Training Gemma-3 for Structured Mathematical Reasoning with Tunix GRPO, LoRA Adapters, and GSM8K Rewards
import importlib.util, os, shutil as _sh if importlib.util.find_spec(“tunix”) is None: print(“Installing Tunix + JAX ecosystem — this takes ~5-8 min…”) %pip install -q ipywidgets tensorboardX transformers grain nest_asyncio %pip install…
Meituan Releases LongCat-2.0: A 1.6T-Parameter Open MoE Model with Native 1M Context and LongCat Sparse Attention
Meituan has released LongCat-2.0, a large-scale Mixture-of-Experts (MoE) language model. It carries 1.6 trillion total parameters and activates about 48 billion per token. The model targets agentic coding: code understanding,…
LlamaIndex ‘legal-kb’: Agentic Retrieval over Index v2 with retrieve, find, read, and grep Tools
LlamaIndex has published legal-kb, a public reference application on GitHub. It is described as a knowledge base for legal documents, powered by LlamaIndex Index v2 (the LlamaParse Platform). The project…
Qwen’s Former Lead on What Hybrid Thinking Got Wrong — and Why He Now Backs Agents
Junyang Lin was the technical lead of Alibaba’s Qwen project. He announced he was stepping down on March 3, 2026. He now lists himself as an independent researcher on his…
Structured PDF-to-JSON: A Guide to Open-Source Extraction Models in 2026
Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become…
NVIDIA HORIZON: A Hands-Free Agent that Evolves Git Worktrees and Hits 100% RTL Benchmark Completion
NVIDIA Research introduced HORIZON, a hands-free agent framework for hardware design. It treats hardware design as repository-level code evolution. This research team exercises the register-transfer level (RTL) instantiation. A structured…
Anthropic Launches Claude Science Beta: A Multi-Agent AI Workbench for Reproducible Genomics, Proteomics, and Cheminformatics Pipelines
This week, Anthropic released Claude Science. It is an app for scientists, available in beta. It runs on Anthropic’s existing Claude models, not a new model. The app targets researchers…
NVIDIA AI Introduces ASPIRE: A Self-Improving Robotics Framework Reaching 31% Zero-Shot on LIBERO-Pro Long Tasks
Traditional robot programming is hard to scale. It requires orchestrating multimodal perception, physical contact dynamics, diverse configurations, and execution failures by hand. Code-as-policy systems let language models compose these into…
Mistral AI Releases Leanstral 1.5: An Apache-2.0 Lean 4 Code Agent Model Solving 587 of 672 PutnamBench Problems
Today, Mistral AI released Leanstral 1.5. It is a code agent model built for Lean 4. The release targets automated theorem proving and proof engineering. Weights are open under Apache…
Designing a Schema-Guided Invoice Intelligence Pipeline with lift-pdf for Accounts-Payable Extraction, Validation, and Ledger Generation
def render_pdf(d, path): “””Draw a realistic one-page invoice: header, meta, bill/ship, line items, totals, payment.””” from reportlab.lib.pagesizes import LETTER from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle from reportlab.lib.units import inch from reportlab.lib…









