Did you ever wonder if your AI model trusted you ?
We just release a new paper TrustMI where we finds a linear trust direction in 6 LLMs.
π https://t.co/tzNKy1OnB1
π€ https://t.co/I44dMClXF4
So proud to have collaborated with an amazing team to build BrainWideBench! Especially excited about standardized evals across models, no more tuning baselines for future work, and a challenging task generalization setup (across animals and tasks).
Weβre excited to share BrainWideBench, a new benchmark for evaluating how models of neural activity generalize across animals and tasks!
A major bottleneck in modeling neural data today is rigorous and standardized evaluation. Modelling techniques need to be tested under multiple regimes and downstream tasks.
π Check out the paper here! https://t.co/zqyw7O8QyK
Special shoutout to @alx_adr, who co-led this work with me and contributed equally as co-first authors!
Excited to announce the 2nd Foundation Models for the Brain and Body Workshop at #NeurIPS2026 in Sydney, Australia! π§ π€
We invite short papers & demos on AI for neural, physiological, or behavioral data.
π Papers: Sep 4
π‘ Demos: Sep 19
Learn more π https://t.co/QrZljOGMgu
Excited to announce the 2nd Foundation Models for the Brain and Body Workshop at #NeurIPS2026 in Sydney, Australia! π§ π€
We invite short papers & demos on AI for neural, physiological, or behavioral data.
π Papers: Sep 4
π‘ Demos: Sep 19
Learn more π https://t.co/QrZljOGMgu
Most agent benchmarks assume static, perfect worlds. But real life is asynchronous, noisy, and ambiguous. π
π Meet Gaia2 + ARE: a new benchmark and open-source platform for creating environments and evaluating AI agents in (more) realistic environments.
New preprint! π§ π€
How do we build neural decoders that are:
β‘οΈ fast enough for real-time use
π― accurate across diverse tasks
π generalizable to new sessions, subjects, and species?
We present POSSM, a hybrid SSM architecture that optimizes for all three of these axes!
π§΅1/7
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.