view article Article From Golden Gate Bridge to Broken JSON: Why Anthropic's SAE Steering Fails for Structured Output 4 days ago • 17
view article Article Community Evals: Because we're done trusting black-box leaderboards over the community +5 8 days ago • 61
view article Article Nemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3’s Top Model 7 days ago • 25
view article Article Training Design for Text-to-Image Models: Lessons from Ablations 8 days ago • 55
view article Article Llasa Goes RL: Training LLaSA with GRPO for Improved Prosody and Expressiveness Nov 5, 2025 • 11
Nemotron ColEmbed V2 Collection State-of-the-Art Late Interaction Vision-Language Embedding Models • 3 items • Updated 7 days ago • 10
view article Article Security, Governance and Performance for Dell On-Prem AI Builders 21 days ago • 7
view article Article AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality 21 days ago • 31
view article Article LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family 23 days ago • 80
LightOnOCR-2 🦉 Collection LightOnOCR-2-1B: a lightweight high-performance end-to-end OCR model family • 12 items • Updated 21 days ago • 22
view article Article How We Built a Semantic Highlight Model To Save Token Cost for RAG 28 days ago • 64
view article Article The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator Dec 17, 2025 • 47