Ze An
Ze An — researcher or builder tracked in the Angestrom contributor network.
Papers · 3
VoiceMem: Streaming Dual-Brain Memory for Real-Time Interaction
Conversational systems, such as duplex speech language models (SLMs), still lack a streaming, accurate, and empathetic memory system as their soul. We introduce VoiceMem, a simple memory architecture with a parallel informational left brain, an emotional right brain, and streaming memory I/O mechanisms. We further build a complete pipeline for memory-aware SLM training, long-horizon evaluation, and decoupled deployment with interchangeable memory backends. Experiments and real-world deployment show three advantages: i) Accuracy: under top-5 retrieval, the left brain outperforms classical syste
Deriving Scaling Laws for OpenEuroLLM Models: Learning Rate, Batch Size and Loss
We study the scaling behavior of learning rate and batch size in pretraining dense large language models on English-prevalent corpora. Beyond scaling \textit{jointly optimal} learning rates and batch sizes, we investigate their \textit{marginal} evolution with model capacity and data scale and develop a model that captures these relationships. As we employ a Warmup-Stable-Decay learning rate schedule, we further investigate the gains from learning rate annealing over a broad range of hyperparameters settings, models and data budgets, and whether the optimal learning rate and batch size \textit
How Language Models Organize and Structure Moral Knowledge
How do large language models (LLMs) organize moral knowledge? Models detect moral content broadly, but detection is a low bar. We ask whether they go further, distinguishing moral foundations from one another and organizing the relationships between them geometrically. We train six independent linear probes on open-weight language models, one per Moral Foundations Theory (MFT) category (care/harm, fair/cheat, lib/oppress, loy/betray, auth/subv, sanc/degrade), and examine how the resulting directions relate to each other in representation space. We find the directions neither collapse into a
News · 3
UAE Artificial Intelligence Market Size and Trends 2025 to 2035 - precedenceresearch.com
<a href="https://news.google.com/rss/articles/CBMieEFVX3lxTE54MmFNaUJabWxZWFZ1UzhaWENtdGwzRHVkZ1NRSHA3SXRQWHd4NEg0dTJRWHRVRDU3Vl9walpqZjNRQjZITVZhaVlzYk91VVg5SFF0WFlCMUQ0TmZGZUdtMU9wMk00d0hjWm5CdjlQUXNqZW5VM2hXeg?oc=5" target="_blank">UAE Artificial Intelligence Market Size and Trends 2025 to 2035</a> <font color="#6f6f6f">precedenceresearch.com</font>
UAE Artificial Intelligence Market Size and Trends 2025 to 2035 - Precedence Research
<a href="https://news.google.com/rss/articles/CBMieEFVX3lxTE54MmFNaUJabWxZWFZ1UzhaWENtdGwzRHVkZ1NRSHA3SXRQWHd4NEg0dTJRWHRVRDU3Vl9walpqZjNRQjZITVZhaVlzYk91VVg5SFF0WFlCMUQ0TmZGZUdtMU9wMk00d0hjWm5CdjlQUXNqZW5VM2hXeg?oc=5" target="_blank">UAE Artificial Intelligence Market Size and Trends 2025 to 2035</a> <font color="#6f6f6f">Precedence Research</font>
Show HN: Shoehorn – Quantize any model down to run on your machine
<p>Working on Mac, Linux, and Windows now. I include a simple GUI to find new models and get things built and set up. It is working quite well across a few models for me. The GitHub README and DESIGN.md files go into detail of the how/why and it's working remarkably well so far. <a href="https://github.com/notactuallytreyanastasio/shoehorn" rel="nofollow">https://github.com/notactuallytreyanastasio/shoehorn</a></p> <hr /> <p>Comments URL: <a href="https://news.ycombinator.com/item?id=49346135">h