Training low-bit ternary models with Axolotl
axolotl-ai-co
• • 5NEW Articles from Team or Enterprise organizations will get promoted to the main section.
ModernBERTic: The First Modern Encoder for South Slavic Languages
permitt
• The Geometry of “As an AI, I Don’t Have Feelings”
anicka
• GAIA-v2-LILT: A Re-Audited Multilingual Agent Benchmark
Lilt-org
• • 1The MCP Era Feels Like Déjà Vu
Navid-AI
• • 5AI evals are becoming the new compute bottleneck
evaleval
• • 29H2 Omega Confirmed, Paradigm Shift: Attempting to Disprove Omega As A Whole
AbstractPhil
• • 1Noetic Diffusion: From Brain Dynamics to Auditable AI Memory
NoeticDiffusion
• Pallas for people who know JAX but not kernels yet
ariG23498
• • 21SPIRALbase, Part 2: A Working Memory for the Landscape
NoeticDiffusion
• GOLDENER <br> Smart data split from embeddings and coreset selection
Yann-CV
• • 1BiomedBERT Small: Medical models at 22.7M parameters
NeuML
• • 4How Shabbat Cleans Jerusalem's Air (For One Day A Week)
danielrosehill
• WikiNER: Your Ultimate Turkish NER Set
turkish-nlp-suite
• • 1Turkish spaCy models
turkish-nlp-suite
• • 1NVIDIA H100 Price in India 2026: Buy, Rent, or Get It for 70% Less Through the Government?
daya-shankar
• Adaptive Ultrasound Imaging with Physics-Informed NV-Raw2Insights-US AI
nvidia
• • 5ChargebackOps: Teaching LLM Agents to Fight Credit Card Disputes
mitudrudutta
• • 1OpenEnv: Training an LLM to Manage Enterprise Email
saisatwik1234567
• Running AI agents to automate outreach at scale
nielsr
• • 14