🔥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

I’m amazed at how many high-performers have serious or chronic health issues like TMJ, severe muscle pain, carpal tunnel. I’ve dealt with my share of health issues; imho it all comes down to stress. A story about stress and what I’ve learned from managing it... **Read On**

Holy pope, this is paper from the new pope on bayes theorem

Angjoo Kanazawa Angjoo Kanazawa and I taught CS 280, graduate computer vision, this semester at UC Berkeley. We found a combination of classical and modern CV material that worked well, and are happy to share our lecture material from the class. cs280-berkeley.github.io Enjoy!

🧵5 Top Free Alternatives to BioRender for Scientific Illustrations! These five websites offer free scientific illustrations for biologists. Great for presentations, research papers and other research communication needs. Save and share the post!

🚀Let’s Think Only with Images. No language and No verbal thought.🤔 Let’s think through a sequence of images💭, like how humans picture steps in their minds🎨. We propose Visual Planning, a novel reasoning paradigm that enables models to reason purely through images.

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

Your language model is wasting half of its layers to just refine probability distributions rather than doing interesting computations. In our paper, we found that the second half of the layers of the Llama 3 models have minimal effect on future computations. 1/6

Check out our new work exploring how to make robots sense touch more like our brains! Surprisingly, ConvRNNs aligned best with mouse somatosensory cortex and even passed the NeuroAI Turing Test on current neural data. We also developed new tactile-specific augmentations for

This aquatic microorganism is called Bdelloid Rotifer. It has chainsaw like mouth.

New Paper! Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents A longstanding goal of AI research has been the creation of AI that can learn indefinitely. One path toward that goal is an AI that improves itself by rewriting its own code, including any code

same data

Looking forward to speaking today at Harvard’s Kempner Institute at Harvard University NeuroAI conference on theories of learning, creativity and reasoning. Looks like a great set of speakers. Virtual attendance is possible: kempnerinstitute.harvard.edu/frontiers-in-n…

Our first NeuroAgent! 🐟🧠 Excited to share new work led by the talented Reece Keller, showing how autonomous behavior and whole-brain dynamics emerge naturally from intrinsic curiosity grounded in world models and memory. Some highlights: - Developed a novel intrinsic drive

BREAKING: Apple just proved AI "reasoning" models like Claude, DeepSeek-R1, and o3-mini don't actually reason at all. They just memorize patterns really well. Here's what Apple discovered: (hint: we're not as close to AGI as the hype suggests)

A good reminder of what to keep in mind while applying HMMs (or discrete-state models more generally) to physical/non-jumpy data

If you're at #RLDM2025, check out our contributed talk at Session 3 (Fri 6/13, 12:10pm), presented by my brilliant co-first-author on this project Sonja Johnson-Yu! Wasn't able to make it in person, but would love to hear your thoughts Kempner Institute at Harvard University Harvard Medical School

guys?

(1/n) Since its publication in 2017, PPO has essentially become synonymous with RL. Today, we are excited to provide you with a better alternative - EPO.

Agents training in RL gym