NEW Articles from Team or Enterprise organizations will get promoted to the main section.
Building a Multi-Task English NLP Cascade in the Open
Fused Batched Thin SVD, Part II: Extending the Jacobi Pipeline to N=6 with Configurable Convergence
Under The Hood : Trinity-Large-Thinking Disected
Under The Hood : Cohere Transcribe Deep Dive
Under The Hood : Kimi K2.5 Disected
Agentic Scientific Machine Learning for Neural Operators
•
1
Training low-bit ternary models with Axolotl
•
4
ModernBERTic: The First Modern Encoder for South Slavic Languages
The Geometry of “As an AI, I Don’t Have Feelings”
GAIA-v2-LILT: A Re-Audited Multilingual Agent Benchmark
The MCP Era Feels Like Déjà Vu
•
4
H2 Omega Confirmed, Paradigm Shift: Attempting to Disprove Omega As A Whole
•
1
Noetic Diffusion: From Brain Dynamics to Auditable AI Memory
Pallas for people who know JAX but not kernels yet
•
17
SPIRALbase, Part 2: A Working Memory for the Landscape
GOLDENER <br> Smart data split from embeddings and coreset selection
•
1
BiomedBERT Small: Medical models at 22.7M parameters
•
4
