STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
Paper: https://
arxiv.org/pdf/2504.01903
Project Page: https://
ucsc-vlaa.github.io/STAR-1
@jiqizhixin
-
STAR-1: Safer Alignment of Reasoning LLMs with 1K Data
By
–
-
STAR-1 Boosts Safety in Reasoning LLMs with Minimal Data
By
–
You can align reasoning LLMs with just 1K data now! UC Santa Cruz released STAR-1, showing that fine-tuning Large Reasoning Models with it boosts safety performance by 40% on average—while barely affecting reasoning ability.
-
Most Powerful 7B Language Model Uses Diffusion Reasoning
By
–
The most powerful 7B language model yet—and it's a diffusion reasoning model.
-
ATEC 2025 AI Robotics Competition Opens with $210K Prize
By
–
ATEC 2025 AI and Robotics Real-World Challenges, with a $210,000 prize pool, is now open for participants. Sign up now! https://
atecup.com/competitions/a
tec2025
… -
Agent S2 Technical Paper Released
By
–
The technical paper of Agent S2 is out! That's it. That's the tweet.
Link: https://
arxiv.org/pdf/2504.00906 -
MCP Server Safety: Essential Precautions for AI Integration
By
–
Be careful when adding MCP servers— not all of them are safe!
-
Breakthrough in Physical AI Technology Announced
By
–
Definitely a breakthrough in Physical AIs!👀🤪 https://t.co/9PlEBRJF2q
— 机器之心 JIQIZHIXIN (@jiqizhixin) 1 avril 2025Definitely a breakthrough in Physical AIs!
-
Vision Large Language Models Guide: Teaching LLMs Image Understanding
By
–
If you’re looking for a read on how to teach LLMs to understand images and videos, the newly released Vision Large Language Models (vLLMs) by @cwolferesearch is a great choice! Link: https://
cameronrwolfe.substack.com/p/vision-llms -
Sensationalism in AGI Research: Does the Title Matter?
By
–
"What the F*ck Is Artificial General Intelligence?"
Do we really need this kind of title just to grab attention for a paper?