Introducing arXivQA: Training retrieval agents for arXiv search We curate a multi-hop arXiv dataset based on real queries and use rubric-as-rewards to train a Qwen model for production-grade retrieval Our latest blog details our experience training with both RLVR and rubrics
MACHINE LEARNING
-
Karpathy’s AutoResearch Enables AI Self-Improvement Loop
By
–
You can now give an AI a GPU and let it improve its own model overnight. This repo turns LLM research into an automated search loop. @karpathy just open-sourced a system that lets AI iterate on its own training code. Karpathy’s AutoResearch turns LLM improvement into an
-
Portfolio Strategy: Specialized Models Beat One-Size-Fits-All
By
–
The winning strategy is not one model to rule them all. It’s a portfolio: • reasoning models
• fast models
• research models
• coding agents
• multimodal systems
A model for every job. -
No-Code AI and Top 10 Machine Learning Trends for 2025
By
–
How could you use no-code AI to boost your projects? Top 10 Machine Learning Trends to Watch in 2025 https://
graphite-note.com/machine-learni
ng-trends/
… #AI #MachineLearning #IoT #WMC26 #5G -
Soumith Celebrates Continued Partnership with NVIDIA and PyTorch
By
–
to me personally, this continues the years of close partnership with NVIDIA I've had via @PyTorch. working with them is always such a joy!
→ View original post on X — @soumithchintala, 2026-03-10 13:52 UTC
-
New AI Results on Previously Unknown Technology Created
By
–
I'm getting strong results for technology the absolutely cannot be in the training data because I just created it myself
-
Structured-RAG: Solving Aggregative Queries in RAG Systems
By
–
Standard RAG falls apart on aggregative queries. Things like "average ARR for companies with >1k employees" require reasoning across hundreds of docs, and vector retrieval just can't handle that reliably. We built Structured-RAG to fix this:
– induces a schema from your -
Autonomous Networks: From Telecom Engineering to AI Data Orchestration
By
–
One of the clearest signals I observed at #MWC26: Autonomous networks are no longer just a telecom engineering story. Conversations at the @IBM booth highlighted something bigger, autonomy is becoming an AI and data orchestration challenge. My latest analysis.
-
Run Claude Code with local LLMs for free
By
–
Run Claude Code using local LLMs for FREE. No API costs. No data leaving your machine. Here's how it works: Claude Code lets you swap its backend via a single env variable. Point `ANTHROPIC_BASE_URL` to a local llama.cpp server, and it'll route all requests to whatever model
-
MiniMax M2.5 Open Source: Claude Opus Performance at 95% Lower Cost
By
–
MiniMax M2.5 went fully open source. If you're running OpenClaw, this changes the game. It's basically Claude Opus performance but 95% cheaper. It scores 80.2% on SWE-Bench Verified. OpenClaw's been great for persistent AI agents with memory, tools, and messaging integrations.