Running 6 Pi Agent · Soyuz (llama.cpp WebGPU) 🛰 6 In-browser coding agent — Soyuz 4B via llama.cpp WebGPU
RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation Paper • 2605.04523 • Published May 6 • 47
Calibri: Enhancing Diffusion Transformers via Parameter-Efficient Calibration Paper • 2603.24800 • Published Mar 25 • 69
Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate Structures Paper • 2603.16475 • Published Mar 17 • 13
Improving Multi-step RAG with Hypergraph-based Memory for Long-Context Complex Relational Modeling Paper • 2512.23959 • Published Dec 30, 2025 • 111
Vikhrmodels/Vikhr-Llama-3.2-1B-Instruct-abliterated Text Generation • 1B • Updated Oct 5, 2024 • 101 • • 8
Vikhrmodels/Vikhr-Nemo-12B-Instruct-R-21-09-24 Text Generation • 12B • Updated Oct 25, 2024 • 5.45k • • 139