新闻
Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis
arXiv:2507.02176v1 Announce Type: cross Abstract: Modeling voice identity is challenging due to its multifaceted nature...
Analytic Subspace Routing: How Recursive Least Squares Works in Continual Learning of Large Language Model
arXiv:2503.13575v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) possess encompassing capabilities that can process...
Analysis of instruction-based LLMs’ capabilities to score and judge text-input problems in an academic setting
arXiv:2509.20982v1 Announce Type: new Abstract: Large language models (LLMs) can act as evaluators, a role...
An Implementation on Building Advanced Multi-Endpoint Machine Learning APIs with LitServe: Batching, Streaming, Caching, and Local Inference
In this tutorial, we explore LitServe, a lightweight and powerful serving framework that allows us...
An Exploratory Analysis on the Explanatory Potential of Embedding-Based Measures of Semantic Transparency for Malay Word Recognition
arXiv:2505.05973v1 Announce Type: new Abstract: Studies of morphological processing have shown that semantic transparency is...
An Efficient Computational Framework for Discrete Fuzzy Numbers Based on Total Orders
arXiv:2511.17080v1 Announce Type: cross Abstract: Discrete fuzzy numbers, and in particular those defined over a...
An Audit and Analysis of LLM-Assisted Health Misinformation Jailbreaks Against LLMs
arXiv:2508.10010v1 Announce Type: new Abstract: Large Language Models (LLMs) are a double-edged sword capable of...
An AI-Powered Research Assistant in the Lab: A Practical Guide for Text Analysis Through Iterative Collaboration with LLMs
arXiv:2505.09724v1 Announce Type: new Abstract: Analyzing texts such as open-ended responses, headlines, or social media...
An Agentic System for Rare Disease Diagnosis with Traceable Reasoning
arXiv:2506.20430v1 Announce Type: new Abstract: Rare diseases collectively affect over 300 million individuals worldwide, yet...
AMD unveils new Threadripper CPUs and Radeon GPUs for gamers at Computex 2025
AMD held a Computex press event to introduce its Radeon RX 9060 XT graphics cards...
Amazon Develops an AI Architecture that Cuts Inference Time 30% by Activating Only Relevant Neurons
Amazon researchers developed a new AI architecture that cuts inference time by 30% by selecting...
AlphaDecay: Module-wise Weight Decay for Heavy-Tailed Balancing in LLMs
arXiv:2506.14562v3 Announce Type: replace Abstract: Weight decay is a standard regularization technique for training large...
