🔥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

SEEING THROUGH YOUR EYES 👁️: Excited to share our new paper (which is out now!!) with Wenbo Tang, Annabella, Thokozile Nyasulu, Maddie Wolf, AntonioFR @azayhara : we discovered a novel sleep microstructure that promotes memory replay! nature.com/articles/s4158… 🧵 1/12👇

Our paper published in Nature Communications! We used evidence accumulation model to explain why people make decisions slower after rule switch. There is a reduction in sensory weight, perhaps reflecting the difficulty of switching sensory readout. Luo Tianlin nature.com/articles/s4146…

663 days since the senseless tragedy that took An, we present a manuscript that reports some of the discoveries that she left us. biorxiv.org/content/10.110…

Agent Laboratory Using LLM Agents as Research Assistants

😍

ASAP learns diverse, agile, whole-body humanoid motions via learning a residual action model from the real world to align sim and real physics, enabling motions that were previously difficult to achieve. It has two stages: Stage 1 pretrains a phase-based motion tracking policy

Two absolutely fantastic bioimage analysis papers out today offering exceptional, generalizable tools for segmentation--Cellpose3 and Segment Anything for Microscopy. (1/3)

🧠 By tracking the activity of thousands of neurons over days & weeks during learning, Janelia researchers led by Weinan Sun Johan Winnubst & Nelson Spruston have systematically detailed, step by step, how cognitive maps form in the brain’s hippocampus. 🗺️ janelia.org/news/mapmaking…

I just improved the open-sourced ASAP code (github.com/LeCAR-Lab/ASAP) with a training command to replicate Cristiano Ronaldo’s iconic "Siuuu" jump in just 2 hours on two RTX 4090 GPUs! Now, your humanoid can pull off elite athletic moves—give it a try! ⚽🤖🔥

Congrats!

🚀#CVPR2025, we propose #HumanMM, recovering human motion in world coordinates from videos with frequent shot transitions. We believe the system will serve as a key component in future markless mocap pipeline. 👇Teaching characters to play table tennis by seeing an Olympics live.

MouseGPT: A Large-scale Vision-Language Model for Mouse Behavior Analysis biorxiv.org/content/10.110… #biorxiv_behav

🥳🥳 I am so excited that HSMR has been selected as CVPR 2025 Oral paper with three Accepts(rating 5)! See you in Nashville!

Excited to share work from mbruchas & John A Rogers labs led by myself, Min-Kyu Lee and Mingzheng Wu with critical help from NeuroLux, Raudel Avila, Genia Kozorovitskiy, and Dr. Yonggang Huang. Work proudly supported by NIDAnews, National Institute of Mental Health (NIMH), and the NIH BRAIN Initiative.

Another step toward a foundation model of the mouse brain: "Neural Encoding and Decoding at Scale (NEDS)" Trained on neural and behavioral data from 70+ mice, NEDS achieves state-of-the-art prediction of behavior (decoding) and neural responses (encoding) on held-out animals.

Check out our latest profile! Dr. Eve Marder (Marder Lab) studies the stability and flexibility of neural circuit function. Follow the link below to learn more! storiesofwin.org/profiles/2025/… #StoriesofWiN #WomenInNeuroscience #WomenInNeuro

I'm experimenting with using SAM2 for automatic tracking of NBA players; it's mind-blowing how well this model performs out of the box. we might even add a SAM2-based tracker to the trackers package at some point. trackers: github.com/roboflow/track…

What happens in the brain when we become conscious of something? Fascinating nature study spanning fMRI, MEG, and iEEG across 256 people found that consciousness is anchored in stable, content-rich activity in visual/parietal cortex, not in prefrontal cortex as previously

Our computer vision textbook is now available for free online here: visionbook.mit.edu We are working on adding some interactive components like search and (beta) integration with LLMs. Hope this is useful and feel free to submit Github issues to help us improve the text!

Recording of my talk "From Sim2Real 1.0 to 4.0 for Humanoid Whole-Body Control and Loco-Manipulation" (at ICRA&CVPR workshops and Caltech): youtu.be/AGNcw4qnimk?si… Slides: drive.google.com/file/d/1h5MxNH…