Lightnews — Scholar-powered news

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(8/8) To apply POCO to your own work, find our open source code on github below 👇

github.com/yuvenduan/POCO

GitHub - yuvenduan/POCO: Official Implementation for POCO: Scalable Neural Forecasting through Population Conditioning

Official Implementation for POCO: Scalable Neural Forecasting through Population Conditioning - yuvenduan/POCO

github.com

4

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(7/8) Thanks to @deisseroth.bsky.social‬, @mishaahrens.bsky.social & Chris Harvey for their contributions, and to @kempnerinstitute.bsky.social & @harvardmed.bsky.social‬ for supporting computational neuroscience research.

Read the paper here: arxiv.org/abs/2506.14957

POCO: Scalable Neural Forecasting through Population Conditioning

Predicting future neural activity is a core challenge in modeling brain dynamics, with applications ranging from scientific investigation to closed-loop neurotechnology. While recent models of populat...

arxiv.org

1 4

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(6/8) Combined with its prediction speed and steady improvement from longer recordings/more sessions, POCO shows enormous potential for usage in larger brains & real-time neurotechnologies like “neuro-foundation models” for brain-computer interfaces (BCI).

1 2

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(5/8) Other time-series forecasting models perform well on synthetic/simulated data 🤖

POCO dominates in context-dense predictions based on REAL neural data 🧠

1 2

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(4/8) Beyond neural predictions, POCO's learned unit embeddings independently reproduce brain region clustering without any anatomical labels.

That means at single-cell resolution across entire brains, POCO mimics biological organization purely from neural activity patterns ✨

1 1 2

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(3/8) POCO forecasts how the brain will behave up to ~15 seconds into the future across behavioral data & species 🔮

After pre-training, POCO’s speed & flexibility allow it to adapt to new recordings with minimal fine-tuning, opening the door for real-time applications.

1 2

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(2/8) POCO was trained on spontaneous & task-specific behavior data from zebrafish, mice, & C. elegans. It combines a local forecaster with a population encoder capturing brain-wide patterns, so we track each neuron individually AND how the whole brain affects each cell 🧠

1 2

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 12

(1/8) New paper from our team!

Yu Duan & Hamza Chaudhry introduce POCO, a tool for predicting brain activity at the cellular & network level during spontaneous behavior.

Find out how we built POCO & how it changes neurobehavioral research 👇

arxiv.org/abs/2506.14957

1 14 49

Kanaka Rajan @kanakarajanphd.bsky.social · Sep 9

Thanks for having me at @camp_course and the @iitmadras Brain Center during my visit to India this summer!🥭

It was lovely to be back home, and a pleasure to work with the young scientists there who are finding their path in computational neuroscience 🧠

3 20

Kanaka Rajan @kanakarajanphd.bsky.social · Aug 14

Brilliant piece by @mattperich.bsky.social on neural manifolds 🌟

His ‪essay in @thetransmitter.bsky.social shows how this view changes the game in computational neuroscience, reproducing behavioral flexibility within finite neural constraints 🧠

www.thetransmitter.org/neural-dynam...

Neural population-based approaches have opened new windows into neural computations and behavior

Neural manifold properties can help us understand how animal brains deal with complex information, execute flexible behaviors and reuse common computations.

www.thetransmitter.org

11 49

Kanaka Rajan @kanakarajanphd.bsky.social · Aug 6

Check out @jordancollver.bsky.social’s‬ great illustration of modular RNNs training to work like a bio-brain🦾🧠

Thanks to Crearte for featuring our collaboration!

www.instagram.com/crearte.ca/p...

The Crearte Foundation | #ArtScience on Instagram: "When a neurobiologist is also a comic artist, science can have a whole new storyline. In a 2022 collaboration between the Rajan Lab at Harvard Med...

6 likes, 0 comments - crearte.ca on July 28, 2025: "When a neurobiologist is also a comic artist, science can have a whole new storyline. In a 2022 collaboration between the Rajan Lab at Harvard Med...

www.instagram.com

2 4 19

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(7/7) Congrats to Riley & Ryan on this work. Also huge thanks to collaborators Felix Berg, @raymondrchua.bsky.social‬, John Vastola, @joshlunger.bsky.social, Billy Qian & everyone who helps us kick the tires.

5

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(6/7) A 4096-unit agent that remembers, plans & navigates risks gives a “window-sized” brain we can watch neuron-by-neuron. ForageWorld is a perfect sandbox for testing cognitive map theories & offers a blueprint for ultra-efficient autonomous AI systems in a naturalistic world.

1 7

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(5/7) Analyzing the trained agent reveals an interpretable neural GPS: past & future positions can be linearly decoded over long horizons from the agent’s ‘neural’ activity, and a lightweight “predict-its-own-position” signal sharpens its compass even further.

1 1 4

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(4/7) What we see is planning & recall over hundreds of timesteps!

After a quick wander, the agent switches from exploring to visiting patches from memory: revisiting food not seen for over 500-1000 steps, skirting predator zones & timing resource visits.

1 5

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(3/7) For the agent’s “brain,” we used a lean recurrent network: 4096 units (<0.2% of the size of an ant brain), with only 10% connectivity & we let RL teach it what to do by trial & error.

1 6

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(2/7) Introducing ForageWorld: Each session spawns a large arena with lakes, predators & food patches that deplete over time. The AI agent must juggle hunger, thirst & fatigue in this virtual space.

The agent can only "see" a small patch around itself, so no bird’s-eye view.

1 1 12

Kanaka Rajan @kanakarajanphd.bsky.social · Jul 2

(1/7) New preprint from Rajan lab! 🧠🤖
@ryanpaulbadman1.bsky.social & Riley Simmons-Edler show–through cog sci, neuro & ethology–how an AI agent with fewer ‘neurons’ than an insect can forage, find safety & dodge predators in a virtual world. Here's what we built

Preprint: arxiv.org/pdf/2506.06981

3 32 94

Kanaka Rajan @kanakarajanphd.bsky.social · Jun 12

New work incoming at #RLDM2025 🤖 🐟

While we look forward to sharing our research, I'm mindful that many colleagues, including the authors of our second abstract, can't attend due to funding & travel issues.

Read the extended abstracts: rldm.org/program-2025/ #neuroskyence

Rajan Lab presentation at RLDM 2025, Investigating active electrosensing and communication in deep-reinforcement learning trained artificial fish collectives

1 6 21

Kanaka Rajan @kanakarajanphd.bsky.social · May 5

It was such a pleasure to host @kordinglab.bsky.social at @kempnerinstitute.bsky.social last week - thank you for joining us!

Kanaka and Konrad smiling together in front of a blackboard

1 2 29

Kanaka Rajan @kanakarajanphd.bsky.social · May 2

Big day for the Rajan lab at @harvardmed.bsky.social Friday Seminar Series 🌟

@satpreetsingh.bsky.social & Siyan Zhou gave outstanding talks on collective behaviors in artificial fish schools & disordered attractors in mice. I’m so proud of their work! 🤖🧠

2 18

Reposted by Kanaka Rajan

The Transmitter @thetransmitter.bsky.social · Apr 15

In his new book, published today, Nachum Ulanovsky calls on the field to embrace naturalistic conditions and move away from overcontrolled experiments.

#neuroskyence

www.thetransmitter.org/systems-neur...

‘Natural Neuroscience,’ an excerpt

In his new book, Nachum Ulanovsky calls on the field to embrace naturalistic conditions and move away from overcontrolled experiments.

www.thetransmitter.org

1 34 81

Kanaka Rajan @kanakarajanphd.bsky.social · Mar 28

Headed to #Cosyne2025?

Don't miss this workshop led by Rajan lab postdocs @satpreetsingh.bsky.social, @chingfang.bsky.social & @gzmozd.bsky.social on how complex tasks, agent-based models & theory-experiment cross-talk help us study how the brain works 🧠🤖

#neuroskyence @cosynemeeting.bsky.social

COSYNE 2025 workshop information for the Rajan Lab.
Monday, March 31, 9:00am-6:30pm features a Workshop titled 'Agent-based models in Neuroscience: Complex Planning, Embodiment, and Beyond'. The workshop explores digital agents and neural computations behind naturalistic behavior, bringing together experimentalists and theorists at the intersection of neuroscience, AI, and biomechanics.
Names and headshots for the organizers (Ching Fang, PhD; Satpreet Singh, PhD; and Gizem Ozdil, PhD) are included

8 37

Reposted by Kanaka Rajan

Kempner Institute at Harvard University @kempnerinstitute.bsky.social · Mar 28

Are you at @CosyneMeeting? Stop by the poster session today to see work from the #KempnerInstitute! #COSYNE2025

@cpehlevan.bsky.social @naoshigeuchida.bsky.social @blsabatini.bsky.social @kanakarajanphd.bsky.social @gershbrain.bsky.social

1 6

Kanaka Rajan @kanakarajanphd.bsky.social · Mar 28

Big showing from the Rajan Lab at @cosynemeeting.bsky.social!

We have posters on everything from multi-agent social foraging to neuromodulated neural networks. Catch us in Poster Sessions 2 & 3 🧠🤖

#Cosyne2025 #NeuroAI #CompSci #neuroskyence

COSYNE 2025 Rajan lab posters.
Friday, March 28 - Poster Session 2:
2-043: Emergent small-group foraging under variable group size, food scarcity, and sensory capabilities by Zhouyang (Hanson) Lu, Satpreet H Singh, Sonja Johnson-Yu, Aaron Walsman, Kanaka Rajan
2-058: 'Modeling rapid neuromodulation in the cortex-basal ganglia-thalamus loop' by Julia Costacurta and Yu Duan (co-first), John Assad, Kanaka Rajan and Scott Linderman (co-senior)
2-060: 'Measuring and Controlling Solution Degeneracy across Task-Trained RNNs' by Ann Huang, Satpreet Singh, Kanaka Rajan

Saturday, March 29 - Poster Session 3:

3-020: 'ForageWorld: RL agents in complex foraging arenas develop internal maps for navigation and planning' by Ryan Badman, Riley Simmons-Edler, Joshua Lunger, John Vastola, William Qian, Kanaka Rajan
3-109: 'Inhibition-stabilized disordered dynamics in mouse cortex during navigational decision-making' by Siyan Zhou, Ryan Badman, Charlotte Arlt, Kanaka Rajan, Christopher Harvey

9 37