🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

im getting a sense of why "complex" number is named that way...

😂

Introducing CaRL: Learning Scalable Planning Policies with Simple Rewards We show how simple rewards enable scaling up PPO for planning. CaRL outperforms prior learning-based approaches on nuPlan Val14 and CARLA longest6 v2, using less inference compute. arxiv.org/abs/2504.17838

“Physics from Symmetry” is an excellent book that derives essential equations in physics, including elementary particles, properties (e.g, spin), fundamental forces, quantum and classical mechanics, and electromagnetism, using only the symmetry under Lorentz transformation.

📣 Excited to share our #CVPR2025 Spotlight paper and my internship project Wayve: SimLingo. A Vision-Language-Action (VLA) model that achieves state-of-the-art driving performance with language capabilities. Code: github.com/RenzKa/simlingo Paper: arxiv.org/abs/2503.09594

New Paper: Continuous Thought Machines 🧠 Neurons in brains use timing and synchronization in the way that they compute, but this is largely ignored in modern neural nets. We believe neural timing is key for the flexibility and adaptability of biological intelligence. We

“When brain waves are in phase, meaning the peaks and valleys of the waves are aligned, local groups of neurons in the brain’s cortex can share information to produce conscious cognitive functions such as attention, perception and reasoning”. search.app/4kKALDgvtdE6UT…

Could a major opportunity to improve representation in deep learning be hiding in plain sight? Check out our new position paper: Questioning Representational Optimism in Deep Learning: The Fractured Entangled Representation Hypothesis. The idea stems from a little-known

First time in London🎸

.SSI Inc.

It's interesting to see that entropy minimization seems like a superficial objective at first glance, yet it turns out to improve LLM performance. It was also considered quite effective in the older semi-supervised learning literature.

Announcing the first fully AI-generated scientific discovery to pass the highest level of peer review – the main track of an A* conference (ACL 2025). Several groups have shown AI-generated work at workshops, but main conference acceptance is a far higher bar. While workshops

Our world is built from locality but our current AI models are not. What does this imply?

One of the most compelling math textbooks I’ve ever found

I visited OIST this winter. OIST is a relatively newly established university with a truly unique environment surrounded by beautiful tropical oceans and nature, with a very international feel on its campus. (80% international students and over 60% international faculty).

what are some career paths which merge mathematics, visual aesthetics, music and writing?

There are traditionally two types of research: problem-driven research and method-driven research. As we’ve seen with large language models and now AlphaEvolve, it should be very clear now that total method-driven research is a huge opportunity. Problem-driven research is nice