by performing…
DREAMS: A Social Exchange Theory-Informed Modeling of Misinformation Engagement on Social Media
arXiv:2602.01567v1 Announce Type: cross Abstract: Social media engagement prediction is a central challenge in computational social science, particularly for understanding…
Multimodal UNcommonsense: From Odd to Ordinary and Ordinary to Odd
arXiv:2602.01561v1 Announce Type: cross Abstract: Commonsense reasoning in multimodal contexts remains a foundational challenge in artificial intelligence. We introduce Multimodal…
Avoiding Premature Collapse: Adaptive Annealing for Entropy-Regularized Structural Inference
arXiv:2601.23039v2 Announce Type: replace-cross Abstract: Differentiable matching layers, often implemented via entropy-regularized Optimal Transport, serve as a critical approximate inference…
JAF: Judge Agent Forest
arXiv:2601.22269v1 Announce Type: new Abstract: Judge agents are fundamental to agentic AI frameworks: they provide automated evaluation, and enable iterative…
Token-Guard: Towards Token-Level Hallucination Control via Self-Checking Decoding
arXiv:2601.21969v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often hallucinate, generating content inconsistent with the input. Retrieval-Augmented Generation (RAG)…
On the Impact of Code Comments for Automated Bug-Fixing: An Empirical Study
arXiv:2601.23059v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly relevant in Software Engineering research and practice, with Automated…
Adaptive Edge Learning for Density-Aware Graph Generation
arXiv:2601.23052v1 Announce Type: cross Abstract: Generating realistic graph-structured data is challenging due to discrete structures, variable sizes, and class-specific connectivity…
Effective LoRA Adapter Routing using Task Representations
arXiv:2601.21795v2 Announce Type: replace-cross Abstract: Low-rank adaptation (LoRA) enables parameter efficient specialization of large language models (LLMs) through modular adapters,…