AI News
Tencent Releases Hy3: An Open 295B Mixture-of-Experts (MoE) Model with 21B Active Parameters and 256K Context
Tencent’s Hy team released Hy3. Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model. It activates only 21B parameters per token. The weights ship under the Apache…
Grow, expand and leverage your business..
Building a Scaffold-Split Random Forest QSAR Co-Scientist for EGFR Inhibitor Discovery Using ChEMBL, RDKit, SHAP, and BRICS
banner("[2/9] BIOACTIVITY MINING (ChEMBL activities -> pIC50)") def pull_activities(tid, cap): url, rows…
Scaling Properties of Continuous Diffusion Spoken Language Models
Speech-only spoken language models (SLMs) lag behind text and text-speech models in…
Understanding Annotator Safety Policy with Interpretability
Safety policies define what constitutes safe and unsafe AI outputs, guiding data…
Fortress: A Case Study in Stabilizing Search Recommendations via Temporal Data Augmentation and Feature Pruning
In search and recommendation systems, predictive models often suffer from temporal instability…
Segmental Attention Decoding with Long Form Acoustic Encodings
We address the fundamental incompatibility of attention-based encoder-decoder (AED) models with long-form…
Revisiting ASR Error Correction with Specialized Models
Language models play a central role in automatic speech recognition (ASR), yet…
How to Run End-to-End Tests with Claude Code
like Claude Code can be used for a wide variety of tasks.…